feat: update v8

.gitignore

@@ -1,7 +1,6 @@
 .DS_Store
-yolov5s.pt
+yolo*.pt
 # __pycache__
 gradio_queue.db
 __pycache__
-.venv
-__pycache__
+.venv

README.md

@@ -1,5 +1,5 @@
 ---
-title: Yolov5 Ndl Layout
+title: Yolov8 Ndl Layout
 emoji: 🐢
 colorFrom: indigo
 colorTo: red

app.py

@@ -1,38 +1,65 @@
 import gradio as gr
-import torch
-from PIL import Image
 import json
 
-# Model
-model = torch.hub.load('ultralytics/yolov5', 'custom', path='best.pt', source="local")
+from ultralyticsplus import YOLO, render_result
 
-def yolo(im, size=1024):
-    g = (size / max(im.size))  # gain
-    im = im.resize((int(x * g) for x in im.size), resample=Image.Resampling.LANCZOS)  # resize
+# Model Heading and Description
+model_heading = "YOLOv8 NDL-DocL Datasets"
+description = """YOLOv8 NDL-DocL Datasets Gradio demo for object detection. Upload an image or click an example image to use."""
 
-    results = model(im)  # inference
+article = "<p style='text-align: center'>YOLOv5 NDL-DocL Datasets is an object detection model trained on the <a href=\"https://github.com/ndl-lab/layout-dataset\">NDL-DocL Datasets</a>.</p>"
 
-    results.render()
+image_path= [
+       
+    ['『源氏物語』(東京大学総合図書館所蔵).jpg', 0.25, 0.45],
+     ['『源氏物語』(京都大学所蔵).jpg', 0.25, 0.45],
+      ['『平家物語』(国文学研究資料館提供).jpg', 0.25, 0.45]
+]
 
-    df = results.pandas().xyxy[0].to_json(orient="records")
-    res = json.loads(df)
+# Load YOLO model
+model = YOLO('model_- 19 may 2024 15_13.pt')
 
-    return [
-        Image.fromarray(results.imgs[0]),
-        res
-    ]
+def yolov8_img_inference(
+    image: gr.Image = None,
+    conf_threshold: gr.Slider = 0.25,
+    iou_threshold: gr.Slider = 0.45,
+):
+    """
+    YOLOv8 inference function
+    Args:
+        image: Input image
+        conf_threshold: Confidence threshold
+        iou_threshold: IOU threshold
+    Returns:
+        Rendered image
+    """
+    results = model.predict(image, conf=conf_threshold, iou=iou_threshold)
+    render = render_result(model=model, image=image, result=results[0])            
 
+    json_data = json.loads(results[0].tojson())
+    
+    return render, json_data
 
-inputs = gr.Image(type='pil', label="Original Image")
-outputs = [
-    gr.Image(type="pil", label="Output Image"),
-    gr.JSON(label="Output JSON")
+    
+inputs_image = [
+    gr.Image(type="filepath", label="Input Image"),
+    gr.Slider(minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold"),
+    gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold"),
 ]
 
-title = "YOLOv5 NDL-DocL Datasets"
-description = "YOLOv5 NDL-DocL Datasets Gradio demo for object detection. Upload an image or click an example image to use."
-article = "<p style='text-align: center'>YOLOv5 NDL-DocL Datasets is an object detection model trained on the <a href=\"https://github.com/ndl-lab/layout-dataset\">NDL-DocL Datasets</a>.</p>"
+outputs_image =[
+    gr.Image(type="filepath", label="Output Image"),
+    gr.JSON(label="Output JSON")
+]
+demo = gr.Interface(
+    fn=yolov8_img_inference,
+    inputs=inputs_image,
+    outputs=outputs_image,
+    title=model_heading,
+    description=description,
+    examples=image_path,
+    article=article,
+    cache_examples=False
+)
 
-examples = [['『源氏物語』(東京大学総合図書館所蔵).jpg'], ['『源氏物語』(京都大学所蔵).jpg'], ['『平家物語』(国文学研究資料館提供).jpg']]
-demo = gr.Interface(yolo, inputs, outputs, title=title, description=description, article=article,examples=examples)
-demo.launch(share=False)
+demo.launch(share=False)

init.sh

@@ -1,6 +1,3 @@
-rm best.pt
-gdown https://drive.google.com/uc?id=1DduqMfElGLPYWZTbrEO8F3qn6VPOZDPM
-
 wget https://iiif.dl.itc.u-tokyo.ac.jp/iiif/genji/TIFF/A00_6587/01/01_0004.tif/full/1024,/0/default.jpg -O "『源氏物語』(東京大学総合図書館所蔵).jpg"
 
 wget https://rmda.kulib.kyoto-u.ac.jp/iiif/RB00007030/01/RB00007030_00003_0.ptif/full/1024,/0/default.jpg -O "『源氏物語』(京都大学所蔵).jpg"

best.pt → model_- 19 may 2024 15_13.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497dd54a738a54abfc938507c16b77e4e46930372e6e189ae87895aa5bba0b7c
-size 173348189
+oid sha256:8acb10e585c68b31142f2f4470606da52ce054ab467368b6bfe22ca547620e12
+size 136737193

requirements.txt

@@ -1,5 +1 @@
-torch
-Pillow
-opencv-python
-torchvision
-seaborn
+ultralyticsplus

ultralytics/yolov5/export.py

@@ -1,559 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit
-
-Format                      | `export.py --include`         | Model
----                         | ---                           | ---
-PyTorch                     | -                             | yolov5s.pt
-TorchScript                 | `torchscript`                 | yolov5s.torchscript
-ONNX                        | `onnx`                        | yolov5s.onnx
-OpenVINO                    | `openvino`                    | yolov5s_openvino_model/
-TensorRT                    | `engine`                      | yolov5s.engine
-CoreML                      | `coreml`                      | yolov5s.mlmodel
-TensorFlow SavedModel       | `saved_model`                 | yolov5s_saved_model/
-TensorFlow GraphDef         | `pb`                          | yolov5s.pb
-TensorFlow Lite             | `tflite`                      | yolov5s.tflite
-TensorFlow Edge TPU         | `edgetpu`                     | yolov5s_edgetpu.tflite
-TensorFlow.js               | `tfjs`                        | yolov5s_web_model/
-
-Requirements:
-    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu  # CPU
-    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow  # GPU
-
-Usage:
-    $ python path/to/export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ...
-
-Inference:
-    $ python path/to/detect.py --weights yolov5s.pt                 # PyTorch
-                                         yolov5s.torchscript        # TorchScript
-                                         yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
-                                         yolov5s.xml                # OpenVINO
-                                         yolov5s.engine             # TensorRT
-                                         yolov5s.mlmodel            # CoreML (MacOS-only)
-                                         yolov5s_saved_model        # TensorFlow SavedModel
-                                         yolov5s.pb                 # TensorFlow GraphDef
-                                         yolov5s.tflite             # TensorFlow Lite
-                                         yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
-
-TensorFlow.js:
-    $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
-    $ npm install
-    $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
-    $ npm start
-"""
-
-import argparse
-import json
-import os
-import platform
-import subprocess
-import sys
-import time
-import warnings
-from pathlib import Path
-
-import pandas as pd
-import torch
-import torch.nn as nn
-from torch.utils.mobile_optimizer import optimize_for_mobile
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[0]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
-
-from models.common import Conv
-from models.experimental import attempt_load
-from models.yolo import Detect
-from utils.activations import SiLU
-from utils.datasets import LoadImages
-from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, check_version, colorstr,
-                           file_size, print_args, url2file)
-from utils.torch_utils import select_device
-
-
-def export_formats():
-    # YOLOv5 export formats
-    x = [['PyTorch', '-', '.pt', True],
-         ['TorchScript', 'torchscript', '.torchscript', True],
-         ['ONNX', 'onnx', '.onnx', True],
-         ['OpenVINO', 'openvino', '_openvino_model', False],
-         ['TensorRT', 'engine', '.engine', True],
-         ['CoreML', 'coreml', '.mlmodel', False],
-         ['TensorFlow SavedModel', 'saved_model', '_saved_model', True],
-         ['TensorFlow GraphDef', 'pb', '.pb', True],
-         ['TensorFlow Lite', 'tflite', '.tflite', False],
-         ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False],
-         ['TensorFlow.js', 'tfjs', '_web_model', False]]
-    return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'GPU'])
-
-
-def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
-    # YOLOv5 TorchScript model export
-    try:
-        LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
-        f = file.with_suffix('.torchscript')
-
-        ts = torch.jit.trace(model, im, strict=False)
-        d = {"shape": im.shape, "stride": int(max(model.stride)), "names": model.names}
-        extra_files = {'config.txt': json.dumps(d)}  # torch._C.ExtraFilesMap()
-        if optimize:  # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
-            optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files)
-        else:
-            ts.save(str(f), _extra_files=extra_files)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'{prefix} export failure: {e}')
-
-
-def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
-    # YOLOv5 ONNX export
-    try:
-        check_requirements(('onnx',))
-        import onnx
-
-        LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
-        f = file.with_suffix('.onnx')
-
-        torch.onnx.export(model, im, f, verbose=False, opset_version=opset,
-                          training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
-                          do_constant_folding=not train,
-                          input_names=['images'],
-                          output_names=['output'],
-                          dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # shape(1,3,640,640)
-                                        'output': {0: 'batch', 1: 'anchors'}  # shape(1,25200,85)
-                                        } if dynamic else None)
-
-        # Checks
-        model_onnx = onnx.load(f)  # load onnx model
-        onnx.checker.check_model(model_onnx)  # check onnx model
-        # LOGGER.info(onnx.helper.printable_graph(model_onnx.graph))  # print
-
-        # Simplify
-        if simplify:
-            try:
-                check_requirements(('onnx-simplifier',))
-                import onnxsim
-
-                LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
-                model_onnx, check = onnxsim.simplify(
-                    model_onnx,
-                    dynamic_input_shape=dynamic,
-                    input_shapes={'images': list(im.shape)} if dynamic else None)
-                assert check, 'assert check failed'
-                onnx.save(model_onnx, f)
-            except Exception as e:
-                LOGGER.info(f'{prefix} simplifier failure: {e}')
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'{prefix} export failure: {e}')
-
-
-def export_openvino(model, im, file, prefix=colorstr('OpenVINO:')):
-    # YOLOv5 OpenVINO export
-    try:
-        check_requirements(('openvino-dev',))  # requires openvino-dev: https://pypi.org/project/openvino-dev/
-        import openvino.inference_engine as ie
-
-        LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...')
-        f = str(file).replace('.pt', '_openvino_model' + os.sep)
-
-        cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f}"
-        subprocess.check_output(cmd, shell=True)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
-    # YOLOv5 CoreML export
-    try:
-        check_requirements(('coremltools',))
-        import coremltools as ct
-
-        LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
-        f = file.with_suffix('.mlmodel')
-
-        ts = torch.jit.trace(model, im, strict=False)  # TorchScript model
-        ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
-        ct_model.save(f)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return ct_model, f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-        return None, None
-
-
-def export_engine(model, im, file, train, half, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')):
-    # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
-    try:
-        check_requirements(('tensorrt',))
-        import tensorrt as trt
-
-        if trt.__version__[0] == '7':  # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
-            grid = model.model[-1].anchor_grid
-            model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
-            export_onnx(model, im, file, 12, train, False, simplify)  # opset 12
-            model.model[-1].anchor_grid = grid
-        else:  # TensorRT >= 8
-            check_version(trt.__version__, '8.0.0', hard=True)  # require tensorrt>=8.0.0
-            export_onnx(model, im, file, 13, train, False, simplify)  # opset 13
-        onnx = file.with_suffix('.onnx')
-
-        LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...')
-        assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`'
-        assert onnx.exists(), f'failed to export ONNX file: {onnx}'
-        f = file.with_suffix('.engine')  # TensorRT engine file
-        logger = trt.Logger(trt.Logger.INFO)
-        if verbose:
-            logger.min_severity = trt.Logger.Severity.VERBOSE
-
-        builder = trt.Builder(logger)
-        config = builder.create_builder_config()
-        config.max_workspace_size = workspace * 1 << 30
-        # config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30)  # fix TRT 8.4 deprecation notice
-
-        flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
-        network = builder.create_network(flag)
-        parser = trt.OnnxParser(network, logger)
-        if not parser.parse_from_file(str(onnx)):
-            raise RuntimeError(f'failed to load ONNX file: {onnx}')
-
-        inputs = [network.get_input(i) for i in range(network.num_inputs)]
-        outputs = [network.get_output(i) for i in range(network.num_outputs)]
-        LOGGER.info(f'{prefix} Network Description:')
-        for inp in inputs:
-            LOGGER.info(f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}')
-        for out in outputs:
-            LOGGER.info(f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}')
-
-        LOGGER.info(f'{prefix} building FP{16 if builder.platform_has_fast_fp16 else 32} engine in {f}')
-        if builder.platform_has_fast_fp16:
-            config.set_flag(trt.BuilderFlag.FP16)
-        with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
-            t.write(engine.serialize())
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_saved_model(model, im, file, dynamic,
-                       tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
-                       conf_thres=0.25, keras=False, prefix=colorstr('TensorFlow SavedModel:')):
-    # YOLOv5 TensorFlow SavedModel export
-    try:
-        import tensorflow as tf
-        from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
-
-        from models.tf import TFDetect, TFModel
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
-        f = str(file).replace('.pt', '_saved_model')
-        batch_size, ch, *imgsz = list(im.shape)  # BCHW
-
-        tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
-        im = tf.zeros((batch_size, *imgsz, ch))  # BHWC order for TensorFlow
-        _ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
-        inputs = tf.keras.Input(shape=(*imgsz, ch), batch_size=None if dynamic else batch_size)
-        outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
-        keras_model = tf.keras.Model(inputs=inputs, outputs=outputs)
-        keras_model.trainable = False
-        keras_model.summary()
-        if keras:
-            keras_model.save(f, save_format='tf')
-        else:
-            m = tf.function(lambda x: keras_model(x))  # full model
-            spec = tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)
-            m = m.get_concrete_function(spec)
-            frozen_func = convert_variables_to_constants_v2(m)
-            tfm = tf.Module()
-            tfm.__call__ = tf.function(lambda x: frozen_func(x)[0], [spec])
-            tfm.__call__(im)
-            tf.saved_model.save(
-                tfm,
-                f,
-                options=tf.saved_model.SaveOptions(experimental_custom_gradients=False) if
-                check_version(tf.__version__, '2.6') else tf.saved_model.SaveOptions())
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return keras_model, f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-        return None, None
-
-
-def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')):
-    # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
-    try:
-        import tensorflow as tf
-        from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
-        f = file.with_suffix('.pb')
-
-        m = tf.function(lambda x: keras_model(x))  # full model
-        m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
-        frozen_func = convert_variables_to_constants_v2(m)
-        frozen_func.graph.as_graph_def()
-        tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')):
-    # YOLOv5 TensorFlow Lite export
-    try:
-        import tensorflow as tf
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
-        batch_size, ch, *imgsz = list(im.shape)  # BCHW
-        f = str(file).replace('.pt', '-fp16.tflite')
-
-        converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
-        converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
-        converter.target_spec.supported_types = [tf.float16]
-        converter.optimizations = [tf.lite.Optimize.DEFAULT]
-        if int8:
-            from models.tf import representative_dataset_gen
-            dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False)  # representative data
-            converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib)
-            converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
-            converter.target_spec.supported_types = []
-            converter.inference_input_type = tf.uint8  # or tf.int8
-            converter.inference_output_type = tf.uint8  # or tf.int8
-            converter.experimental_new_quantizer = True
-            f = str(file).replace('.pt', '-int8.tflite')
-
-        tflite_model = converter.convert()
-        open(f, "wb").write(tflite_model)
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_edgetpu(keras_model, im, file, prefix=colorstr('Edge TPU:')):
-    # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
-    try:
-        cmd = 'edgetpu_compiler --version'
-        help_url = 'https://coral.ai/docs/edgetpu/compiler/'
-        assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}'
-        if subprocess.run(cmd + ' >/dev/null', shell=True).returncode != 0:
-            LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
-            sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0  # sudo installed on system
-            for c in ['curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
-                      'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
-                      'sudo apt-get update',
-                      'sudo apt-get install edgetpu-compiler']:
-                subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True)
-        ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]
-
-        LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...')
-        f = str(file).replace('.pt', '-int8_edgetpu.tflite')  # Edge TPU model
-        f_tfl = str(file).replace('.pt', '-int8.tflite')  # TFLite model
-
-        cmd = f"edgetpu_compiler -s {f_tfl}"
-        subprocess.run(cmd, shell=True, check=True)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
-    # YOLOv5 TensorFlow.js export
-    try:
-        check_requirements(('tensorflowjs',))
-        import re
-
-        import tensorflowjs as tfjs
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
-        f = str(file).replace('.pt', '_web_model')  # js dir
-        f_pb = file.with_suffix('.pb')  # *.pb path
-        f_json = f + '/model.json'  # *.json path
-
-        cmd = f'tensorflowjs_converter --input_format=tf_frozen_model ' \
-              f'--output_node_names="Identity,Identity_1,Identity_2,Identity_3" {f_pb} {f}'
-        subprocess.run(cmd, shell=True)
-
-        json = open(f_json).read()
-        with open(f_json, 'w') as j:  # sort JSON Identity_* in ascending order
-            subst = re.sub(
-                r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
-                r'"Identity.?.?": {"name": "Identity.?.?"}, '
-                r'"Identity.?.?": {"name": "Identity.?.?"}, '
-                r'"Identity.?.?": {"name": "Identity.?.?"}}}',
-                r'{"outputs": {"Identity": {"name": "Identity"}, '
-                r'"Identity_1": {"name": "Identity_1"}, '
-                r'"Identity_2": {"name": "Identity_2"}, '
-                r'"Identity_3": {"name": "Identity_3"}}}',
-                json)
-            j.write(subst)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        return f
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-@torch.no_grad()
-def run(data=ROOT / 'data/coco128.yaml',  # 'dataset.yaml path'
-        weights=ROOT / 'yolov5s.pt',  # weights path
-        imgsz=(640, 640),  # image (height, width)
-        batch_size=1,  # batch size
-        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
-        include=('torchscript', 'onnx'),  # include formats
-        half=False,  # FP16 half-precision export
-        inplace=False,  # set YOLOv5 Detect() inplace=True
-        train=False,  # model.train() mode
-        optimize=False,  # TorchScript: optimize for mobile
-        int8=False,  # CoreML/TF INT8 quantization
-        dynamic=False,  # ONNX/TF: dynamic axes
-        simplify=False,  # ONNX: simplify model
-        opset=12,  # ONNX: opset version
-        verbose=False,  # TensorRT: verbose log
-        workspace=4,  # TensorRT: workspace size (GB)
-        nms=False,  # TF: add NMS to model
-        agnostic_nms=False,  # TF: add agnostic NMS to model
-        topk_per_class=100,  # TF.js NMS: topk per class to keep
-        topk_all=100,  # TF.js NMS: topk for all classes to keep
-        iou_thres=0.45,  # TF.js NMS: IoU threshold
-        conf_thres=0.25  # TF.js NMS: confidence threshold
-        ):
-    t = time.time()
-    include = [x.lower() for x in include]  # to lowercase
-    formats = tuple(export_formats()['Argument'][1:])  # --include arguments
-    flags = [x in include for x in formats]
-    assert sum(flags) == len(include), f'ERROR: Invalid --include {include}, valid --include arguments are {formats}'
-    jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = flags  # export booleans
-    file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights)  # PyTorch weights
-
-    # Load PyTorch model
-    device = select_device(device)
-    assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
-    model = attempt_load(weights, map_location=device, inplace=True, fuse=True)  # load FP32 model
-    nc, names = model.nc, model.names  # number of classes, class names
-
-    # Checks
-    imgsz *= 2 if len(imgsz) == 1 else 1  # expand
-    opset = 12 if ('openvino' in include) else opset  # OpenVINO requires opset <= 12
-    assert nc == len(names), f'Model class count {nc} != len(names) {len(names)}'
-
-    # Input
-    gs = int(max(model.stride))  # grid size (max stride)
-    imgsz = [check_img_size(x, gs) for x in imgsz]  # verify img_size are gs-multiples
-    im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection
-
-    # Update model
-    if half:
-        im, model = im.half(), model.half()  # to FP16
-    model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
-    for k, m in model.named_modules():
-        if isinstance(m, Conv):  # assign export-friendly activations
-            if isinstance(m.act, nn.SiLU):
-                m.act = SiLU()
-        elif isinstance(m, Detect):
-            m.inplace = inplace
-            m.onnx_dynamic = dynamic
-            if hasattr(m, 'forward_export'):
-                m.forward = m.forward_export  # assign custom forward (optional)
-
-    for _ in range(2):
-        y = model(im)  # dry runs
-    shape = tuple(y[0].shape)  # model output shape
-    LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)")
-
-    # Exports
-    f = [''] * 10  # exported filenames
-    warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning)  # suppress TracerWarning
-    if jit:
-        f[0] = export_torchscript(model, im, file, optimize)
-    if engine:  # TensorRT required before ONNX
-        f[1] = export_engine(model, im, file, train, half, simplify, workspace, verbose)
-    if onnx or xml:  # OpenVINO requires ONNX
-        f[2] = export_onnx(model, im, file, opset, train, dynamic, simplify)
-    if xml:  # OpenVINO
-        f[3] = export_openvino(model, im, file)
-    if coreml:
-        _, f[4] = export_coreml(model, im, file)
-
-    # TensorFlow Exports
-    if any((saved_model, pb, tflite, edgetpu, tfjs)):
-        if int8 or edgetpu:  # TFLite --int8 bug https://github.com/ultralytics/yolov5/issues/5707
-            check_requirements(('flatbuffers==1.12',))  # required before `import tensorflow`
-        assert not (tflite and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.'
-        model, f[5] = export_saved_model(model.cpu(), im, file, dynamic, tf_nms=nms or agnostic_nms or tfjs,
-                                         agnostic_nms=agnostic_nms or tfjs, topk_per_class=topk_per_class,
-                                         topk_all=topk_all, conf_thres=conf_thres, iou_thres=iou_thres)  # keras model
-        if pb or tfjs:  # pb prerequisite to tfjs
-            f[6] = export_pb(model, im, file)
-        if tflite or edgetpu:
-            f[7] = export_tflite(model, im, file, int8=int8 or edgetpu, data=data, ncalib=100)
-        if edgetpu:
-            f[8] = export_edgetpu(model, im, file)
-        if tfjs:
-            f[9] = export_tfjs(model, im, file)
-
-    # Finish
-    f = [str(x) for x in f if x]  # filter out '' and None
-    if any(f):
-        LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)'
-                    f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
-                    f"\nDetect:          python detect.py --weights {f[-1]}"
-                    f"\nPyTorch Hub:     model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')"
-                    f"\nValidate:        python val.py --weights {f[-1]}"
-                    f"\nVisualize:       https://netron.app")
-    return f  # return list of exported files/dirs
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
-    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)')
-    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
-    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
-    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-    parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
-    parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
-    parser.add_argument('--train', action='store_true', help='model.train() mode')
-    parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
-    parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
-    parser.add_argument('--dynamic', action='store_true', help='ONNX/TF: dynamic axes')
-    parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
-    parser.add_argument('--opset', type=int, default=12, help='ONNX: opset version')
-    parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log')
-    parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)')
-    parser.add_argument('--nms', action='store_true', help='TF: add NMS to model')
-    parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model')
-    parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
-    parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
-    parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
-    parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
-    parser.add_argument('--include', nargs='+',
-                        default=['torchscript', 'onnx'],
-                        help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs')
-    opt = parser.parse_args()
-    print_args(FILE.stem, opt)
-    return opt
-
-
-def main(opt):
-    for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]):
-        run(**vars(opt))
-
-
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)

ultralytics/yolov5/hubconf.py

@@ -1,143 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/
-
-Usage:
-    import torch
-    model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
-    model = torch.hub.load('ultralytics/yolov5:master', 'custom', 'path/to/yolov5s.onnx')  # file from branch
-"""
-
-import torch
-
-
-def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    """Creates or loads a YOLOv5 model
-
-    Arguments:
-        name (str): model name 'yolov5s' or path 'path/to/best.pt'
-        pretrained (bool): load pretrained weights into the model
-        channels (int): number of input channels
-        classes (int): number of model classes
-        autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
-        verbose (bool): print all information to screen
-        device (str, torch.device, None): device to use for model parameters
-
-    Returns:
-        YOLOv5 model
-    """
-    from pathlib import Path
-
-    from models.common import AutoShape, DetectMultiBackend
-    from models.yolo import Model
-    from utils.downloads import attempt_download
-    from utils.general import LOGGER, check_requirements, intersect_dicts, logging
-    from utils.torch_utils import select_device
-
-    if not verbose:
-        LOGGER.setLevel(logging.WARNING)
-    check_requirements(exclude=('tensorboard', 'thop', 'opencv-python'))
-    name = Path(name)
-    path = name.with_suffix('.pt') if name.suffix == '' else name  # checkpoint path
-    try:
-        device = select_device(('0' if torch.cuda.is_available() else 'cpu') if device is None else device)
-
-        if pretrained and channels == 3 and classes == 80:
-            model = DetectMultiBackend(path, device=device)  # download/load FP32 model
-            # model = models.experimental.attempt_load(path, map_location=device)  # download/load FP32 model
-        else:
-            cfg = list((Path(__file__).parent / 'models').rglob(f'{path.stem}.yaml'))[0]  # model.yaml path
-            model = Model(cfg, channels, classes)  # create model
-            if pretrained:
-                ckpt = torch.load(attempt_download(path), map_location=device)  # load
-                csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
-                csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors'])  # intersect
-                model.load_state_dict(csd, strict=False)  # load
-                if len(ckpt['model'].names) == classes:
-                    model.names = ckpt['model'].names  # set class names attribute
-        if autoshape:
-            model = AutoShape(model)  # for file/URI/PIL/cv2/np inputs and NMS
-        return model.to(device)
-
-    except Exception as e:
-        help_url = 'https://github.com/ultralytics/yolov5/issues/36'
-        s = f'{e}. Cache may be out of date, try `force_reload=True` or see {help_url} for help.'
-        raise Exception(s) from e
-
-
-def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None):
-    # YOLOv5 custom or local model
-    return _create(path, autoshape=autoshape, verbose=verbose, device=device)
-
-
-def yolov5n(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-nano model https://github.com/ultralytics/yolov5
-    return _create('yolov5n', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-small model https://github.com/ultralytics/yolov5
-    return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-medium model https://github.com/ultralytics/yolov5
-    return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-large model https://github.com/ultralytics/yolov5
-    return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
-    return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5n6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5n6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-if __name__ == '__main__':
-    model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True)  # pretrained
-    # model = custom(path='path/to/model.pt')  # custom
-
-    # Verify inference
-    from pathlib import Path
-
-    import cv2
-    import numpy as np
-    from PIL import Image
-
-    imgs = ['data/images/zidane.jpg',  # filename
-            Path('data/images/zidane.jpg'),  # Path
-            'https://ultralytics.com/images/zidane.jpg',  # URI
-            cv2.imread('data/images/bus.jpg')[:, :, ::-1],  # OpenCV
-            Image.open('data/images/bus.jpg'),  # PIL
-            np.zeros((320, 640, 3))]  # numpy
-
-    results = model(imgs, size=320)  # batched inference
-    results.print()
-    results.save()

ultralytics/yolov5/models/common.py

@@ -1,684 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Common modules
-"""
-
-import json
-import math
-import platform
-import warnings
-from collections import OrderedDict, namedtuple
-from copy import copy
-from pathlib import Path
-
-import cv2
-import numpy as np
-import pandas as pd
-import requests
-import torch
-import torch.nn as nn
-import yaml
-from PIL import Image
-from torch.cuda import amp
-
-from utils.datasets import exif_transpose, letterbox
-from utils.general import (LOGGER, check_requirements, check_suffix, check_version, colorstr, increment_path,
-                           make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh)
-from utils.plots import Annotator, colors, save_one_box
-from utils.torch_utils import copy_attr, time_sync
-
-
-def autopad(k, p=None):  # kernel, padding
-    # Pad to 'same'
-    if p is None:
-        p = k // 2 if isinstance(k, int) else (x // 2 for x in k)  # auto-pad
-    return p
-
-
-class Conv(nn.Module):
-    # Standard convolution
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__()
-        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
-        self.bn = nn.BatchNorm2d(c2)
-        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
-
-    def forward(self, x):
-        return self.act(self.bn(self.conv(x)))
-
-    def forward_fuse(self, x):
-        return self.act(self.conv(x))
-
-
-class DWConv(Conv):
-    # Depth-wise convolution class
-    def __init__(self, c1, c2, k=1, s=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
-
-
-class TransformerLayer(nn.Module):
-    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
-    def __init__(self, c, num_heads):
-        super().__init__()
-        self.q = nn.Linear(c, c, bias=False)
-        self.k = nn.Linear(c, c, bias=False)
-        self.v = nn.Linear(c, c, bias=False)
-        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
-        self.fc1 = nn.Linear(c, c, bias=False)
-        self.fc2 = nn.Linear(c, c, bias=False)
-
-    def forward(self, x):
-        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
-        x = self.fc2(self.fc1(x)) + x
-        return x
-
-
-class TransformerBlock(nn.Module):
-    # Vision Transformer https://arxiv.org/abs/2010.11929
-    def __init__(self, c1, c2, num_heads, num_layers):
-        super().__init__()
-        self.conv = None
-        if c1 != c2:
-            self.conv = Conv(c1, c2)
-        self.linear = nn.Linear(c2, c2)  # learnable position embedding
-        self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
-        self.c2 = c2
-
-    def forward(self, x):
-        if self.conv is not None:
-            x = self.conv(x)
-        b, _, w, h = x.shape
-        p = x.flatten(2).permute(2, 0, 1)
-        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
-
-
-class Bottleneck(nn.Module):
-    # Standard bottleneck
-    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = Conv(c_, c2, 3, 1, g=g)
-        self.add = shortcut and c1 == c2
-
-    def forward(self, x):
-        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
-
-
-class BottleneckCSP(nn.Module):
-    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
-        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
-        self.cv4 = Conv(2 * c_, c2, 1, 1)
-        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
-        self.act = nn.SiLU()
-        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
-
-    def forward(self, x):
-        y1 = self.cv3(self.m(self.cv1(x)))
-        y2 = self.cv2(x)
-        return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))
-
-
-class C3(nn.Module):
-    # CSP Bottleneck with 3 convolutions
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = Conv(c1, c_, 1, 1)
-        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
-        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
-        # self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)))
-
-    def forward(self, x):
-        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
-
-
-class C3TR(C3):
-    # C3 module with TransformerBlock()
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
-        super().__init__(c1, c2, n, shortcut, g, e)
-        c_ = int(c2 * e)
-        self.m = TransformerBlock(c_, c_, 4, n)
-
-
-class C3SPP(C3):
-    # C3 module with SPP()
-    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
-        super().__init__(c1, c2, n, shortcut, g, e)
-        c_ = int(c2 * e)
-        self.m = SPP(c_, c_, k)
-
-
-class C3Ghost(C3):
-    # C3 module with GhostBottleneck()
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
-        super().__init__(c1, c2, n, shortcut, g, e)
-        c_ = int(c2 * e)  # hidden channels
-        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
-
-
-class SPP(nn.Module):
-    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
-    def __init__(self, c1, c2, k=(5, 9, 13)):
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
-        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
-
-    def forward(self, x):
-        x = self.cv1(x)
-        with warnings.catch_warnings():
-            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
-            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
-
-
-class SPPF(nn.Module):
-    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
-    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = Conv(c_ * 4, c2, 1, 1)
-        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
-
-    def forward(self, x):
-        x = self.cv1(x)
-        with warnings.catch_warnings():
-            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
-            y1 = self.m(x)
-            y2 = self.m(y1)
-            return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))
-
-
-class Focus(nn.Module):
-    # Focus wh information into c-space
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__()
-        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
-        # self.contract = Contract(gain=2)
-
-    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
-        return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
-        # return self.conv(self.contract(x))
-
-
-class GhostConv(nn.Module):
-    # Ghost Convolution https://github.com/huawei-noah/ghostnet
-    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
-        super().__init__()
-        c_ = c2 // 2  # hidden channels
-        self.cv1 = Conv(c1, c_, k, s, None, g, act)
-        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
-
-    def forward(self, x):
-        y = self.cv1(x)
-        return torch.cat((y, self.cv2(y)), 1)
-
-
-class GhostBottleneck(nn.Module):
-    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
-    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
-        super().__init__()
-        c_ = c2 // 2
-        self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pw
-                                  DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
-                                  GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
-        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
-                                      Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
-
-    def forward(self, x):
-        return self.conv(x) + self.shortcut(x)
-
-
-class Contract(nn.Module):
-    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
-    def __init__(self, gain=2):
-        super().__init__()
-        self.gain = gain
-
-    def forward(self, x):
-        b, c, h, w = x.size()  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
-        s = self.gain
-        x = x.view(b, c, h // s, s, w // s, s)  # x(1,64,40,2,40,2)
-        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
-        return x.view(b, c * s * s, h // s, w // s)  # x(1,256,40,40)
-
-
-class Expand(nn.Module):
-    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
-    def __init__(self, gain=2):
-        super().__init__()
-        self.gain = gain
-
-    def forward(self, x):
-        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
-        s = self.gain
-        x = x.view(b, s, s, c // s ** 2, h, w)  # x(1,2,2,16,80,80)
-        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
-        return x.view(b, c // s ** 2, h * s, w * s)  # x(1,16,160,160)
-
-
-class Concat(nn.Module):
-    # Concatenate a list of tensors along dimension
-    def __init__(self, dimension=1):
-        super().__init__()
-        self.d = dimension
-
-    def forward(self, x):
-        return torch.cat(x, self.d)
-
-
-class DetectMultiBackend(nn.Module):
-    # YOLOv5 MultiBackend class for python inference on various backends
-    def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False):
-        # Usage:
-        #   PyTorch:              weights = *.pt
-        #   TorchScript:                    *.torchscript
-        #   ONNX Runtime:                   *.onnx
-        #   ONNX OpenCV DNN:                *.onnx with --dnn
-        #   OpenVINO:                       *.xml
-        #   CoreML:                         *.mlmodel
-        #   TensorRT:                       *.engine
-        #   TensorFlow SavedModel:          *_saved_model
-        #   TensorFlow GraphDef:            *.pb
-        #   TensorFlow Lite:                *.tflite
-        #   TensorFlow Edge TPU:            *_edgetpu.tflite
-        from models.experimental import attempt_download, attempt_load  # scoped to avoid circular import
-
-        super().__init__()
-        w = str(weights[0] if isinstance(weights, list) else weights)
-        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self.model_type(w)  # get backend
-        stride, names = 64, [f'class{i}' for i in range(1000)]  # assign defaults
-        w = attempt_download(w)  # download if not local
-        fp16 &= (pt or jit or onnx or engine) and device.type != 'cpu'  # FP16
-        if data:  # data.yaml path (optional)
-            with open(data, errors='ignore') as f:
-                names = yaml.safe_load(f)['names']  # class names
-
-        if pt:  # PyTorch
-            model = attempt_load(weights if isinstance(weights, list) else w, map_location=device)
-            stride = max(int(model.stride.max()), 32)  # model stride
-            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
-            model.half() if fp16 else model.float()
-            self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
-        elif jit:  # TorchScript
-            LOGGER.info(f'Loading {w} for TorchScript inference...')
-            extra_files = {'config.txt': ''}  # model metadata
-            model = torch.jit.load(w, _extra_files=extra_files)
-            model.half() if fp16 else model.float()
-            if extra_files['config.txt']:
-                d = json.loads(extra_files['config.txt'])  # extra_files dict
-                stride, names = int(d['stride']), d['names']
-        elif dnn:  # ONNX OpenCV DNN
-            LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
-            check_requirements(('opencv-python>=4.5.4',))
-            net = cv2.dnn.readNetFromONNX(w)
-        elif onnx:  # ONNX Runtime
-            LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
-            cuda = torch.cuda.is_available()
-            check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
-            import onnxruntime
-            providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
-            session = onnxruntime.InferenceSession(w, providers=providers)
-        elif xml:  # OpenVINO
-            LOGGER.info(f'Loading {w} for OpenVINO inference...')
-            check_requirements(('openvino-dev',))  # requires openvino-dev: https://pypi.org/project/openvino-dev/
-            import openvino.inference_engine as ie
-            core = ie.IECore()
-            if not Path(w).is_file():  # if not *.xml
-                w = next(Path(w).glob('*.xml'))  # get *.xml file from *_openvino_model dir
-            network = core.read_network(model=w, weights=Path(w).with_suffix('.bin'))  # *.xml, *.bin paths
-            executable_network = core.load_network(network, device_name='CPU', num_requests=1)
-        elif engine:  # TensorRT
-            LOGGER.info(f'Loading {w} for TensorRT inference...')
-            import tensorrt as trt  # https://developer.nvidia.com/nvidia-tensorrt-download
-            check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=7.0.0
-            Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
-            logger = trt.Logger(trt.Logger.INFO)
-            with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
-                model = runtime.deserialize_cuda_engine(f.read())
-            bindings = OrderedDict()
-            fp16 = False  # default updated below
-            for index in range(model.num_bindings):
-                name = model.get_binding_name(index)
-                dtype = trt.nptype(model.get_binding_dtype(index))
-                shape = tuple(model.get_binding_shape(index))
-                data = torch.from_numpy(np.empty(shape, dtype=np.dtype(dtype))).to(device)
-                bindings[name] = Binding(name, dtype, shape, data, int(data.data_ptr()))
-                if model.binding_is_input(index) and dtype == np.float16:
-                    fp16 = True
-            binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
-            context = model.create_execution_context()
-            batch_size = bindings['images'].shape[0]
-        elif coreml:  # CoreML
-            LOGGER.info(f'Loading {w} for CoreML inference...')
-            import coremltools as ct
-            model = ct.models.MLModel(w)
-        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
-            if saved_model:  # SavedModel
-                LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
-                import tensorflow as tf
-                keras = False  # assume TF1 saved_model
-                model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
-            elif pb:  # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
-                LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
-                import tensorflow as tf
-
-                def wrap_frozen_graph(gd, inputs, outputs):
-                    x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), [])  # wrapped
-                    ge = x.graph.as_graph_element
-                    return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
-
-                gd = tf.Graph().as_graph_def()  # graph_def
-                gd.ParseFromString(open(w, 'rb').read())
-                frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs="Identity:0")
-            elif tflite or edgetpu:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
-                try:  # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
-                    from tflite_runtime.interpreter import Interpreter, load_delegate
-                except ImportError:
-                    import tensorflow as tf
-                    Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
-                if edgetpu:  # Edge TPU https://coral.ai/software/#edgetpu-runtime
-                    LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
-                    delegate = {'Linux': 'libedgetpu.so.1',
-                                'Darwin': 'libedgetpu.1.dylib',
-                                'Windows': 'edgetpu.dll'}[platform.system()]
-                    interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
-                else:  # Lite
-                    LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
-                    interpreter = Interpreter(model_path=w)  # load TFLite model
-                interpreter.allocate_tensors()  # allocate
-                input_details = interpreter.get_input_details()  # inputs
-                output_details = interpreter.get_output_details()  # outputs
-            elif tfjs:
-                raise Exception('ERROR: YOLOv5 TF.js inference is not supported')
-        self.__dict__.update(locals())  # assign all variables to self
-
-    def forward(self, im, augment=False, visualize=False, val=False):
-        # YOLOv5 MultiBackend inference
-        b, ch, h, w = im.shape  # batch, channel, height, width
-        if self.pt or self.jit:  # PyTorch
-            y = self.model(im) if self.jit else self.model(im, augment=augment, visualize=visualize)
-            return y if val else y[0]
-        elif self.dnn:  # ONNX OpenCV DNN
-            im = im.cpu().numpy()  # torch to numpy
-            self.net.setInput(im)
-            y = self.net.forward()
-        elif self.onnx:  # ONNX Runtime
-            im = im.cpu().numpy()  # torch to numpy
-            y = self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0]
-        elif self.xml:  # OpenVINO
-            im = im.cpu().numpy()  # FP32
-            desc = self.ie.TensorDesc(precision='FP32', dims=im.shape, layout='NCHW')  # Tensor Description
-            request = self.executable_network.requests[0]  # inference request
-            request.set_blob(blob_name='images', blob=self.ie.Blob(desc, im))  # name=next(iter(request.input_blobs))
-            request.infer()
-            y = request.output_blobs['output'].buffer  # name=next(iter(request.output_blobs))
-        elif self.engine:  # TensorRT
-            assert im.shape == self.bindings['images'].shape, (im.shape, self.bindings['images'].shape)
-            self.binding_addrs['images'] = int(im.data_ptr())
-            self.context.execute_v2(list(self.binding_addrs.values()))
-            y = self.bindings['output'].data
-        elif self.coreml:  # CoreML
-            im = im.permute(0, 2, 3, 1).cpu().numpy()  # torch BCHW to numpy BHWC shape(1,320,192,3)
-            im = Image.fromarray((im[0] * 255).astype('uint8'))
-            # im = im.resize((192, 320), Image.ANTIALIAS)
-            y = self.model.predict({'image': im})  # coordinates are xywh normalized
-            if 'confidence' in y:
-                box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels
-                conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
-                y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
-            else:
-                k = 'var_' + str(sorted(int(k.replace('var_', '')) for k in y)[-1])  # output key
-                y = y[k]  # output
-        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
-            im = im.permute(0, 2, 3, 1).cpu().numpy()  # torch BCHW to numpy BHWC shape(1,320,192,3)
-            if self.saved_model:  # SavedModel
-                y = (self.model(im, training=False) if self.keras else self.model(im)).numpy()
-            elif self.pb:  # GraphDef
-                y = self.frozen_func(x=self.tf.constant(im)).numpy()
-            else:  # Lite or Edge TPU
-                input, output = self.input_details[0], self.output_details[0]
-                int8 = input['dtype'] == np.uint8  # is TFLite quantized uint8 model
-                if int8:
-                    scale, zero_point = input['quantization']
-                    im = (im / scale + zero_point).astype(np.uint8)  # de-scale
-                self.interpreter.set_tensor(input['index'], im)
-                self.interpreter.invoke()
-                y = self.interpreter.get_tensor(output['index'])
-                if int8:
-                    scale, zero_point = output['quantization']
-                    y = (y.astype(np.float32) - zero_point) * scale  # re-scale
-            y[..., :4] *= [w, h, w, h]  # xywh normalized to pixels
-
-        if isinstance(y, np.ndarray):
-            y = torch.tensor(y, device=self.device)
-        return (y, []) if val else y
-
-    def warmup(self, imgsz=(1, 3, 640, 640)):
-        # Warmup model by running inference once
-        if any((self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb)):  # warmup types
-            if self.device.type != 'cpu':  # only warmup GPU models
-                im = torch.zeros(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
-                for _ in range(2 if self.jit else 1):  #
-                    self.forward(im)  # warmup
-
-    @staticmethod
-    def model_type(p='path/to/model.pt'):
-        # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
-        from export import export_formats
-        suffixes = list(export_formats().Suffix) + ['.xml']  # export suffixes
-        check_suffix(p, suffixes)  # checks
-        p = Path(p).name  # eliminate trailing separators
-        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, xml2 = (s in p for s in suffixes)
-        xml |= xml2  # *_openvino_model or *.xml
-        tflite &= not edgetpu  # *.tflite
-        return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs
-
-
-class AutoShape(nn.Module):
-    # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
-    conf = 0.25  # NMS confidence threshold
-    iou = 0.45  # NMS IoU threshold
-    agnostic = False  # NMS class-agnostic
-    multi_label = False  # NMS multiple labels per box
-    classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
-    max_det = 1000  # maximum number of detections per image
-    amp = False  # Automatic Mixed Precision (AMP) inference
-
-    def __init__(self, model):
-        super().__init__()
-        LOGGER.info('Adding AutoShape... ')
-        copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=())  # copy attributes
-        self.dmb = isinstance(model, DetectMultiBackend)  # DetectMultiBackend() instance
-        self.pt = not self.dmb or model.pt  # PyTorch model
-        self.model = model.eval()
-
-    def _apply(self, fn):
-        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
-        self = super()._apply(fn)
-        if self.pt:
-            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
-            m.stride = fn(m.stride)
-            m.grid = list(map(fn, m.grid))
-            if isinstance(m.anchor_grid, list):
-                m.anchor_grid = list(map(fn, m.anchor_grid))
-        return self
-
-    @torch.no_grad()
-    def forward(self, imgs, size=640, augment=False, profile=False):
-        # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
-        #   file:       imgs = 'data/images/zidane.jpg'  # str or PosixPath
-        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
-        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
-        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
-        #   numpy:           = np.zeros((640,1280,3))  # HWC
-        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
-        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
-
-        t = [time_sync()]
-        p = next(self.model.parameters()) if self.pt else torch.zeros(1)  # for device and type
-        autocast = self.amp and (p.device.type != 'cpu')  # Automatic Mixed Precision (AMP) inference
-        if isinstance(imgs, torch.Tensor):  # torch
-            with amp.autocast(autocast):
-                return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference
-
-        # Pre-process
-        n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])  # number of images, list of images
-        shape0, shape1, files = [], [], []  # image and inference shapes, filenames
-        for i, im in enumerate(imgs):
-            f = f'image{i}'  # filename
-            if isinstance(im, (str, Path)):  # filename or uri
-                im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
-                im = np.asarray(exif_transpose(im))
-            elif isinstance(im, Image.Image):  # PIL Image
-                im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
-            files.append(Path(f).with_suffix('.jpg').name)
-            if im.shape[0] < 5:  # image in CHW
-                im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
-            im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3)  # enforce 3ch input
-            s = im.shape[:2]  # HWC
-            shape0.append(s)  # image shape
-            g = (size / max(s))  # gain
-            shape1.append([y * g for y in s])
-            imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
-        shape1 = [make_divisible(x, self.stride) if self.pt else size for x in np.array(shape1).max(0)]  # inf shape
-        x = [letterbox(im, shape1, auto=False)[0] for im in imgs]  # pad
-        x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2)))  # stack and BHWC to BCHW
-        x = torch.from_numpy(x).to(p.device).type_as(p) / 255  # uint8 to fp16/32
-        t.append(time_sync())
-
-        with amp.autocast(autocast):
-            # Inference
-            y = self.model(x, augment, profile)  # forward
-            t.append(time_sync())
-
-            # Post-process
-            y = non_max_suppression(y if self.dmb else y[0], self.conf, self.iou, self.classes, self.agnostic,
-                                    self.multi_label, max_det=self.max_det)  # NMS
-            for i in range(n):
-                scale_coords(shape1, y[i][:, :4], shape0[i])
-
-            t.append(time_sync())
-            return Detections(imgs, y, files, t, self.names, x.shape)
-
-
-class Detections:
-    # YOLOv5 detections class for inference results
-    def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None):
-        super().__init__()
-        d = pred[0].device  # device
-        gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs]  # normalizations
-        self.imgs = imgs  # list of images as numpy arrays
-        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
-        self.names = names  # class names
-        self.files = files  # image filenames
-        self.times = times  # profiling times
-        self.xyxy = pred  # xyxy pixels
-        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
-        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
-        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
-        self.n = len(self.pred)  # number of images (batch size)
-        self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3))  # timestamps (ms)
-        self.s = shape  # inference BCHW shape
-
-    def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
-        crops = []
-        for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
-            s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
-            if pred.shape[0]:
-                for c in pred[:, -1].unique():
-                    n = (pred[:, -1] == c).sum()  # detections per class
-                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
-                if show or save or render or crop:
-                    annotator = Annotator(im, example=str(self.names))
-                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
-                        label = f'{self.names[int(cls)]} {conf:.2f}'
-                        if crop:
-                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
-                            crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
-                                          'im': save_one_box(box, im, file=file, save=save)})
-                        else:  # all others
-                            annotator.box_label(box, label, color=colors(cls))
-                    im = annotator.im
-            else:
-                s += '(no detections)'
-
-            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
-            if pprint:
-                LOGGER.info(s.rstrip(', '))
-            if show:
-                im.show(self.files[i])  # show
-            if save:
-                f = self.files[i]
-                im.save(save_dir / f)  # save
-                if i == self.n - 1:
-                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
-            if render:
-                self.imgs[i] = np.asarray(im)
-        if crop:
-            if save:
-                LOGGER.info(f'Saved results to {save_dir}\n')
-            return crops
-
-    def print(self):
-        self.display(pprint=True)  # print results
-        LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
-                    self.t)
-
-    def show(self):
-        self.display(show=True)  # show results
-
-    def save(self, save_dir='runs/detect/exp'):
-        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True)  # increment save_dir
-        self.display(save=True, save_dir=save_dir)  # save results
-
-    def crop(self, save=True, save_dir='runs/detect/exp'):
-        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
-        return self.display(crop=True, save=save, save_dir=save_dir)  # crop results
-
-    def render(self):
-        self.display(render=True)  # render results
-        return self.imgs
-
-    def pandas(self):
-        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
-        new = copy(self)  # return copy
-        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
-        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
-        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
-            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
-            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
-        return new
-
-    def tolist(self):
-        # return a list of Detections objects, i.e. 'for result in results.tolist():'
-        r = range(self.n)  # iterable
-        x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
-        # for d in x:
-        #    for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
-        #        setattr(d, k, getattr(d, k)[0])  # pop out of list
-        return x
-
-    def __len__(self):
-        return self.n
-
-
-class Classify(nn.Module):
-    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__()
-        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
-        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g)  # to x(b,c2,1,1)
-        self.flat = nn.Flatten()
-
-    def forward(self, x):
-        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
-        return self.flat(self.conv(z))  # flatten to x(b,c2)

ultralytics/yolov5/models/experimental.py

@@ -1,121 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Experimental modules
-"""
-import math
-
-import numpy as np
-import torch
-import torch.nn as nn
-
-from models.common import Conv
-from utils.downloads import attempt_download
-
-
-class CrossConv(nn.Module):
-    # Cross Convolution Downsample
-    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
-        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = Conv(c1, c_, (1, k), (1, s))
-        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
-        self.add = shortcut and c1 == c2
-
-    def forward(self, x):
-        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
-
-
-class Sum(nn.Module):
-    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
-    def __init__(self, n, weight=False):  # n: number of inputs
-        super().__init__()
-        self.weight = weight  # apply weights boolean
-        self.iter = range(n - 1)  # iter object
-        if weight:
-            self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True)  # layer weights
-
-    def forward(self, x):
-        y = x[0]  # no weight
-        if self.weight:
-            w = torch.sigmoid(self.w) * 2
-            for i in self.iter:
-                y = y + x[i + 1] * w[i]
-        else:
-            for i in self.iter:
-                y = y + x[i + 1]
-        return y
-
-
-class MixConv2d(nn.Module):
-    # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
-    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):  # ch_in, ch_out, kernel, stride, ch_strategy
-        super().__init__()
-        n = len(k)  # number of convolutions
-        if equal_ch:  # equal c_ per group
-            i = torch.linspace(0, n - 1E-6, c2).floor()  # c2 indices
-            c_ = [(i == g).sum() for g in range(n)]  # intermediate channels
-        else:  # equal weight.numel() per group
-            b = [c2] + [0] * n
-            a = np.eye(n + 1, n, k=-1)
-            a -= np.roll(a, 1, axis=1)
-            a *= np.array(k) ** 2
-            a[0] = 1
-            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
-
-        self.m = nn.ModuleList(
-            [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
-        self.bn = nn.BatchNorm2d(c2)
-        self.act = nn.SiLU()
-
-    def forward(self, x):
-        return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
-
-
-class Ensemble(nn.ModuleList):
-    # Ensemble of models
-    def __init__(self):
-        super().__init__()
-
-    def forward(self, x, augment=False, profile=False, visualize=False):
-        y = []
-        for module in self:
-            y.append(module(x, augment, profile, visualize)[0])
-        # y = torch.stack(y).max(0)[0]  # max ensemble
-        # y = torch.stack(y).mean(0)  # mean ensemble
-        y = torch.cat(y, 1)  # nms ensemble
-        return y, None  # inference, train output
-
-
-def attempt_load(weights, map_location=None, inplace=True, fuse=True):
-    from models.yolo import Detect, Model
-
-    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
-    model = Ensemble()
-    for w in weights if isinstance(weights, list) else [weights]:
-        ckpt = torch.load(attempt_download(w), map_location=map_location)  # load
-        ckpt = (ckpt.get('ema') or ckpt['model']).float()  # FP32 model
-        model.append(ckpt.fuse().eval() if fuse else ckpt.eval())  # fused or un-fused model in eval mode
-
-    # Compatibility updates
-    for m in model.modules():
-        t = type(m)
-        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model):
-            m.inplace = inplace  # torch 1.7.0 compatibility
-            if t is Detect:
-                if not isinstance(m.anchor_grid, list):  # new Detect Layer compatibility
-                    delattr(m, 'anchor_grid')
-                    setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
-        elif t is Conv:
-            m._non_persistent_buffers_set = set()  # torch 1.6.0 compatibility
-        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
-            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
-
-    if len(model) == 1:
-        return model[-1]  # return model
-    else:
-        print(f'Ensemble created with {weights}\n')
-        for k in ['names']:
-            setattr(model, k, getattr(model[-1], k))
-        model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
-        return model  # return ensemble

ultralytics/yolov5/models/hub/anchors.yaml

@@ -1,59 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Default anchors for COCO data
-
-
-# P5 -------------------------------------------------------------------------------------------------------------------
-# P5-640:
-anchors_p5_640:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-
-# P6 -------------------------------------------------------------------------------------------------------------------
-# P6-640:  thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11,  21,19,  17,41,  43,32,  39,70,  86,64,  65,131,  134,130,  120,265,  282,180,  247,354,  512,387
-anchors_p6_640:
-  - [9,11,  21,19,  17,41]  # P3/8
-  - [43,32,  39,70,  86,64]  # P4/16
-  - [65,131,  134,130,  120,265]  # P5/32
-  - [282,180,  247,354,  512,387]  # P6/64
-
-# P6-1280:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27,  44,40,  38,94,  96,68,  86,152,  180,137,  140,301,  303,264,  238,542,  436,615,  739,380,  925,792
-anchors_p6_1280:
-  - [19,27,  44,40,  38,94]  # P3/8
-  - [96,68,  86,152,  180,137]  # P4/16
-  - [140,301,  303,264,  238,542]  # P5/32
-  - [436,615,  739,380,  925,792]  # P6/64
-
-# P6-1920:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41,  67,59,  57,141,  144,103,  129,227,  270,205,  209,452,  455,396,  358,812,  653,922,  1109,570,  1387,1187
-anchors_p6_1920:
-  - [28,41,  67,59,  57,141]  # P3/8
-  - [144,103,  129,227,  270,205]  # P4/16
-  - [209,452,  455,396,  358,812]  # P5/32
-  - [653,922,  1109,570,  1387,1187]  # P6/64
-
-
-# P7 -------------------------------------------------------------------------------------------------------------------
-# P7-640:  thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11,  13,30,  29,20,  30,46,  61,38,  39,92,  78,80,  146,66,  79,163,  149,150,  321,143,  157,303,  257,402,  359,290,  524,372
-anchors_p7_640:
-  - [11,11,  13,30,  29,20]  # P3/8
-  - [30,46,  61,38,  39,92]  # P4/16
-  - [78,80,  146,66,  79,163]  # P5/32
-  - [149,150,  321,143,  157,303]  # P6/64
-  - [257,402,  359,290,  524,372]  # P7/128
-
-# P7-1280:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22,  54,36,  32,77,  70,83,  138,71,  75,173,  165,159,  148,334,  375,151,  334,317,  251,626,  499,474,  750,326,  534,814,  1079,818
-anchors_p7_1280:
-  - [19,22,  54,36,  32,77]  # P3/8
-  - [70,83,  138,71,  75,173]  # P4/16
-  - [165,159,  148,334,  375,151]  # P5/32
-  - [334,317,  251,626,  499,474]  # P6/64
-  - [750,326,  534,814,  1079,818]  # P7/128
-
-# P7-1920:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34,  81,55,  47,115,  105,124,  207,107,  113,259,  247,238,  222,500,  563,227,  501,476,  376,939,  749,711,  1126,489,  801,1222,  1618,1227
-anchors_p7_1920:
-  - [29,34,  81,55,  47,115]  # P3/8
-  - [105,124,  207,107,  113,259]  # P4/16
-  - [247,238,  222,500,  563,227]  # P5/32
-  - [501,476,  376,939,  749,711]  # P6/64
-  - [1126,489,  801,1222,  1618,1227]  # P7/128

ultralytics/yolov5/models/hub/yolov3-spp.yaml

@@ -1,51 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# darknet53 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [32, 3, 1]],  # 0
-   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
-   [-1, 1, Bottleneck, [64]],
-   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
-   [-1, 2, Bottleneck, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
-   [-1, 8, Bottleneck, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
-   [-1, 8, Bottleneck, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
-   [-1, 4, Bottleneck, [1024]],  # 10
-  ]
-
-# YOLOv3-SPP head
-head:
-  [[-1, 1, Bottleneck, [1024, False]],
-   [-1, 1, SPP, [512, [5, 9, 13]]],
-   [-1, 1, Conv, [1024, 3, 1]],
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
-
-   [-2, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Bottleneck, [512, False]],
-   [-1, 1, Bottleneck, [512, False]],
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
-
-   [-2, 1, Conv, [128, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
-   [-1, 1, Bottleneck, [256, False]],
-   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
-
-   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov3-tiny.yaml

@@ -1,41 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,14, 23,27, 37,58]  # P4/16
-  - [81,82, 135,169, 344,319]  # P5/32
-
-# YOLOv3-tiny backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [16, 3, 1]],  # 0
-   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 1-P1/2
-   [-1, 1, Conv, [32, 3, 1]],
-   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 3-P2/4
-   [-1, 1, Conv, [64, 3, 1]],
-   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 5-P3/8
-   [-1, 1, Conv, [128, 3, 1]],
-   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 7-P4/16
-   [-1, 1, Conv, [256, 3, 1]],
-   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 9-P5/32
-   [-1, 1, Conv, [512, 3, 1]],
-   [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]],  # 11
-   [-1, 1, nn.MaxPool2d, [2, 1, 0]],  # 12
-  ]
-
-# YOLOv3-tiny head
-head:
-  [[-1, 1, Conv, [1024, 3, 1]],
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, Conv, [512, 3, 1]],  # 15 (P5/32-large)
-
-   [-2, 1, Conv, [128, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Conv, [256, 3, 1]],  # 19 (P4/16-medium)
-
-   [[19, 15], 1, Detect, [nc, anchors]],  # Detect(P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov3.yaml

@@ -1,51 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# darknet53 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [32, 3, 1]],  # 0
-   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
-   [-1, 1, Bottleneck, [64]],
-   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
-   [-1, 2, Bottleneck, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
-   [-1, 8, Bottleneck, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
-   [-1, 8, Bottleneck, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
-   [-1, 4, Bottleneck, [1024]],  # 10
-  ]
-
-# YOLOv3 head
-head:
-  [[-1, 1, Bottleneck, [1024, False]],
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, Conv, [1024, 3, 1]],
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
-
-   [-2, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Bottleneck, [512, False]],
-   [-1, 1, Bottleneck, [512, False]],
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
-
-   [-2, 1, Conv, [128, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
-   [-1, 1, Bottleneck, [256, False]],
-   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
-
-   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5-bifpn.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 BiFPN head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14, 6], 1, Concat, [1]],  # cat P4 <--- BiFPN change
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5-fpn.yaml

@@ -1,42 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 FPN head
-head:
-  [[-1, 3, C3, [1024, False]],  # 10 (P5/32-large)
-
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 3, C3, [512, False]],  # 14 (P4/16-medium)
-
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 3, C3, [256, False]],  # 18 (P3/8-small)
-
-   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5-p2.yaml

@@ -1,54 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head with (P2, P3, P4, P5) outputs
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [128, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 2], 1, Concat, [1]],  # cat backbone P2
-   [-1, 1, C3, [128, False]],  # 21 (P2/4-xsmall)
-
-   [-1, 1, Conv, [128, 3, 2]],
-   [[-1, 18], 1, Concat, [1]],  # cat head P3
-   [-1, 3, C3, [256, False]],  # 24 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 27 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 30 (P5/32-large)
-
-   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(P2, P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5-p34.yaml

@@ -1,41 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [ [ -1, 1, Conv, [ 64, 6, 2, 2 ] ],  # 0-P1/2
-    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
-    [ -1, 3, C3, [ 128 ] ],
-    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
-    [ -1, 6, C3, [ 256 ] ],
-    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
-    [ -1, 9, C3, [ 512 ] ],
-    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 7-P5/32
-    [ -1, 3, C3, [ 1024 ] ],
-    [ -1, 1, SPPF, [ 1024, 5 ] ],  # 9
-  ]
-
-# YOLOv5 v6.0 head with (P3, P4) outputs
-head:
-  [ [ -1, 1, Conv, [ 512, 1, 1 ] ],
-    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
-    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
-    [ -1, 3, C3, [ 512, False ] ],  # 13
-
-    [ -1, 1, Conv, [ 256, 1, 1 ] ],
-    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
-    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
-    [ -1, 3, C3, [ 256, False ] ],  # 17 (P3/8-small)
-
-    [ -1, 1, Conv, [ 256, 3, 2 ] ],
-    [ [ -1, 14 ], 1, Concat, [ 1 ] ],  # cat head P4
-    [ -1, 3, C3, [ 512, False ] ],  # 20 (P4/16-medium)
-
-    [ [ 17, 20 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4)
-  ]

ultralytics/yolov5/models/hub/yolov5-p6.yaml

@@ -1,56 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head with (P3, P4, P5, P6) outputs
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
-  ]

ultralytics/yolov5/models/hub/yolov5-p7.yaml

@@ -1,67 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, Conv, [1280, 3, 2]],  # 11-P7/128
-   [-1, 3, C3, [1280]],
-   [-1, 1, SPPF, [1280, 5]],  # 13
-  ]
-
-# YOLOv5 v6.0 head with (P3, P4, P5, P6, P7) outputs
-head:
-  [[-1, 1, Conv, [1024, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 10], 1, Concat, [1]],  # cat backbone P6
-   [-1, 3, C3, [1024, False]],  # 17
-
-   [-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 21
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 25
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 29 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 26], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 32 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 22], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 35 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 18], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 38 (P6/64-xlarge)
-
-   [-1, 1, Conv, [1024, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P7
-   [-1, 3, C3, [1280, False]],  # 41 (P7/128-xxlarge)
-
-   [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6, P7)
-  ]

ultralytics/yolov5/models/hub/yolov5-panet.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 PANet head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5l6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [19,27,  44,40,  38,94]  # P3/8
-  - [96,68,  86,152,  180,137]  # P4/16
-  - [140,301,  303,264,  238,542]  # P5/32
-  - [436,615,  739,380,  925,792]  # P6/64
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
-  ]

ultralytics/yolov5/models/hub/yolov5m6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-anchors:
-  - [19,27,  44,40,  38,94]  # P3/8
-  - [96,68,  86,152,  180,137]  # P4/16
-  - [140,301,  303,264,  238,542]  # P5/32
-  - [436,615,  739,380,  925,792]  # P6/64
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
-  ]

ultralytics/yolov5/models/hub/yolov5n6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.25  # layer channel multiple
-anchors:
-  - [19,27,  44,40,  38,94]  # P3/8
-  - [96,68,  86,152,  180,137]  # P4/16
-  - [140,301,  303,264,  238,542]  # P5/32
-  - [436,615,  739,380,  925,792]  # P6/64
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
-  ]

ultralytics/yolov5/models/hub/yolov5s-ghost.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, GhostConv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3Ghost, [128]],
-   [-1, 1, GhostConv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3Ghost, [256]],
-   [-1, 1, GhostConv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3Ghost, [512]],
-   [-1, 1, GhostConv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3Ghost, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, GhostConv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3Ghost, [512, False]],  # 13
-
-   [-1, 1, GhostConv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3Ghost, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, GhostConv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3Ghost, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, GhostConv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3Ghost, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5s-transformer.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3TR, [1024]],  # 9 <--- C3TR() Transformer module
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/hub/yolov5s6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-anchors:
-  - [19,27,  44,40,  38,94]  # P3/8
-  - [96,68,  86,152,  180,137]  # P4/16
-  - [140,301,  303,264,  238,542]  # P5/32
-  - [436,615,  739,380,  925,792]  # P6/64
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
-  ]

ultralytics/yolov5/models/hub/yolov5x6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.33  # model depth multiple
-width_multiple: 1.25  # layer channel multiple
-anchors:
-  - [19,27,  44,40,  38,94]  # P3/8
-  - [96,68,  86,152,  180,137]  # P4/16
-  - [140,301,  303,264,  238,542]  # P5/32
-  - [436,615,  739,380,  925,792]  # P6/64
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [768]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [768, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
-   [-1, 3, C3, [768, False]],  # 15
-
-   [-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 19
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 20], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 16], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
-
-   [-1, 1, Conv, [768, 3, 2]],
-   [[-1, 12], 1, Concat, [1]],  # cat head P6
-   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
-
-   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
-  ]

ultralytics/yolov5/models/tf.py

@@ -1,466 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-TensorFlow, Keras and TFLite versions of YOLOv5
-Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
-
-Usage:
-    $ python models/tf.py --weights yolov5s.pt
-
-Export:
-    $ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
-"""
-
-import argparse
-import sys
-from copy import deepcopy
-from pathlib import Path
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[1]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-# ROOT = ROOT.relative_to(Path.cwd())  # relative
-
-import numpy as np
-import tensorflow as tf
-import torch
-import torch.nn as nn
-from tensorflow import keras
-
-from models.common import C3, SPP, SPPF, Bottleneck, BottleneckCSP, Concat, Conv, DWConv, Focus, autopad
-from models.experimental import CrossConv, MixConv2d, attempt_load
-from models.yolo import Detect
-from utils.activations import SiLU
-from utils.general import LOGGER, make_divisible, print_args
-
-
-class TFBN(keras.layers.Layer):
-    # TensorFlow BatchNormalization wrapper
-    def __init__(self, w=None):
-        super().__init__()
-        self.bn = keras.layers.BatchNormalization(
-            beta_initializer=keras.initializers.Constant(w.bias.numpy()),
-            gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
-            moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
-            moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
-            epsilon=w.eps)
-
-    def call(self, inputs):
-        return self.bn(inputs)
-
-
-class TFPad(keras.layers.Layer):
-    def __init__(self, pad):
-        super().__init__()
-        self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
-
-    def call(self, inputs):
-        return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
-
-
-class TFConv(keras.layers.Layer):
-    # Standard convolution
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
-        # ch_in, ch_out, weights, kernel, stride, padding, groups
-        super().__init__()
-        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
-        assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
-        # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
-        # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
-
-        conv = keras.layers.Conv2D(
-            c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
-            kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
-            bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
-        self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
-        self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
-
-        # YOLOv5 activations
-        if isinstance(w.act, nn.LeakyReLU):
-            self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
-        elif isinstance(w.act, nn.Hardswish):
-            self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
-        elif isinstance(w.act, (nn.SiLU, SiLU)):
-            self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
-        else:
-            raise Exception(f'no matching TensorFlow activation found for {w.act}')
-
-    def call(self, inputs):
-        return self.act(self.bn(self.conv(inputs)))
-
-
-class TFFocus(keras.layers.Layer):
-    # Focus wh information into c-space
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
-        # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__()
-        self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
-
-    def call(self, inputs):  # x(b,w,h,c) -> y(b,w/2,h/2,4c)
-        # inputs = inputs / 255  # normalize 0-255 to 0-1
-        return self.conv(tf.concat([inputs[:, ::2, ::2, :],
-                                    inputs[:, 1::2, ::2, :],
-                                    inputs[:, ::2, 1::2, :],
-                                    inputs[:, 1::2, 1::2, :]], 3))
-
-
-class TFBottleneck(keras.layers.Layer):
-    # Standard bottleneck
-    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None):  # ch_in, ch_out, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
-        self.add = shortcut and c1 == c2
-
-    def call(self, inputs):
-        return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
-
-
-class TFConv2d(keras.layers.Layer):
-    # Substitution for PyTorch nn.Conv2D
-    def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
-        super().__init__()
-        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
-        self.conv = keras.layers.Conv2D(
-            c2, k, s, 'VALID', use_bias=bias,
-            kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
-            bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
-
-    def call(self, inputs):
-        return self.conv(inputs)
-
-
-class TFBottleneckCSP(keras.layers.Layer):
-    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
-        # ch_in, ch_out, number, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
-        self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
-        self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
-        self.bn = TFBN(w.bn)
-        self.act = lambda x: keras.activations.relu(x, alpha=0.1)
-        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
-
-    def call(self, inputs):
-        y1 = self.cv3(self.m(self.cv1(inputs)))
-        y2 = self.cv2(inputs)
-        return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
-
-
-class TFC3(keras.layers.Layer):
-    # CSP Bottleneck with 3 convolutions
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
-        # ch_in, ch_out, number, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
-        self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
-        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
-
-    def call(self, inputs):
-        return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
-
-
-class TFSPP(keras.layers.Layer):
-    # Spatial pyramid pooling layer used in YOLOv3-SPP
-    def __init__(self, c1, c2, k=(5, 9, 13), w=None):
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
-        self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
-
-    def call(self, inputs):
-        x = self.cv1(inputs)
-        return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
-
-
-class TFSPPF(keras.layers.Layer):
-    # Spatial pyramid pooling-Fast layer
-    def __init__(self, c1, c2, k=5, w=None):
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
-        self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
-
-    def call(self, inputs):
-        x = self.cv1(inputs)
-        y1 = self.m(x)
-        y2 = self.m(y1)
-        return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
-
-
-class TFDetect(keras.layers.Layer):
-    def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None):  # detection layer
-        super().__init__()
-        self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
-        self.nc = nc  # number of classes
-        self.no = nc + 5  # number of outputs per anchor
-        self.nl = len(anchors)  # number of detection layers
-        self.na = len(anchors[0]) // 2  # number of anchors
-        self.grid = [tf.zeros(1)] * self.nl  # init grid
-        self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
-        self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
-                                      [self.nl, 1, -1, 1, 2])
-        self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
-        self.training = False  # set to False after building model
-        self.imgsz = imgsz
-        for i in range(self.nl):
-            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
-            self.grid[i] = self._make_grid(nx, ny)
-
-    def call(self, inputs):
-        z = []  # inference output
-        x = []
-        for i in range(self.nl):
-            x.append(self.m[i](inputs[i]))
-            # x(bs,20,20,255) to x(bs,3,20,20,85)
-            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
-            x[i] = tf.reshape(x[i], [-1, ny * nx, self.na, self.no])
-
-            if not self.training:  # inference
-                y = tf.sigmoid(x[i])
-                grid = tf.transpose(self.grid[i], [0, 2, 1, 3]) - 0.5
-                anchor_grid = tf.transpose(self.anchor_grid[i], [0, 2, 1, 3]) * 4
-                xy = (y[..., 0:2] * 2 + grid) * self.stride[i]  # xy
-                wh = y[..., 2:4] ** 2 * anchor_grid
-                # Normalize xywh to 0-1 to reduce calibration error
-                xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
-                wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
-                y = tf.concat([xy, wh, y[..., 4:]], -1)
-                z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
-
-        return tf.transpose(x, [0, 2, 1, 3]) if self.training else (tf.concat(z, 1), x)
-
-    @staticmethod
-    def _make_grid(nx=20, ny=20):
-        # yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
-        # return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
-        xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
-        return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
-
-
-class TFUpsample(keras.layers.Layer):
-    def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
-        super().__init__()
-        assert scale_factor == 2, "scale_factor must be 2"
-        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
-        # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
-        # with default arguments: align_corners=False, half_pixel_centers=False
-        # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
-        #                                                            size=(x.shape[1] * 2, x.shape[2] * 2))
-
-    def call(self, inputs):
-        return self.upsample(inputs)
-
-
-class TFConcat(keras.layers.Layer):
-    def __init__(self, dimension=1, w=None):
-        super().__init__()
-        assert dimension == 1, "convert only NCHW to NHWC concat"
-        self.d = 3
-
-    def call(self, inputs):
-        return tf.concat(inputs, self.d)
-
-
-def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
-    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
-    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
-    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
-    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
-
-    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
-    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
-        m_str = m
-        m = eval(m) if isinstance(m, str) else m  # eval strings
-        for j, a in enumerate(args):
-            try:
-                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
-            except NameError:
-                pass
-
-        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
-            c1, c2 = ch[f], args[0]
-            c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
-
-            args = [c1, c2, *args[1:]]
-            if m in [BottleneckCSP, C3]:
-                args.insert(2, n)
-                n = 1
-        elif m is nn.BatchNorm2d:
-            args = [ch[f]]
-        elif m is Concat:
-            c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
-        elif m is Detect:
-            args.append([ch[x + 1] for x in f])
-            if isinstance(args[1], int):  # number of anchors
-                args[1] = [list(range(args[1] * 2))] * len(f)
-            args.append(imgsz)
-        else:
-            c2 = ch[f]
-
-        tf_m = eval('TF' + m_str.replace('nn.', ''))
-        m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
-            else tf_m(*args, w=model.model[i])  # module
-
-        torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
-        t = str(m)[8:-2].replace('__main__.', '')  # module type
-        np = sum(x.numel() for x in torch_m_.parameters())  # number params
-        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
-        LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10}  {t:<40}{str(args):<30}')  # print
-        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
-        layers.append(m_)
-        ch.append(c2)
-    return keras.Sequential(layers), sorted(save)
-
-
-class TFModel:
-    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)):  # model, channels, classes
-        super().__init__()
-        if isinstance(cfg, dict):
-            self.yaml = cfg  # model dict
-        else:  # is *.yaml
-            import yaml  # for torch hub
-            self.yaml_file = Path(cfg).name
-            with open(cfg) as f:
-                self.yaml = yaml.load(f, Loader=yaml.FullLoader)  # model dict
-
-        # Define model
-        if nc and nc != self.yaml['nc']:
-            LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
-            self.yaml['nc'] = nc  # override yaml value
-        self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
-
-    def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
-                conf_thres=0.25):
-        y = []  # outputs
-        x = inputs
-        for i, m in enumerate(self.model.layers):
-            if m.f != -1:  # if not from previous layer
-                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
-
-            x = m(x)  # run
-            y.append(x if m.i in self.savelist else None)  # save output
-
-        # Add TensorFlow NMS
-        if tf_nms:
-            boxes = self._xywh2xyxy(x[0][..., :4])
-            probs = x[0][:, :, 4:5]
-            classes = x[0][:, :, 5:]
-            scores = probs * classes
-            if agnostic_nms:
-                nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
-                return nms, x[1]
-            else:
-                boxes = tf.expand_dims(boxes, 2)
-                nms = tf.image.combined_non_max_suppression(
-                    boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
-                return nms, x[1]
-
-        return x[0]  # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
-        # x = x[0][0]  # [x(1,6300,85), ...] to x(6300,85)
-        # xywh = x[..., :4]  # x(6300,4) boxes
-        # conf = x[..., 4:5]  # x(6300,1) confidences
-        # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1))  # x(6300,1)  classes
-        # return tf.concat([conf, cls, xywh], 1)
-
-    @staticmethod
-    def _xywh2xyxy(xywh):
-        # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
-        x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
-        return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
-
-
-class AgnosticNMS(keras.layers.Layer):
-    # TF Agnostic NMS
-    def call(self, input, topk_all, iou_thres, conf_thres):
-        # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
-        return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
-                         fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
-                         name='agnostic_nms')
-
-    @staticmethod
-    def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25):  # agnostic NMS
-        boxes, classes, scores = x
-        class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
-        scores_inp = tf.reduce_max(scores, -1)
-        selected_inds = tf.image.non_max_suppression(
-            boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
-        selected_boxes = tf.gather(boxes, selected_inds)
-        padded_boxes = tf.pad(selected_boxes,
-                              paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
-                              mode="CONSTANT", constant_values=0.0)
-        selected_scores = tf.gather(scores_inp, selected_inds)
-        padded_scores = tf.pad(selected_scores,
-                               paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
-                               mode="CONSTANT", constant_values=-1.0)
-        selected_classes = tf.gather(class_inds, selected_inds)
-        padded_classes = tf.pad(selected_classes,
-                                paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
-                                mode="CONSTANT", constant_values=-1.0)
-        valid_detections = tf.shape(selected_inds)[0]
-        return padded_boxes, padded_scores, padded_classes, valid_detections
-
-
-def representative_dataset_gen(dataset, ncalib=100):
-    # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
-    for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
-        input = np.transpose(img, [1, 2, 0])
-        input = np.expand_dims(input, axis=0).astype(np.float32)
-        input /= 255
-        yield [input]
-        if n >= ncalib:
-            break
-
-
-def run(weights=ROOT / 'yolov5s.pt',  # weights path
-        imgsz=(640, 640),  # inference size h,w
-        batch_size=1,  # batch size
-        dynamic=False,  # dynamic batch size
-        ):
-    # PyTorch model
-    im = torch.zeros((batch_size, 3, *imgsz))  # BCHW image
-    model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
-    _ = model(im)  # inference
-    model.info()
-
-    # TensorFlow model
-    im = tf.zeros((batch_size, *imgsz, 3))  # BHWC image
-    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
-    _ = tf_model.predict(im)  # inference
-
-    # Keras model
-    im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
-    keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
-    keras_model.summary()
-
-    LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
-    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
-    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
-    parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
-    opt = parser.parse_args()
-    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
-    print_args(FILE.stem, opt)
-    return opt
-
-
-def main(opt):
-    run(**vars(opt))
-
-
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)

ultralytics/yolov5/models/yolo.py

@@ -1,329 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-YOLO-specific modules
-
-Usage:
-    $ python path/to/models/yolo.py --cfg yolov5s.yaml
-"""
-
-import argparse
-import sys
-from copy import deepcopy
-from pathlib import Path
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[1]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-# ROOT = ROOT.relative_to(Path.cwd())  # relative
-
-from models.common import *
-from models.experimental import *
-from utils.autoanchor import check_anchor_order
-from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
-from utils.plots import feature_visualization
-from utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device, time_sync
-
-try:
-    import thop  # for FLOPs computation
-except ImportError:
-    thop = None
-
-
-class Detect(nn.Module):
-    stride = None  # strides computed during build
-    onnx_dynamic = False  # ONNX export parameter
-
-    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
-        super().__init__()
-        self.nc = nc  # number of classes
-        self.no = nc + 5  # number of outputs per anchor
-        self.nl = len(anchors)  # number of detection layers
-        self.na = len(anchors[0]) // 2  # number of anchors
-        self.grid = [torch.zeros(1)] * self.nl  # init grid
-        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
-        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
-        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
-        self.inplace = inplace  # use in-place ops (e.g. slice assignment)
-
-    def forward(self, x):
-        z = []  # inference output
-        for i in range(self.nl):
-            x[i] = self.m[i](x[i])  # conv
-            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
-            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
-
-            if not self.training:  # inference
-                if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
-                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
-
-                y = x[i].sigmoid()
-                if self.inplace:
-                    y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
-                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
-                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
-                    xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
-                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
-                    y = torch.cat((xy, wh, y[..., 4:]), -1)
-                z.append(y.view(bs, -1, self.no))
-
-        return x if self.training else (torch.cat(z, 1), x)
-
-    def _make_grid(self, nx=20, ny=20, i=0):
-        d = self.anchors[i].device
-        shape = 1, self.na, ny, nx, 2  # grid shape
-        if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
-            yv, xv = torch.meshgrid(torch.arange(ny, device=d), torch.arange(nx, device=d), indexing='ij')
-        else:
-            yv, xv = torch.meshgrid(torch.arange(ny, device=d), torch.arange(nx, device=d))
-        grid = torch.stack((xv, yv), 2).expand(shape).float()
-        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape).float()
-        return grid, anchor_grid
-
-
-class Model(nn.Module):
-    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
-        super().__init__()
-        if isinstance(cfg, dict):
-            self.yaml = cfg  # model dict
-        else:  # is *.yaml
-            import yaml  # for torch hub
-            self.yaml_file = Path(cfg).name
-            with open(cfg, encoding='ascii', errors='ignore') as f:
-                self.yaml = yaml.safe_load(f)  # model dict
-
-        # Define model
-        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
-        if nc and nc != self.yaml['nc']:
-            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
-            self.yaml['nc'] = nc  # override yaml value
-        if anchors:
-            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
-            self.yaml['anchors'] = round(anchors)  # override yaml value
-        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
-        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
-        self.inplace = self.yaml.get('inplace', True)
-
-        # Build strides, anchors
-        m = self.model[-1]  # Detect()
-        if isinstance(m, Detect):
-            s = 256  # 2x min stride
-            m.inplace = self.inplace
-            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
-            check_anchor_order(m)  # must be in pixel-space (not grid-space)
-            m.anchors /= m.stride.view(-1, 1, 1)
-            self.stride = m.stride
-            self._initialize_biases()  # only run once
-
-        # Init weights, biases
-        initialize_weights(self)
-        self.info()
-        LOGGER.info('')
-
-    def forward(self, x, augment=False, profile=False, visualize=False):
-        if augment:
-            return self._forward_augment(x)  # augmented inference, None
-        return self._forward_once(x, profile, visualize)  # single-scale inference, train
-
-    def _forward_augment(self, x):
-        img_size = x.shape[-2:]  # height, width
-        s = [1, 0.83, 0.67]  # scales
-        f = [None, 3, None]  # flips (2-ud, 3-lr)
-        y = []  # outputs
-        for si, fi in zip(s, f):
-            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
-            yi = self._forward_once(xi)[0]  # forward
-            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
-            yi = self._descale_pred(yi, fi, si, img_size)
-            y.append(yi)
-        y = self._clip_augmented(y)  # clip augmented tails
-        return torch.cat(y, 1), None  # augmented inference, train
-
-    def _forward_once(self, x, profile=False, visualize=False):
-        y, dt = [], []  # outputs
-        for m in self.model:
-            if m.f != -1:  # if not from previous layer
-                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
-            if profile:
-                self._profile_one_layer(m, x, dt)
-            x = m(x)  # run
-            y.append(x if m.i in self.save else None)  # save output
-            if visualize:
-                feature_visualization(x, m.type, m.i, save_dir=visualize)
-        return x
-
-    def _descale_pred(self, p, flips, scale, img_size):
-        # de-scale predictions following augmented inference (inverse operation)
-        if self.inplace:
-            p[..., :4] /= scale  # de-scale
-            if flips == 2:
-                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
-            elif flips == 3:
-                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
-        else:
-            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
-            if flips == 2:
-                y = img_size[0] - y  # de-flip ud
-            elif flips == 3:
-                x = img_size[1] - x  # de-flip lr
-            p = torch.cat((x, y, wh, p[..., 4:]), -1)
-        return p
-
-    def _clip_augmented(self, y):
-        # Clip YOLOv5 augmented inference tails
-        nl = self.model[-1].nl  # number of detection layers (P3-P5)
-        g = sum(4 ** x for x in range(nl))  # grid points
-        e = 1  # exclude layer count
-        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
-        y[0] = y[0][:, :-i]  # large
-        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
-        y[-1] = y[-1][:, i:]  # small
-        return y
-
-    def _profile_one_layer(self, m, x, dt):
-        c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
-        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
-        t = time_sync()
-        for _ in range(10):
-            m(x.copy() if c else x)
-        dt.append((time_sync() - t) * 100)
-        if m == self.model[0]:
-            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  {'module'}")
-        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
-        if c:
-            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
-
-    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
-        # https://arxiv.org/abs/1708.02002 section 3.3
-        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
-        m = self.model[-1]  # Detect() module
-        for mi, s in zip(m.m, m.stride):  # from
-            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
-            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
-            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # cls
-            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
-
-    def _print_biases(self):
-        m = self.model[-1]  # Detect() module
-        for mi in m.m:  # from
-            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
-            LOGGER.info(
-                ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
-
-    # def _print_weights(self):
-    #     for m in self.model.modules():
-    #         if type(m) is Bottleneck:
-    #             LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
-
-    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
-        LOGGER.info('Fusing layers... ')
-        for m in self.model.modules():
-            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
-                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
-                delattr(m, 'bn')  # remove batchnorm
-                m.forward = m.forward_fuse  # update forward
-        self.info()
-        return self
-
-    def info(self, verbose=False, img_size=640):  # print model information
-        model_info(self, verbose, img_size)
-
-    def _apply(self, fn):
-        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
-        self = super()._apply(fn)
-        m = self.model[-1]  # Detect()
-        if isinstance(m, Detect):
-            m.stride = fn(m.stride)
-            m.grid = list(map(fn, m.grid))
-            if isinstance(m.anchor_grid, list):
-                m.anchor_grid = list(map(fn, m.anchor_grid))
-        return self
-
-
-def parse_model(d, ch):  # model_dict, input_channels(3)
-    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
-    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
-    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
-    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
-
-    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
-    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
-        m = eval(m) if isinstance(m, str) else m  # eval strings
-        for j, a in enumerate(args):
-            try:
-                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
-            except NameError:
-                pass
-
-        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
-                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
-            c1, c2 = ch[f], args[0]
-            if c2 != no:  # if not output
-                c2 = make_divisible(c2 * gw, 8)
-
-            args = [c1, c2, *args[1:]]
-            if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
-                args.insert(2, n)  # number of repeats
-                n = 1
-        elif m is nn.BatchNorm2d:
-            args = [ch[f]]
-        elif m is Concat:
-            c2 = sum(ch[x] for x in f)
-        elif m is Detect:
-            args.append([ch[x] for x in f])
-            if isinstance(args[1], int):  # number of anchors
-                args[1] = [list(range(args[1] * 2))] * len(f)
-        elif m is Contract:
-            c2 = ch[f] * args[0] ** 2
-        elif m is Expand:
-            c2 = ch[f] // args[0] ** 2
-        else:
-            c2 = ch[f]
-
-        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
-        t = str(m)[8:-2].replace('__main__.', '')  # module type
-        np = sum(x.numel() for x in m_.parameters())  # number params
-        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
-        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
-        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
-        layers.append(m_)
-        if i == 0:
-            ch = []
-        ch.append(c2)
-    return nn.Sequential(*layers), sorted(save)
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
-    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-    parser.add_argument('--profile', action='store_true', help='profile model speed')
-    parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
-    opt = parser.parse_args()
-    opt.cfg = check_yaml(opt.cfg)  # check YAML
-    print_args(FILE.stem, opt)
-    device = select_device(opt.device)
-
-    # Create model
-    model = Model(opt.cfg).to(device)
-    model.train()
-
-    # Profile
-    if opt.profile:
-        img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
-        y = model(img, profile=True)
-
-    # Test all models
-    if opt.test:
-        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
-            try:
-                _ = Model(cfg)
-            except Exception as e:
-                print(f'Error in {cfg}: {e}')
-
-    # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
-    # from torch.utils.tensorboard import SummaryWriter
-    # tb_writer = SummaryWriter('.')
-    # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
-    # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), [])  # add model graph

ultralytics/yolov5/models/yolov5l.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/yolov5m.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/yolov5n.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.25  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/yolov5s.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/models/yolov5x.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.33  # model depth multiple
-width_multiple: 1.25  # layer channel multiple
-anchors:
-  - [10,13, 16,30, 33,23]  # P3/8
-  - [30,61, 62,45, 59,119]  # P4/16
-  - [116,90, 156,198, 373,326]  # P5/32
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3, [128]],
-   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3, [256]],
-   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]],
-   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, Conv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3, [512, False]],  # 13
-
-   [-1, 1, Conv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, Conv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, Conv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

ultralytics/yolov5/utils/__init__.py

@@ -1,36 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-utils/initialization
-"""
-
-
-def notebook_init(verbose=True):
-    # Check system software and hardware
-    print('Checking setup...')
-
-    import os
-    import shutil
-
-    from utils.general import check_requirements, emojis, is_colab
-    from utils.torch_utils import select_device  # imports
-
-    check_requirements(('psutil', 'IPython'))
-    import psutil
-    from IPython import display  # to display images and clear console output
-
-    if is_colab():
-        shutil.rmtree('/content/sample_data', ignore_errors=True)  # remove colab /sample_data directory
-
-    # System info
-    if verbose:
-        gb = 1 << 30  # bytes to GiB (1024 ** 3)
-        ram = psutil.virtual_memory().total
-        total, used, free = shutil.disk_usage("/")
-        display.clear_output()
-        s = f'({os.cpu_count()} CPUs, {ram / gb:.1f} GB RAM, {(total - free) / gb:.1f}/{total / gb:.1f} GB disk)'
-    else:
-        s = ''
-
-    select_device(newline=False)
-    print(emojis(f'Setup complete ✅ {s}'))
-    return display

ultralytics/yolov5/utils/activations.py

@@ -1,101 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Activation functions
-"""
-
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-
-
-# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
-class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
-    @staticmethod
-    def forward(x):
-        return x * torch.sigmoid(x)
-
-
-class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
-    @staticmethod
-    def forward(x):
-        # return x * F.hardsigmoid(x)  # for TorchScript and CoreML
-        return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0  # for TorchScript, CoreML and ONNX
-
-
-# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
-class Mish(nn.Module):
-    @staticmethod
-    def forward(x):
-        return x * F.softplus(x).tanh()
-
-
-class MemoryEfficientMish(nn.Module):
-    class F(torch.autograd.Function):
-        @staticmethod
-        def forward(ctx, x):
-            ctx.save_for_backward(x)
-            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))
-
-        @staticmethod
-        def backward(ctx, grad_output):
-            x = ctx.saved_tensors[0]
-            sx = torch.sigmoid(x)
-            fx = F.softplus(x).tanh()
-            return grad_output * (fx + x * sx * (1 - fx * fx))
-
-    def forward(self, x):
-        return self.F.apply(x)
-
-
-# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
-class FReLU(nn.Module):
-    def __init__(self, c1, k=3):  # ch_in, kernel
-        super().__init__()
-        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
-        self.bn = nn.BatchNorm2d(c1)
-
-    def forward(self, x):
-        return torch.max(x, self.bn(self.conv(x)))
-
-
-# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
-class AconC(nn.Module):
-    r""" ACON activation (activate or not).
-    AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
-    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
-    """
-
-    def __init__(self, c1):
-        super().__init__()
-        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
-        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
-        self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
-
-    def forward(self, x):
-        dpx = (self.p1 - self.p2) * x
-        return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
-
-
-class MetaAconC(nn.Module):
-    r""" ACON activation (activate or not).
-    MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
-    according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
-    """
-
-    def __init__(self, c1, k=1, s=1, r=16):  # ch_in, kernel, stride, r
-        super().__init__()
-        c2 = max(r, c1 // r)
-        self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
-        self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
-        self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
-        self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
-        # self.bn1 = nn.BatchNorm2d(c2)
-        # self.bn2 = nn.BatchNorm2d(c1)
-
-    def forward(self, x):
-        y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
-        # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
-        # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y)))))  # bug/unstable
-        beta = torch.sigmoid(self.fc2(self.fc1(y)))  # bug patch BN layers removed
-        dpx = (self.p1 - self.p2) * x
-        return dpx * torch.sigmoid(beta * dpx) + self.p2 * x

ultralytics/yolov5/utils/augmentations.py

@@ -1,277 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Image augmentation functions
-"""
-
-import math
-import random
-
-import cv2
-import numpy as np
-
-from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box
-from utils.metrics import bbox_ioa
-
-
-class Albumentations:
-    # YOLOv5 Albumentations class (optional, only used if package is installed)
-    def __init__(self):
-        self.transform = None
-        try:
-            import albumentations as A
-            check_version(A.__version__, '1.0.3', hard=True)  # version requirement
-
-            self.transform = A.Compose([
-                A.Blur(p=0.01),
-                A.MedianBlur(p=0.01),
-                A.ToGray(p=0.01),
-                A.CLAHE(p=0.01),
-                A.RandomBrightnessContrast(p=0.0),
-                A.RandomGamma(p=0.0),
-                A.ImageCompression(quality_lower=75, p=0.0)],
-                bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
-
-            LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
-        except ImportError:  # package not installed, skip
-            pass
-        except Exception as e:
-            LOGGER.info(colorstr('albumentations: ') + f'{e}')
-
-    def __call__(self, im, labels, p=1.0):
-        if self.transform and random.random() < p:
-            new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0])  # transformed
-            im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
-        return im, labels
-
-
-def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
-    # HSV color-space augmentation
-    if hgain or sgain or vgain:
-        r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains
-        hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
-        dtype = im.dtype  # uint8
-
-        x = np.arange(0, 256, dtype=r.dtype)
-        lut_hue = ((x * r[0]) % 180).astype(dtype)
-        lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
-        lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
-
-        im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
-        cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im)  # no return needed
-
-
-def hist_equalize(im, clahe=True, bgr=False):
-    # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255
-    yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
-    if clahe:
-        c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
-        yuv[:, :, 0] = c.apply(yuv[:, :, 0])
-    else:
-        yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0])  # equalize Y channel histogram
-    return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB)  # convert YUV image to RGB
-
-
-def replicate(im, labels):
-    # Replicate labels
-    h, w = im.shape[:2]
-    boxes = labels[:, 1:].astype(int)
-    x1, y1, x2, y2 = boxes.T
-    s = ((x2 - x1) + (y2 - y1)) / 2  # side length (pixels)
-    for i in s.argsort()[:round(s.size * 0.5)]:  # smallest indices
-        x1b, y1b, x2b, y2b = boxes[i]
-        bh, bw = y2b - y1b, x2b - x1b
-        yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw))  # offset x, y
-        x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
-        im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b]  # im4[ymin:ymax, xmin:xmax]
-        labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
-
-    return im, labels
-
-
-def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
-    # Resize and pad image while meeting stride-multiple constraints
-    shape = im.shape[:2]  # current shape [height, width]
-    if isinstance(new_shape, int):
-        new_shape = (new_shape, new_shape)
-
-    # Scale ratio (new / old)
-    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
-    if not scaleup:  # only scale down, do not scale up (for better val mAP)
-        r = min(r, 1.0)
-
-    # Compute padding
-    ratio = r, r  # width, height ratios
-    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
-    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
-    if auto:  # minimum rectangle
-        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
-    elif scaleFill:  # stretch
-        dw, dh = 0.0, 0.0
-        new_unpad = (new_shape[1], new_shape[0])
-        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
-
-    dw /= 2  # divide padding into 2 sides
-    dh /= 2
-
-    if shape[::-1] != new_unpad:  # resize
-        im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
-    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
-    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
-    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
-    return im, ratio, (dw, dh)
-
-
-def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
-                       border=(0, 0)):
-    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
-    # targets = [cls, xyxy]
-
-    height = im.shape[0] + border[0] * 2  # shape(h,w,c)
-    width = im.shape[1] + border[1] * 2
-
-    # Center
-    C = np.eye(3)
-    C[0, 2] = -im.shape[1] / 2  # x translation (pixels)
-    C[1, 2] = -im.shape[0] / 2  # y translation (pixels)
-
-    # Perspective
-    P = np.eye(3)
-    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
-    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)
-
-    # Rotation and Scale
-    R = np.eye(3)
-    a = random.uniform(-degrees, degrees)
-    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
-    s = random.uniform(1 - scale, 1 + scale)
-    # s = 2 ** random.uniform(-scale, scale)
-    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
-
-    # Shear
-    S = np.eye(3)
-    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
-    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)
-
-    # Translation
-    T = np.eye(3)
-    T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
-    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)
-
-    # Combined rotation matrix
-    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
-    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
-        if perspective:
-            im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
-        else:  # affine
-            im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
-
-    # Visualize
-    # import matplotlib.pyplot as plt
-    # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
-    # ax[0].imshow(im[:, :, ::-1])  # base
-    # ax[1].imshow(im2[:, :, ::-1])  # warped
-
-    # Transform label coordinates
-    n = len(targets)
-    if n:
-        use_segments = any(x.any() for x in segments)
-        new = np.zeros((n, 4))
-        if use_segments:  # warp segments
-            segments = resample_segments(segments)  # upsample
-            for i, segment in enumerate(segments):
-                xy = np.ones((len(segment), 3))
-                xy[:, :2] = segment
-                xy = xy @ M.T  # transform
-                xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]  # perspective rescale or affine
-
-                # clip
-                new[i] = segment2box(xy, width, height)
-
-        else:  # warp boxes
-            xy = np.ones((n * 4, 3))
-            xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
-            xy = xy @ M.T  # transform
-            xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8)  # perspective rescale or affine
-
-            # create new boxes
-            x = xy[:, [0, 2, 4, 6]]
-            y = xy[:, [1, 3, 5, 7]]
-            new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
-
-            # clip
-            new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
-            new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
-
-        # filter candidates
-        i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
-        targets = targets[i]
-        targets[:, 1:5] = new[i]
-
-    return im, targets
-
-
-def copy_paste(im, labels, segments, p=0.5):
-    # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
-    n = len(segments)
-    if p and n:
-        h, w, c = im.shape  # height, width, channels
-        im_new = np.zeros(im.shape, np.uint8)
-        for j in random.sample(range(n), k=round(p * n)):
-            l, s = labels[j], segments[j]
-            box = w - l[3], l[2], w - l[1], l[4]
-            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
-            if (ioa < 0.30).all():  # allow 30% obscuration of existing labels
-                labels = np.concatenate((labels, [[l[0], *box]]), 0)
-                segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
-                cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
-
-        result = cv2.bitwise_and(src1=im, src2=im_new)
-        result = cv2.flip(result, 1)  # augment segments (flip left-right)
-        i = result > 0  # pixels to replace
-        # i[:, :] = result.max(2).reshape(h, w, 1)  # act over ch
-        im[i] = result[i]  # cv2.imwrite('debug.jpg', im)  # debug
-
-    return im, labels, segments
-
-
-def cutout(im, labels, p=0.5):
-    # Applies image cutout augmentation https://arxiv.org/abs/1708.04552
-    if random.random() < p:
-        h, w = im.shape[:2]
-        scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16  # image size fraction
-        for s in scales:
-            mask_h = random.randint(1, int(h * s))  # create random masks
-            mask_w = random.randint(1, int(w * s))
-
-            # box
-            xmin = max(0, random.randint(0, w) - mask_w // 2)
-            ymin = max(0, random.randint(0, h) - mask_h // 2)
-            xmax = min(w, xmin + mask_w)
-            ymax = min(h, ymin + mask_h)
-
-            # apply random color mask
-            im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
-
-            # return unobscured labels
-            if len(labels) and s > 0.03:
-                box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
-                ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
-                labels = labels[ioa < 0.60]  # remove >60% obscured labels
-
-    return labels
-
-
-def mixup(im, labels, im2, labels2):
-    # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
-    r = np.random.beta(32.0, 32.0)  # mixup ratio, alpha=beta=32.0
-    im = (im * r + im2 * (1 - r)).astype(np.uint8)
-    labels = np.concatenate((labels, labels2), 0)
-    return im, labels
-
-
-def box_candidates(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16):  # box1(4,n), box2(4,n)
-    # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
-    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
-    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
-    ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
-    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr)  # candidates

ultralytics/yolov5/utils/autoanchor.py

@@ -1,170 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-AutoAnchor utils
-"""
-
-import random
-
-import numpy as np
-import torch
-import yaml
-from tqdm import tqdm
-
-from utils.general import LOGGER, colorstr, emojis
-
-PREFIX = colorstr('AutoAnchor: ')
-
-
-def check_anchor_order(m):
-    # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
-    a = m.anchors.prod(-1).mean(-1).view(-1)  # mean anchor area per output layer
-    da = a[-1] - a[0]  # delta a
-    ds = m.stride[-1] - m.stride[0]  # delta s
-    if da and (da.sign() != ds.sign()):  # same order
-        LOGGER.info(f'{PREFIX}Reversing anchor order')
-        m.anchors[:] = m.anchors.flip(0)
-
-
-def check_anchors(dataset, model, thr=4.0, imgsz=640):
-    # Check anchor fit to data, recompute if necessary
-    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
-    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
-    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
-    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
-
-    def metric(k):  # compute metric
-        r = wh[:, None] / k[None]
-        x = torch.min(r, 1 / r).min(2)[0]  # ratio metric
-        best = x.max(1)[0]  # best_x
-        aat = (x > 1 / thr).float().sum(1).mean()  # anchors above threshold
-        bpr = (best > 1 / thr).float().mean()  # best possible recall
-        return bpr, aat
-
-    stride = m.stride.to(m.anchors.device).view(-1, 1, 1)  # model strides
-    anchors = m.anchors.clone() * stride  # current anchors
-    bpr, aat = metric(anchors.cpu().view(-1, 2))
-    s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). '
-    if bpr > 0.98:  # threshold to recompute
-        LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset ✅'))
-    else:
-        LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...'))
-        na = m.anchors.numel() // 2  # number of anchors
-        try:
-            anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
-        except Exception as e:
-            LOGGER.info(f'{PREFIX}ERROR: {e}')
-        new_bpr = metric(anchors)[0]
-        if new_bpr > bpr:  # replace anchors
-            anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
-            m.anchors[:] = anchors.clone().view_as(m.anchors)
-            check_anchor_order(m)  # must be in pixel-space (not grid-space)
-            m.anchors /= stride
-            s = f'{PREFIX}Done ✅ (optional: update model *.yaml to use these anchors in the future)'
-        else:
-            s = f'{PREFIX}Done ⚠️ (original anchors better than new anchors, proceeding with original anchors)'
-        LOGGER.info(emojis(s))
-
-
-def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
-    """ Creates kmeans-evolved anchors from training dataset
-
-        Arguments:
-            dataset: path to data.yaml, or a loaded dataset
-            n: number of anchors
-            img_size: image size used for training
-            thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
-            gen: generations to evolve anchors using genetic algorithm
-            verbose: print all results
-
-        Return:
-            k: kmeans evolved anchors
-
-        Usage:
-            from utils.autoanchor import *; _ = kmean_anchors()
-    """
-    from scipy.cluster.vq import kmeans
-
-    npr = np.random
-    thr = 1 / thr
-
-    def metric(k, wh):  # compute metrics
-        r = wh[:, None] / k[None]
-        x = torch.min(r, 1 / r).min(2)[0]  # ratio metric
-        # x = wh_iou(wh, torch.tensor(k))  # iou metric
-        return x, x.max(1)[0]  # x, best_x
-
-    def anchor_fitness(k):  # mutation fitness
-        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
-        return (best * (best > thr).float()).mean()  # fitness
-
-    def print_results(k, verbose=True):
-        k = k[np.argsort(k.prod(1))]  # sort small to large
-        x, best = metric(k, wh0)
-        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
-        s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \
-            f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \
-            f'past_thr={x[x > thr].mean():.3f}-mean: '
-        for i, x in enumerate(k):
-            s += '%i,%i, ' % (round(x[0]), round(x[1]))
-        if verbose:
-            LOGGER.info(s[:-2])
-        return k
-
-    if isinstance(dataset, str):  # *.yaml file
-        with open(dataset, errors='ignore') as f:
-            data_dict = yaml.safe_load(f)  # model dict
-        from utils.datasets import LoadImagesAndLabels
-        dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
-
-    # Get label wh
-    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
-    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
-
-    # Filter
-    i = (wh0 < 3.0).any(1).sum()
-    if i:
-        LOGGER.info(f'{PREFIX}WARNING: Extremely small objects found: {i} of {len(wh0)} labels are < 3 pixels in size')
-    wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels
-    # wh = wh * (npr.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1
-
-    # Kmeans init
-    try:
-        LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...')
-        assert n <= len(wh)  # apply overdetermined constraint
-        s = wh.std(0)  # sigmas for whitening
-        k = kmeans(wh / s, n, iter=30)[0] * s  # points
-        assert n == len(k)  # kmeans may return fewer points than requested if wh is insufficient or too similar
-    except Exception:
-        LOGGER.warning(f'{PREFIX}WARNING: switching strategies from kmeans to random init')
-        k = np.sort(npr.rand(n * 2)).reshape(n, 2) * img_size  # random init
-    wh, wh0 = (torch.tensor(x, dtype=torch.float32) for x in (wh, wh0))
-    k = print_results(k, verbose=False)
-
-    # Plot
-    # k, d = [None] * 20, [None] * 20
-    # for i in tqdm(range(1, 21)):
-    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
-    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
-    # ax = ax.ravel()
-    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
-    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
-    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
-    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
-    # fig.savefig('wh.png', dpi=200)
-
-    # Evolve
-    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
-    pbar = tqdm(range(gen), bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
-    for _ in pbar:
-        v = np.ones(sh)
-        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
-            v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
-        kg = (k.copy() * v).clip(min=2.0)
-        fg = anchor_fitness(kg)
-        if fg > f:
-            f, k = fg, kg.copy()
-            pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
-            if verbose:
-                print_results(k, verbose)
-
-    return print_results(k)

ultralytics/yolov5/utils/autobatch.py

@@ -1,58 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Auto-batch utils
-"""
-
-from copy import deepcopy
-
-import numpy as np
-import torch
-from torch.cuda import amp
-
-from utils.general import LOGGER, colorstr
-from utils.torch_utils import profile
-
-
-def check_train_batch_size(model, imgsz=640):
-    # Check YOLOv5 training batch size
-    with amp.autocast():
-        return autobatch(deepcopy(model).train(), imgsz)  # compute optimal batch size
-
-
-def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
-    # Automatically estimate best batch size to use `fraction` of available CUDA memory
-    # Usage:
-    #     import torch
-    #     from utils.autobatch import autobatch
-    #     model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)
-    #     print(autobatch(model))
-
-    prefix = colorstr('AutoBatch: ')
-    LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}')
-    device = next(model.parameters()).device  # get model device
-    if device.type == 'cpu':
-        LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}')
-        return batch_size
-
-    gb = 1 << 30  # bytes to GiB (1024 ** 3)
-    d = str(device).upper()  # 'CUDA:0'
-    properties = torch.cuda.get_device_properties(device)  # device properties
-    t = properties.total_memory / gb  # (GiB)
-    r = torch.cuda.memory_reserved(device) / gb  # (GiB)
-    a = torch.cuda.memory_allocated(device) / gb  # (GiB)
-    f = t - (r + a)  # free inside reserved
-    LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free')
-
-    batch_sizes = [1, 2, 4, 8, 16]
-    try:
-        img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
-        y = profile(img, model, n=3, device=device)
-    except Exception as e:
-        LOGGER.warning(f'{prefix}{e}')
-
-    y = [x[2] for x in y if x]  # memory [2]
-    batch_sizes = batch_sizes[:len(y)]
-    p = np.polyfit(batch_sizes, y, deg=1)  # first degree polynomial fit
-    b = int((f * fraction - p[1]) / p[0])  # y intercept (optimal batch size)
-    LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)')
-    return b

ultralytics/yolov5/utils/aws/mime.sh

@@ -1,26 +0,0 @@
-# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
-# This script will run on every instance restart, not only on first start
-# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
-
-Content-Type: multipart/mixed; boundary="//"
-MIME-Version: 1.0
-
---//
-Content-Type: text/cloud-config; charset="us-ascii"
-MIME-Version: 1.0
-Content-Transfer-Encoding: 7bit
-Content-Disposition: attachment; filename="cloud-config.txt"
-
-#cloud-config
-cloud_final_modules:
-- [scripts-user, always]
-
---//
-Content-Type: text/x-shellscript; charset="us-ascii"
-MIME-Version: 1.0
-Content-Transfer-Encoding: 7bit
-Content-Disposition: attachment; filename="userdata.txt"
-
-#!/bin/bash
-# --- paste contents of userdata.sh here ---
---//

ultralytics/yolov5/utils/aws/resume.py

@@ -1,40 +0,0 @@
-# Resume all interrupted trainings in yolov5/ dir including DDP trainings
-# Usage: $ python utils/aws/resume.py
-
-import os
-import sys
-from pathlib import Path
-
-import torch
-import yaml
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[2]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-
-port = 0  # --master_port
-path = Path('').resolve()
-for last in path.rglob('*/**/last.pt'):
-    ckpt = torch.load(last)
-    if ckpt['optimizer'] is None:
-        continue
-
-    # Load opt.yaml
-    with open(last.parent.parent / 'opt.yaml', errors='ignore') as f:
-        opt = yaml.safe_load(f)
-
-    # Get device count
-    d = opt['device'].split(',')  # devices
-    nd = len(d)  # number of devices
-    ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1)  # distributed data parallel
-
-    if ddp:  # multi-GPU
-        port += 1
-        cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
-    else:  # single-GPU
-        cmd = f'python train.py --resume {last}'
-
-    cmd += ' > /dev/null 2>&1 &'  # redirect output to dev/null and run in daemon thread
-    print(cmd)
-    os.system(cmd)

ultralytics/yolov5/utils/aws/userdata.sh

@@ -1,27 +0,0 @@
-#!/bin/bash
-# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
-# This script will run only once on first instance start (for a re-start script see mime.sh)
-# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
-# Use >300 GB SSD
-
-cd home/ubuntu
-if [ ! -d yolov5 ]; then
-  echo "Running first-time script." # install dependencies, download COCO, pull Docker
-  git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5
-  cd yolov5
-  bash data/scripts/get_coco.sh && echo "COCO done." &
-  sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
-  python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
-  wait && echo "All tasks done." # finish background tasks
-else
-  echo "Running re-start script." # resume interrupted runs
-  i=0
-  list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
-  while IFS= read -r id; do
-    ((i++))
-    echo "restarting container $i: $id"
-    sudo docker start $id
-    # sudo docker exec -it $id python train.py --resume # single-GPU
-    sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
-  done <<<"$list"
-fi

ultralytics/yolov5/utils/benchmarks.py

@@ -1,104 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Run YOLOv5 benchmarks on all supported export formats
-
-Format                      | `export.py --include`         | Model
----                         | ---                           | ---
-PyTorch                     | -                             | yolov5s.pt
-TorchScript                 | `torchscript`                 | yolov5s.torchscript
-ONNX                        | `onnx`                        | yolov5s.onnx
-OpenVINO                    | `openvino`                    | yolov5s_openvino_model/
-TensorRT                    | `engine`                      | yolov5s.engine
-CoreML                      | `coreml`                      | yolov5s.mlmodel
-TensorFlow SavedModel       | `saved_model`                 | yolov5s_saved_model/
-TensorFlow GraphDef         | `pb`                          | yolov5s.pb
-TensorFlow Lite             | `tflite`                      | yolov5s.tflite
-TensorFlow Edge TPU         | `edgetpu`                     | yolov5s_edgetpu.tflite
-TensorFlow.js               | `tfjs`                        | yolov5s_web_model/
-
-Requirements:
-    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu  # CPU
-    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow  # GPU
-    $ pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com  # TensorRT
-
-Usage:
-    $ python utils/benchmarks.py --weights yolov5s.pt --img 640
-"""
-
-import argparse
-import sys
-import time
-from pathlib import Path
-
-import pandas as pd
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[1]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-# ROOT = ROOT.relative_to(Path.cwd())  # relative
-
-import export
-import val
-from utils import notebook_init
-from utils.general import LOGGER, print_args
-from utils.torch_utils import select_device
-
-
-def run(weights=ROOT / 'yolov5s.pt',  # weights path
-        imgsz=640,  # inference size (pixels)
-        batch_size=1,  # batch size
-        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
-        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
-        half=False,  # use FP16 half-precision inference
-        ):
-    y, t = [], time.time()
-    formats = export.export_formats()
-    device = select_device(device)
-    for i, (name, f, suffix, gpu) in formats.iterrows():  # index, (name, file, suffix, gpu-capable)
-        try:
-            if device.type != 'cpu':
-                assert gpu, f'{name} inference not supported on GPU'
-            if f == '-':
-                w = weights  # PyTorch format
-            else:
-                w = export.run(weights=weights, imgsz=[imgsz], include=[f], device=device, half=half)[-1]  # all others
-            assert suffix in str(w), 'export failed'
-            result = val.run(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
-            metrics = result[0]  # metrics (mp, mr, map50, map, *losses(box, obj, cls))
-            speeds = result[2]  # times (preprocess, inference, postprocess)
-            y.append([name, round(metrics[3], 4), round(speeds[1], 2)])  # mAP, t_inference
-        except Exception as e:
-            LOGGER.warning(f'WARNING: Benchmark failure for {name}: {e}')
-            y.append([name, None, None])  # mAP, t_inference
-
-    # Print results
-    LOGGER.info('\n')
-    parse_opt()
-    notebook_init()  # print system info
-    py = pd.DataFrame(y, columns=['Format', '[email protected]:0.95', 'Inference time (ms)'])
-    LOGGER.info(f'\nBenchmarks complete ({time.time() - t:.2f}s)')
-    LOGGER.info(str(py))
-    return py
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
-    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
-    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
-    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
-    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
-    opt = parser.parse_args()
-    print_args(FILE.stem, opt)
-    return opt
-
-
-def main(opt):
-    run(**vars(opt))
-
-
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)

ultralytics/yolov5/utils/callbacks.py

@@ -1,78 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Callback utils
-"""
-
-
-class Callbacks:
-    """"
-    Handles all registered callbacks for YOLOv5 Hooks
-    """
-
-    def __init__(self):
-        # Define the available callbacks
-        self._callbacks = {
-            'on_pretrain_routine_start': [],
-            'on_pretrain_routine_end': [],
-
-            'on_train_start': [],
-            'on_train_epoch_start': [],
-            'on_train_batch_start': [],
-            'optimizer_step': [],
-            'on_before_zero_grad': [],
-            'on_train_batch_end': [],
-            'on_train_epoch_end': [],
-
-            'on_val_start': [],
-            'on_val_batch_start': [],
-            'on_val_image_end': [],
-            'on_val_batch_end': [],
-            'on_val_end': [],
-
-            'on_fit_epoch_end': [],  # fit = train + val
-            'on_model_save': [],
-            'on_train_end': [],
-            'on_params_update': [],
-            'teardown': [],
-        }
-        self.stop_training = False  # set True to interrupt training
-
-    def register_action(self, hook, name='', callback=None):
-        """
-        Register a new action to a callback hook
-
-        Args:
-            hook        The callback hook name to register the action to
-            name        The name of the action for later reference
-            callback    The callback to fire
-        """
-        assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
-        assert callable(callback), f"callback '{callback}' is not callable"
-        self._callbacks[hook].append({'name': name, 'callback': callback})
-
-    def get_registered_actions(self, hook=None):
-        """"
-        Returns all the registered actions by callback hook
-
-        Args:
-            hook The name of the hook to check, defaults to all
-        """
-        if hook:
-            return self._callbacks[hook]
-        else:
-            return self._callbacks
-
-    def run(self, hook, *args, **kwargs):
-        """
-        Loop through the registered actions and fire all callbacks
-
-        Args:
-            hook The name of the hook to check, defaults to all
-            args Arguments to receive from YOLOv5
-            kwargs Keyword Arguments to receive from YOLOv5
-        """
-
-        assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
-
-        for logger in self._callbacks[hook]:
-            logger['callback'](*args, **kwargs)

ultralytics/yolov5/utils/datasets.py

@@ -1,1039 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Dataloaders and dataset utils
-"""
-
-import glob
-import hashlib
-import json
-import math
-import os
-import random
-import shutil
-import time
-from itertools import repeat
-from multiprocessing.pool import Pool, ThreadPool
-from pathlib import Path
-from threading import Thread
-from urllib.parse import urlparse
-from zipfile import ZipFile
-
-import cv2
-import numpy as np
-import torch
-import torch.nn.functional as F
-import yaml
-from PIL import ExifTags, Image, ImageOps
-from torch.utils.data import DataLoader, Dataset, dataloader, distributed
-from tqdm import tqdm
-
-from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective
-from utils.general import (DATASETS_DIR, LOGGER, NUM_THREADS, check_dataset, check_requirements, check_yaml, clean_str,
-                           segments2boxes, xyn2xy, xywh2xyxy, xywhn2xyxy, xyxy2xywhn)
-from utils.torch_utils import torch_distributed_zero_first
-
-# Parameters
-HELP_URL = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
-IMG_FORMATS = 'bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp'  # include image suffixes
-VID_FORMATS = 'asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'ts', 'wmv'  # include video suffixes
-BAR_FORMAT = '{l_bar}{bar:10}{r_bar}{bar:-10b}'  # tqdm bar format
-
-# Get orientation exif tag
-for orientation in ExifTags.TAGS.keys():
-    if ExifTags.TAGS[orientation] == 'Orientation':
-        break
-
-
-def get_hash(paths):
-    # Returns a single hash value of a list of paths (files or dirs)
-    size = sum(os.path.getsize(p) for p in paths if os.path.exists(p))  # sizes
-    h = hashlib.md5(str(size).encode())  # hash sizes
-    h.update(''.join(paths).encode())  # hash paths
-    return h.hexdigest()  # return hash
-
-
-def exif_size(img):
-    # Returns exif-corrected PIL size
-    s = img.size  # (width, height)
-    try:
-        rotation = dict(img._getexif().items())[orientation]
-        if rotation == 6:  # rotation 270
-            s = (s[1], s[0])
-        elif rotation == 8:  # rotation 90
-            s = (s[1], s[0])
-    except Exception:
-        pass
-
-    return s
-
-
-def exif_transpose(image):
-    """
-    Transpose a PIL image accordingly if it has an EXIF Orientation tag.
-    Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose()
-
-    :param image: The image to transpose.
-    :return: An image.
-    """
-    exif = image.getexif()
-    orientation = exif.get(0x0112, 1)  # default 1
-    if orientation > 1:
-        method = {2: Image.FLIP_LEFT_RIGHT,
-                  3: Image.ROTATE_180,
-                  4: Image.FLIP_TOP_BOTTOM,
-                  5: Image.TRANSPOSE,
-                  6: Image.ROTATE_270,
-                  7: Image.TRANSVERSE,
-                  8: Image.ROTATE_90,
-                  }.get(orientation)
-        if method is not None:
-            image = image.transpose(method)
-            del exif[0x0112]
-            image.info["exif"] = exif.tobytes()
-    return image
-
-
-def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0,
-                      rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix='', shuffle=False):
-    if rect and shuffle:
-        LOGGER.warning('WARNING: --rect is incompatible with DataLoader shuffle, setting shuffle=False')
-        shuffle = False
-    with torch_distributed_zero_first(rank):  # init dataset *.cache only once if DDP
-        dataset = LoadImagesAndLabels(path, imgsz, batch_size,
-                                      augment=augment,  # augmentation
-                                      hyp=hyp,  # hyperparameters
-                                      rect=rect,  # rectangular batches
-                                      cache_images=cache,
-                                      single_cls=single_cls,
-                                      stride=int(stride),
-                                      pad=pad,
-                                      image_weights=image_weights,
-                                      prefix=prefix)
-
-    batch_size = min(batch_size, len(dataset))
-    nd = torch.cuda.device_count()  # number of CUDA devices
-    nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers])  # number of workers
-    sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
-    loader = DataLoader if image_weights else InfiniteDataLoader  # only DataLoader allows for attribute updates
-    return loader(dataset,
-                  batch_size=batch_size,
-                  shuffle=shuffle and sampler is None,
-                  num_workers=nw,
-                  sampler=sampler,
-                  pin_memory=True,
-                  collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn), dataset
-
-
-class InfiniteDataLoader(dataloader.DataLoader):
-    """ Dataloader that reuses workers
-
-    Uses same syntax as vanilla DataLoader
-    """
-
-    def __init__(self, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
-        self.iterator = super().__iter__()
-
-    def __len__(self):
-        return len(self.batch_sampler.sampler)
-
-    def __iter__(self):
-        for i in range(len(self)):
-            yield next(self.iterator)
-
-
-class _RepeatSampler:
-    """ Sampler that repeats forever
-
-    Args:
-        sampler (Sampler)
-    """
-
-    def __init__(self, sampler):
-        self.sampler = sampler
-
-    def __iter__(self):
-        while True:
-            yield from iter(self.sampler)
-
-
-class LoadImages:
-    # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
-    def __init__(self, path, img_size=640, stride=32, auto=True):
-        p = str(Path(path).resolve())  # os-agnostic absolute path
-        if '*' in p:
-            files = sorted(glob.glob(p, recursive=True))  # glob
-        elif os.path.isdir(p):
-            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
-        elif os.path.isfile(p):
-            files = [p]  # files
-        else:
-            raise Exception(f'ERROR: {p} does not exist')
-
-        images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
-        videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
-        ni, nv = len(images), len(videos)
-
-        self.img_size = img_size
-        self.stride = stride
-        self.files = images + videos
-        self.nf = ni + nv  # number of files
-        self.video_flag = [False] * ni + [True] * nv
-        self.mode = 'image'
-        self.auto = auto
-        if any(videos):
-            self.new_video(videos[0])  # new video
-        else:
-            self.cap = None
-        assert self.nf > 0, f'No images or videos found in {p}. ' \
-                            f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'
-
-    def __iter__(self):
-        self.count = 0
-        return self
-
-    def __next__(self):
-        if self.count == self.nf:
-            raise StopIteration
-        path = self.files[self.count]
-
-        if self.video_flag[self.count]:
-            # Read video
-            self.mode = 'video'
-            ret_val, img0 = self.cap.read()
-            while not ret_val:
-                self.count += 1
-                self.cap.release()
-                if self.count == self.nf:  # last video
-                    raise StopIteration
-                else:
-                    path = self.files[self.count]
-                    self.new_video(path)
-                    ret_val, img0 = self.cap.read()
-
-            self.frame += 1
-            s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
-
-        else:
-            # Read image
-            self.count += 1
-            img0 = cv2.imread(path)  # BGR
-            assert img0 is not None, f'Image Not Found {path}'
-            s = f'image {self.count}/{self.nf} {path}: '
-
-        # Padded resize
-        img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]
-
-        # Convert
-        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
-        img = np.ascontiguousarray(img)
-
-        return path, img, img0, self.cap, s
-
-    def new_video(self, path):
-        self.frame = 0
-        self.cap = cv2.VideoCapture(path)
-        self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))
-
-    def __len__(self):
-        return self.nf  # number of files
-
-
-class LoadWebcam:  # for inference
-    # YOLOv5 local webcam dataloader, i.e. `python detect.py --source 0`
-    def __init__(self, pipe='0', img_size=640, stride=32):
-        self.img_size = img_size
-        self.stride = stride
-        self.pipe = eval(pipe) if pipe.isnumeric() else pipe
-        self.cap = cv2.VideoCapture(self.pipe)  # video capture object
-        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size
-
-    def __iter__(self):
-        self.count = -1
-        return self
-
-    def __next__(self):
-        self.count += 1
-        if cv2.waitKey(1) == ord('q'):  # q to quit
-            self.cap.release()
-            cv2.destroyAllWindows()
-            raise StopIteration
-
-        # Read frame
-        ret_val, img0 = self.cap.read()
-        img0 = cv2.flip(img0, 1)  # flip left-right
-
-        # Print
-        assert ret_val, f'Camera Error {self.pipe}'
-        img_path = 'webcam.jpg'
-        s = f'webcam {self.count}: '
-
-        # Padded resize
-        img = letterbox(img0, self.img_size, stride=self.stride)[0]
-
-        # Convert
-        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
-        img = np.ascontiguousarray(img)
-
-        return img_path, img, img0, None, s
-
-    def __len__(self):
-        return 0
-
-
-class LoadStreams:
-    # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streams`
-    def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
-        self.mode = 'stream'
-        self.img_size = img_size
-        self.stride = stride
-
-        if os.path.isfile(sources):
-            with open(sources) as f:
-                sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
-        else:
-            sources = [sources]
-
-        n = len(sources)
-        self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
-        self.sources = [clean_str(x) for x in sources]  # clean source names for later
-        self.auto = auto
-        for i, s in enumerate(sources):  # index, source
-            # Start thread to read frames from video stream
-            st = f'{i + 1}/{n}: {s}... '
-            if urlparse(s).hostname in ('youtube.com', 'youtu.be'):  # if source is YouTube video
-                check_requirements(('pafy', 'youtube_dl==2020.12.2'))
-                import pafy
-                s = pafy.new(s).getbest(preftype="mp4").url  # YouTube URL
-            s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
-            cap = cv2.VideoCapture(s)
-            assert cap.isOpened(), f'{st}Failed to open {s}'
-            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-            fps = cap.get(cv2.CAP_PROP_FPS)  # warning: may return 0 or nan
-            self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf')  # infinite stream fallback
-            self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30  # 30 FPS fallback
-
-            _, self.imgs[i] = cap.read()  # guarantee first frame
-            self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
-            LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
-            self.threads[i].start()
-        LOGGER.info('')  # newline
-
-        # check for common shapes
-        s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
-        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
-        if not self.rect:
-            LOGGER.warning('WARNING: Stream shapes differ. For optimal performance supply similarly-shaped streams.')
-
-    def update(self, i, cap, stream):
-        # Read stream `i` frames in daemon thread
-        n, f, read = 0, self.frames[i], 1  # frame number, frame array, inference every 'read' frame
-        while cap.isOpened() and n < f:
-            n += 1
-            # _, self.imgs[index] = cap.read()
-            cap.grab()
-            if n % read == 0:
-                success, im = cap.retrieve()
-                if success:
-                    self.imgs[i] = im
-                else:
-                    LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.')
-                    self.imgs[i] = np.zeros_like(self.imgs[i])
-                    cap.open(stream)  # re-open stream if signal was lost
-            time.sleep(1 / self.fps[i])  # wait time
-
-    def __iter__(self):
-        self.count = -1
-        return self
-
-    def __next__(self):
-        self.count += 1
-        if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'):  # q to quit
-            cv2.destroyAllWindows()
-            raise StopIteration
-
-        # Letterbox
-        img0 = self.imgs.copy()
-        img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]
-
-        # Stack
-        img = np.stack(img, 0)
-
-        # Convert
-        img = img[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW
-        img = np.ascontiguousarray(img)
-
-        return self.sources, img, img0, None, ''
-
-    def __len__(self):
-        return len(self.sources)  # 1E12 frames = 32 streams at 30 FPS for 30 years
-
-
-def img2label_paths(img_paths):
-    # Define label paths as a function of image paths
-    sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep  # /images/, /labels/ substrings
-    return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
-
-
-class LoadImagesAndLabels(Dataset):
-    # YOLOv5 train_loader/val_loader, loads images and labels for training and validation
-    cache_version = 0.6  # dataset labels *.cache version
-
-    def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
-                 cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
-        self.img_size = img_size
-        self.augment = augment
-        self.hyp = hyp
-        self.image_weights = image_weights
-        self.rect = False if image_weights else rect
-        self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
-        self.mosaic_border = [-img_size // 2, -img_size // 2]
-        self.stride = stride
-        self.path = path
-        self.albumentations = Albumentations() if augment else None
-
-        try:
-            f = []  # image files
-            for p in path if isinstance(path, list) else [path]:
-                p = Path(p)  # os-agnostic
-                if p.is_dir():  # dir
-                    f += glob.glob(str(p / '**' / '*.*'), recursive=True)
-                    # f = list(p.rglob('*.*'))  # pathlib
-                elif p.is_file():  # file
-                    with open(p) as t:
-                        t = t.read().strip().splitlines()
-                        parent = str(p.parent) + os.sep
-                        f += [x.replace('./', parent) if x.startswith('./') else x for x in t]  # local to global path
-                        # f += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
-                else:
-                    raise Exception(f'{prefix}{p} does not exist')
-            self.im_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
-            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS])  # pathlib
-            assert self.im_files, f'{prefix}No images found'
-        except Exception as e:
-            raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
-
-        # Check cache
-        self.label_files = img2label_paths(self.im_files)  # labels
-        cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
-        try:
-            cache, exists = np.load(cache_path, allow_pickle=True).item(), True  # load dict
-            assert cache['version'] == self.cache_version  # same version
-            assert cache['hash'] == get_hash(self.label_files + self.im_files)  # same hash
-        except Exception:
-            cache, exists = self.cache_labels(cache_path, prefix), False  # cache
-
-        # Display cache
-        nf, nm, ne, nc, n = cache.pop('results')  # found, missing, empty, corrupt, total
-        if exists:
-            d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupt"
-            tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=BAR_FORMAT)  # display cache results
-            if cache['msgs']:
-                LOGGER.info('\n'.join(cache['msgs']))  # display warnings
-        assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
-
-        # Read cache
-        [cache.pop(k) for k in ('hash', 'version', 'msgs')]  # remove items
-        labels, shapes, self.segments = zip(*cache.values())
-        self.labels = list(labels)
-        self.shapes = np.array(shapes, dtype=np.float64)
-        self.im_files = list(cache.keys())  # update
-        self.label_files = img2label_paths(cache.keys())  # update
-        n = len(shapes)  # number of images
-        bi = np.floor(np.arange(n) / batch_size).astype(np.int)  # batch index
-        nb = bi[-1] + 1  # number of batches
-        self.batch = bi  # batch index of image
-        self.n = n
-        self.indices = range(n)
-
-        # Update labels
-        include_class = []  # filter labels to include only these classes (optional)
-        include_class_array = np.array(include_class).reshape(1, -1)
-        for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
-            if include_class:
-                j = (label[:, 0:1] == include_class_array).any(1)
-                self.labels[i] = label[j]
-                if segment:
-                    self.segments[i] = segment[j]
-            if single_cls:  # single-class training, merge all classes into 0
-                self.labels[i][:, 0] = 0
-                if segment:
-                    self.segments[i][:, 0] = 0
-
-        # Rectangular Training
-        if self.rect:
-            # Sort by aspect ratio
-            s = self.shapes  # wh
-            ar = s[:, 1] / s[:, 0]  # aspect ratio
-            irect = ar.argsort()
-            self.im_files = [self.im_files[i] for i in irect]
-            self.label_files = [self.label_files[i] for i in irect]
-            self.labels = [self.labels[i] for i in irect]
-            self.shapes = s[irect]  # wh
-            ar = ar[irect]
-
-            # Set training image shapes
-            shapes = [[1, 1]] * nb
-            for i in range(nb):
-                ari = ar[bi == i]
-                mini, maxi = ari.min(), ari.max()
-                if maxi < 1:
-                    shapes[i] = [maxi, 1]
-                elif mini > 1:
-                    shapes[i] = [1, 1 / mini]
-
-            self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride
-
-        # Cache images into RAM/disk for faster training (WARNING: large datasets may exceed system resources)
-        self.ims = [None] * n
-        self.npy_files = [Path(f).with_suffix('.npy') for f in self.im_files]
-        if cache_images:
-            gb = 0  # Gigabytes of cached images
-            self.im_hw0, self.im_hw = [None] * n, [None] * n
-            fcn = self.cache_images_to_disk if cache_images == 'disk' else self.load_image
-            results = ThreadPool(NUM_THREADS).imap(fcn, range(n))
-            pbar = tqdm(enumerate(results), total=n, bar_format=BAR_FORMAT)
-            for i, x in pbar:
-                if cache_images == 'disk':
-                    gb += self.npy_files[i].stat().st_size
-                else:  # 'ram'
-                    self.ims[i], self.im_hw0[i], self.im_hw[i] = x  # im, hw_orig, hw_resized = load_image(self, i)
-                    gb += self.ims[i].nbytes
-                pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
-            pbar.close()
-
-    def cache_labels(self, path=Path('./labels.cache'), prefix=''):
-        # Cache dataset labels, check images and read shapes
-        x = {}  # dict
-        nm, nf, ne, nc, msgs = 0, 0, 0, 0, []  # number missing, found, empty, corrupt, messages
-        desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..."
-        with Pool(NUM_THREADS) as pool:
-            pbar = tqdm(pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix))),
-                        desc=desc, total=len(self.im_files), bar_format=BAR_FORMAT)
-            for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
-                nm += nm_f
-                nf += nf_f
-                ne += ne_f
-                nc += nc_f
-                if im_file:
-                    x[im_file] = [lb, shape, segments]
-                if msg:
-                    msgs.append(msg)
-                pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupt"
-
-        pbar.close()
-        if msgs:
-            LOGGER.info('\n'.join(msgs))
-        if nf == 0:
-            LOGGER.warning(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
-        x['hash'] = get_hash(self.label_files + self.im_files)
-        x['results'] = nf, nm, ne, nc, len(self.im_files)
-        x['msgs'] = msgs  # warnings
-        x['version'] = self.cache_version  # cache version
-        try:
-            np.save(path, x)  # save cache for next time
-            path.with_suffix('.cache.npy').rename(path)  # remove .npy suffix
-            LOGGER.info(f'{prefix}New cache created: {path}')
-        except Exception as e:
-            LOGGER.warning(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}')  # not writeable
-        return x
-
-    def __len__(self):
-        return len(self.im_files)
-
-    # def __iter__(self):
-    #     self.count = -1
-    #     print('ran dataset iter')
-    #     #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
-    #     return self
-
-    def __getitem__(self, index):
-        index = self.indices[index]  # linear, shuffled, or image_weights
-
-        hyp = self.hyp
-        mosaic = self.mosaic and random.random() < hyp['mosaic']
-        if mosaic:
-            # Load mosaic
-            img, labels = self.load_mosaic(index)
-            shapes = None
-
-            # MixUp augmentation
-            if random.random() < hyp['mixup']:
-                img, labels = mixup(img, labels, *self.load_mosaic(random.randint(0, self.n - 1)))
-
-        else:
-            # Load image
-            img, (h0, w0), (h, w) = self.load_image(index)
-
-            # Letterbox
-            shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size  # final letterboxed shape
-            img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
-            shapes = (h0, w0), ((h / h0, w / w0), pad)  # for COCO mAP rescaling
-
-            labels = self.labels[index].copy()
-            if labels.size:  # normalized xywh to pixel xyxy format
-                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
-
-            if self.augment:
-                img, labels = random_perspective(img, labels,
-                                                 degrees=hyp['degrees'],
-                                                 translate=hyp['translate'],
-                                                 scale=hyp['scale'],
-                                                 shear=hyp['shear'],
-                                                 perspective=hyp['perspective'])
-
-        nl = len(labels)  # number of labels
-        if nl:
-            labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)
-
-        if self.augment:
-            # Albumentations
-            img, labels = self.albumentations(img, labels)
-            nl = len(labels)  # update after albumentations
-
-            # HSV color-space
-            augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
-
-            # Flip up-down
-            if random.random() < hyp['flipud']:
-                img = np.flipud(img)
-                if nl:
-                    labels[:, 2] = 1 - labels[:, 2]
-
-            # Flip left-right
-            if random.random() < hyp['fliplr']:
-                img = np.fliplr(img)
-                if nl:
-                    labels[:, 1] = 1 - labels[:, 1]
-
-            # Cutouts
-            # labels = cutout(img, labels, p=0.5)
-            # nl = len(labels)  # update after cutout
-
-        labels_out = torch.zeros((nl, 6))
-        if nl:
-            labels_out[:, 1:] = torch.from_numpy(labels)
-
-        # Convert
-        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
-        img = np.ascontiguousarray(img)
-
-        return torch.from_numpy(img), labels_out, self.im_files[index], shapes
-
-    def load_image(self, i):
-        # Loads 1 image from dataset index 'i', returns (im, original hw, resized hw)
-        im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i],
-        if im is None:  # not cached in RAM
-            if fn.exists():  # load npy
-                im = np.load(fn)
-            else:  # read image
-                im = cv2.imread(f)  # BGR
-                assert im is not None, f'Image Not Found {f}'
-            h0, w0 = im.shape[:2]  # orig hw
-            r = self.img_size / max(h0, w0)  # ratio
-            if r != 1:  # if sizes are not equal
-                im = cv2.resize(im,
-                                (int(w0 * r), int(h0 * r)),
-                                interpolation=cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA)
-            return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
-        else:
-            return self.ims[i], self.im_hw0[i], self.im_hw[i]  # im, hw_original, hw_resized
-
-    def cache_images_to_disk(self, i):
-        # Saves an image as an *.npy file for faster loading
-        f = self.npy_files[i]
-        if not f.exists():
-            np.save(f.as_posix(), cv2.imread(self.im_files[i]))
-
-    def load_mosaic(self, index):
-        # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
-        labels4, segments4 = [], []
-        s = self.img_size
-        yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border)  # mosaic center x, y
-        indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
-        random.shuffle(indices)
-        for i, index in enumerate(indices):
-            # Load image
-            img, _, (h, w) = self.load_image(index)
-
-            # place img in img4
-            if i == 0:  # top left
-                img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
-                x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
-                x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
-            elif i == 1:  # top right
-                x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
-                x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
-            elif i == 2:  # bottom left
-                x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
-                x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
-            elif i == 3:  # bottom right
-                x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
-                x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
-
-            img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
-            padw = x1a - x1b
-            padh = y1a - y1b
-
-            # Labels
-            labels, segments = self.labels[index].copy(), self.segments[index].copy()
-            if labels.size:
-                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
-                segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
-            labels4.append(labels)
-            segments4.extend(segments)
-
-        # Concat/clip labels
-        labels4 = np.concatenate(labels4, 0)
-        for x in (labels4[:, 1:], *segments4):
-            np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
-        # img4, labels4 = replicate(img4, labels4)  # replicate
-
-        # Augment
-        img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
-        img4, labels4 = random_perspective(img4, labels4, segments4,
-                                           degrees=self.hyp['degrees'],
-                                           translate=self.hyp['translate'],
-                                           scale=self.hyp['scale'],
-                                           shear=self.hyp['shear'],
-                                           perspective=self.hyp['perspective'],
-                                           border=self.mosaic_border)  # border to remove
-
-        return img4, labels4
-
-    def load_mosaic9(self, index):
-        # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
-        labels9, segments9 = [], []
-        s = self.img_size
-        indices = [index] + random.choices(self.indices, k=8)  # 8 additional image indices
-        random.shuffle(indices)
-        hp, wp = -1, -1  # height, width previous
-        for i, index in enumerate(indices):
-            # Load image
-            img, _, (h, w) = self.load_image(index)
-
-            # place img in img9
-            if i == 0:  # center
-                img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
-                h0, w0 = h, w
-                c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
-            elif i == 1:  # top
-                c = s, s - h, s + w, s
-            elif i == 2:  # top right
-                c = s + wp, s - h, s + wp + w, s
-            elif i == 3:  # right
-                c = s + w0, s, s + w0 + w, s + h
-            elif i == 4:  # bottom right
-                c = s + w0, s + hp, s + w0 + w, s + hp + h
-            elif i == 5:  # bottom
-                c = s + w0 - w, s + h0, s + w0, s + h0 + h
-            elif i == 6:  # bottom left
-                c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
-            elif i == 7:  # left
-                c = s - w, s + h0 - h, s, s + h0
-            elif i == 8:  # top left
-                c = s - w, s + h0 - hp - h, s, s + h0 - hp
-
-            padx, pady = c[:2]
-            x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords
-
-            # Labels
-            labels, segments = self.labels[index].copy(), self.segments[index].copy()
-            if labels.size:
-                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady)  # normalized xywh to pixel xyxy format
-                segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
-            labels9.append(labels)
-            segments9.extend(segments)
-
-            # Image
-            img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:]  # img9[ymin:ymax, xmin:xmax]
-            hp, wp = h, w  # height, width previous
-
-        # Offset
-        yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border)  # mosaic center x, y
-        img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
-
-        # Concat/clip labels
-        labels9 = np.concatenate(labels9, 0)
-        labels9[:, [1, 3]] -= xc
-        labels9[:, [2, 4]] -= yc
-        c = np.array([xc, yc])  # centers
-        segments9 = [x - c for x in segments9]
-
-        for x in (labels9[:, 1:], *segments9):
-            np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
-        # img9, labels9 = replicate(img9, labels9)  # replicate
-
-        # Augment
-        img9, labels9 = random_perspective(img9, labels9, segments9,
-                                           degrees=self.hyp['degrees'],
-                                           translate=self.hyp['translate'],
-                                           scale=self.hyp['scale'],
-                                           shear=self.hyp['shear'],
-                                           perspective=self.hyp['perspective'],
-                                           border=self.mosaic_border)  # border to remove
-
-        return img9, labels9
-
-    @staticmethod
-    def collate_fn(batch):
-        im, label, path, shapes = zip(*batch)  # transposed
-        for i, lb in enumerate(label):
-            lb[:, 0] = i  # add target image index for build_targets()
-        return torch.stack(im, 0), torch.cat(label, 0), path, shapes
-
-    @staticmethod
-    def collate_fn4(batch):
-        img, label, path, shapes = zip(*batch)  # transposed
-        n = len(shapes) // 4
-        im4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
-
-        ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]])
-        wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]])
-        s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]])  # scale
-        for i in range(n):  # zidane torch.zeros(16,3,720,1280)  # BCHW
-            i *= 4
-            if random.random() < 0.5:
-                im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear', align_corners=False)[
-                    0].type(img[i].type())
-                lb = label[i]
-            else:
-                im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
-                lb = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
-            im4.append(im)
-            label4.append(lb)
-
-        for i, lb in enumerate(label4):
-            lb[:, 0] = i  # add target image index for build_targets()
-
-        return torch.stack(im4, 0), torch.cat(label4, 0), path4, shapes4
-
-
-# Ancillary functions --------------------------------------------------------------------------------------------------
-def create_folder(path='./new'):
-    # Create folder
-    if os.path.exists(path):
-        shutil.rmtree(path)  # delete output folder
-    os.makedirs(path)  # make new output folder
-
-
-def flatten_recursive(path=DATASETS_DIR / 'coco128'):
-    # Flatten a recursive directory by bringing all files to top level
-    new_path = Path(str(path) + '_flat')
-    create_folder(new_path)
-    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
-        shutil.copyfile(file, new_path / Path(file).name)
-
-
-def extract_boxes(path=DATASETS_DIR / 'coco128'):  # from utils.datasets import *; extract_boxes()
-    # Convert detection dataset into classification dataset, with one directory per class
-    path = Path(path)  # images dir
-    shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None  # remove existing
-    files = list(path.rglob('*.*'))
-    n = len(files)  # number of files
-    for im_file in tqdm(files, total=n):
-        if im_file.suffix[1:] in IMG_FORMATS:
-            # image
-            im = cv2.imread(str(im_file))[..., ::-1]  # BGR to RGB
-            h, w = im.shape[:2]
-
-            # labels
-            lb_file = Path(img2label_paths([str(im_file)])[0])
-            if Path(lb_file).exists():
-                with open(lb_file) as f:
-                    lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels
-
-                for j, x in enumerate(lb):
-                    c = int(x[0])  # class
-                    f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg'  # new filename
-                    if not f.parent.is_dir():
-                        f.parent.mkdir(parents=True)
-
-                    b = x[1:] * [w, h, w, h]  # box
-                    # b[2:] = b[2:].max()  # rectangle to square
-                    b[2:] = b[2:] * 1.2 + 3  # pad
-                    b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
-
-                    b[[0, 2]] = np.clip(b[[0, 2]], 0, w)  # clip boxes outside of image
-                    b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
-                    assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
-
-
-def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
-    """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
-    Usage: from utils.datasets import *; autosplit()
-    Arguments
-        path:            Path to images directory
-        weights:         Train, val, test weights (list, tuple)
-        annotated_only:  Only use images with an annotated txt file
-    """
-    path = Path(path)  # images dir
-    files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS)  # image files only
-    n = len(files)  # number of files
-    random.seed(0)  # for reproducibility
-    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
-
-    txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt']  # 3 txt files
-    [(path.parent / x).unlink(missing_ok=True) for x in txt]  # remove existing
-
-    print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
-    for i, img in tqdm(zip(indices, files), total=n):
-        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
-            with open(path.parent / txt[i], 'a') as f:
-                f.write('./' + img.relative_to(path.parent).as_posix() + '\n')  # add image to txt file
-
-
-def verify_image_label(args):
-    # Verify one image-label pair
-    im_file, lb_file, prefix = args
-    nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', []  # number (missing, found, empty, corrupt), message, segments
-    try:
-        # verify images
-        im = Image.open(im_file)
-        im.verify()  # PIL verify
-        shape = exif_size(im)  # image size
-        assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
-        assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}'
-        if im.format.lower() in ('jpg', 'jpeg'):
-            with open(im_file, 'rb') as f:
-                f.seek(-2, 2)
-                if f.read() != b'\xff\xd9':  # corrupt JPEG
-                    ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100)
-                    msg = f'{prefix}WARNING: {im_file}: corrupt JPEG restored and saved'
-
-        # verify labels
-        if os.path.isfile(lb_file):
-            nf = 1  # label found
-            with open(lb_file) as f:
-                lb = [x.split() for x in f.read().strip().splitlines() if len(x)]
-                if any(len(x) > 6 for x in lb):  # is segment
-                    classes = np.array([x[0] for x in lb], dtype=np.float32)
-                    segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb]  # (cls, xy1...)
-                    lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1)  # (cls, xywh)
-                lb = np.array(lb, dtype=np.float32)
-            nl = len(lb)
-            if nl:
-                assert lb.shape[1] == 5, f'labels require 5 columns, {lb.shape[1]} columns detected'
-                assert (lb >= 0).all(), f'negative label values {lb[lb < 0]}'
-                assert (lb[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {lb[:, 1:][lb[:, 1:] > 1]}'
-                _, i = np.unique(lb, axis=0, return_index=True)
-                if len(i) < nl:  # duplicate row check
-                    lb = lb[i]  # remove duplicates
-                    if segments:
-                        segments = segments[i]
-                    msg = f'{prefix}WARNING: {im_file}: {nl - len(i)} duplicate labels removed'
-            else:
-                ne = 1  # label empty
-                lb = np.zeros((0, 5), dtype=np.float32)
-        else:
-            nm = 1  # label missing
-            lb = np.zeros((0, 5), dtype=np.float32)
-        return im_file, lb, shape, segments, nm, nf, ne, nc, msg
-    except Exception as e:
-        nc = 1
-        msg = f'{prefix}WARNING: {im_file}: ignoring corrupt image/label: {e}'
-        return [None, None, None, None, nm, nf, ne, nc, msg]
-
-
-def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False):
-    """ Return dataset statistics dictionary with images and instances counts per split per class
-    To run in parent directory: export PYTHONPATH="$PWD/yolov5"
-    Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True)
-    Usage2: from utils.datasets import *; dataset_stats('path/to/coco128_with_yaml.zip')
-    Arguments
-        path:           Path to data.yaml or data.zip (with data.yaml inside data.zip)
-        autodownload:   Attempt to download dataset if not found locally
-        verbose:        Print stats dictionary
-    """
-
-    def round_labels(labels):
-        # Update labels to integer class and 6 decimal place floats
-        return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels]
-
-    def unzip(path):
-        # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
-        if str(path).endswith('.zip'):  # path is data.zip
-            assert Path(path).is_file(), f'Error unzipping {path}, file not found'
-            ZipFile(path).extractall(path=path.parent)  # unzip
-            dir = path.with_suffix('')  # dataset directory == zip name
-            return True, str(dir), next(dir.rglob('*.yaml'))  # zipped, data_dir, yaml_path
-        else:  # path is data.yaml
-            return False, None, path
-
-    def hub_ops(f, max_dim=1920):
-        # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing
-        f_new = im_dir / Path(f).name  # dataset-hub image filename
-        try:  # use PIL
-            im = Image.open(f)
-            r = max_dim / max(im.height, im.width)  # ratio
-            if r < 1.0:  # image too large
-                im = im.resize((int(im.width * r), int(im.height * r)))
-            im.save(f_new, 'JPEG', quality=75, optimize=True)  # save
-        except Exception as e:  # use OpenCV
-            print(f'WARNING: HUB ops PIL failure {f}: {e}')
-            im = cv2.imread(f)
-            im_height, im_width = im.shape[:2]
-            r = max_dim / max(im_height, im_width)  # ratio
-            if r < 1.0:  # image too large
-                im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA)
-            cv2.imwrite(str(f_new), im)
-
-    zipped, data_dir, yaml_path = unzip(Path(path))
-    with open(check_yaml(yaml_path), errors='ignore') as f:
-        data = yaml.safe_load(f)  # data dict
-        if zipped:
-            data['path'] = data_dir  # TODO: should this be dir.resolve()?
-    check_dataset(data, autodownload)  # download dataset if missing
-    hub_dir = Path(data['path'] + ('-hub' if hub else ''))
-    stats = {'nc': data['nc'], 'names': data['names']}  # statistics dictionary
-    for split in 'train', 'val', 'test':
-        if data.get(split) is None:
-            stats[split] = None  # i.e. no test set
-            continue
-        x = []
-        dataset = LoadImagesAndLabels(data[split])  # load dataset
-        for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'):
-            x.append(np.bincount(label[:, 0].astype(int), minlength=data['nc']))
-        x = np.array(x)  # shape(128x80)
-        stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
-                        'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
-                                        'per_class': (x > 0).sum(0).tolist()},
-                        'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
-                                   zip(dataset.im_files, dataset.labels)]}
-
-        if hub:
-            im_dir = hub_dir / 'images'
-            im_dir.mkdir(parents=True, exist_ok=True)
-            for _ in tqdm(ThreadPool(NUM_THREADS).imap(hub_ops, dataset.im_files), total=dataset.n, desc='HUB Ops'):
-                pass
-
-    # Profile
-    stats_path = hub_dir / 'stats.json'
-    if profile:
-        for _ in range(1):
-            file = stats_path.with_suffix('.npy')
-            t1 = time.time()
-            np.save(file, stats)
-            t2 = time.time()
-            x = np.load(file, allow_pickle=True)
-            print(f'stats.npy times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
-
-            file = stats_path.with_suffix('.json')
-            t1 = time.time()
-            with open(file, 'w') as f:
-                json.dump(stats, f)  # save stats *.json
-            t2 = time.time()
-            with open(file) as f:
-                x = json.load(f)  # load hyps dict
-            print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
-
-    # Save, print and return
-    if hub:
-        print(f'Saving {stats_path.resolve()}...')
-        with open(stats_path, 'w') as f:
-            json.dump(stats, f)  # save stats.json
-    if verbose:
-        print(json.dumps(stats, indent=2, sort_keys=False))
-    return stats

ultralytics/yolov5/utils/downloads.py

@@ -1,153 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Download utils
-"""
-
-import os
-import platform
-import subprocess
-import time
-import urllib
-from pathlib import Path
-from zipfile import ZipFile
-
-import requests
-import torch
-
-
-def gsutil_getsize(url=''):
-    # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
-    s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
-    return eval(s.split(' ')[0]) if len(s) else 0  # bytes
-
-
-def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
-    # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
-    file = Path(file)
-    assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}"
-    try:  # url1
-        print(f'Downloading {url} to {file}...')
-        torch.hub.download_url_to_file(url, str(file))
-        assert file.exists() and file.stat().st_size > min_bytes, assert_msg  # check
-    except Exception as e:  # url2
-        file.unlink(missing_ok=True)  # remove partial downloads
-        print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...')
-        os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -")  # curl download, retry and resume on fail
-    finally:
-        if not file.exists() or file.stat().st_size < min_bytes:  # check
-            file.unlink(missing_ok=True)  # remove partial downloads
-            print(f"ERROR: {assert_msg}\n{error_msg}")
-        print('')
-
-
-def attempt_download(file, repo='ultralytics/yolov5'):  # from utils.downloads import *; attempt_download()
-    # Attempt file download if does not exist
-    file = Path(str(file).strip().replace("'", ''))
-
-    if not file.exists():
-        # URL specified
-        name = Path(urllib.parse.unquote(str(file))).name  # decode '%2F' to '/' etc.
-        if str(file).startswith(('http:/', 'https:/')):  # download
-            url = str(file).replace(':/', '://')  # Pathlib turns :// -> :/
-            file = name.split('?')[0]  # parse authentication https://url.com/file.txt?auth...
-            if Path(file).is_file():
-                print(f'Found {url} locally at {file}')  # file already exists
-            else:
-                safe_download(file=file, url=url, min_bytes=1E5)
-            return file
-
-        # GitHub assets
-        file.parent.mkdir(parents=True, exist_ok=True)  # make parent dir (if required)
-        try:
-            response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json()  # github api
-            assets = [x['name'] for x in response['assets']]  # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
-            tag = response['tag_name']  # i.e. 'v1.0'
-        except Exception:  # fallback plan
-            assets = ['yolov5n.pt', 'yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
-                      'yolov5n6.pt', 'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
-            try:
-                tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
-            except Exception:
-                tag = 'v6.0'  # current release
-
-        if name in assets:
-            safe_download(file,
-                          url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
-                          # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}',  # backup url (optional)
-                          min_bytes=1E5,
-                          error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/')
-
-    return str(file)
-
-
-def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
-    # Downloads a file from Google Drive. from yolov5.utils.downloads import *; gdrive_download()
-    t = time.time()
-    file = Path(file)
-    cookie = Path('cookie')  # gdrive cookie
-    print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
-    file.unlink(missing_ok=True)  # remove existing file
-    cookie.unlink(missing_ok=True)  # remove existing cookie
-
-    # Attempt file download
-    out = "NUL" if platform.system() == "Windows" else "/dev/null"
-    os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
-    if os.path.exists('cookie'):  # large file
-        s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
-    else:  # small file
-        s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
-    r = os.system(s)  # execute, capture return
-    cookie.unlink(missing_ok=True)  # remove existing cookie
-
-    # Error check
-    if r != 0:
-        file.unlink(missing_ok=True)  # remove partial
-        print('Download error ')  # raise Exception('Download error')
-        return r
-
-    # Unzip if archive
-    if file.suffix == '.zip':
-        print('unzipping... ', end='')
-        ZipFile(file).extractall(path=file.parent)  # unzip
-        file.unlink()  # remove zip
-
-    print(f'Done ({time.time() - t:.1f}s)')
-    return r
-
-
-def get_token(cookie="./cookie"):
-    with open(cookie) as f:
-        for line in f:
-            if "download" in line:
-                return line.split()[-1]
-    return ""
-
-# Google utils: https://cloud.google.com/storage/docs/reference/libraries ----------------------------------------------
-#
-#
-# def upload_blob(bucket_name, source_file_name, destination_blob_name):
-#     # Uploads a file to a bucket
-#     # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
-#
-#     storage_client = storage.Client()
-#     bucket = storage_client.get_bucket(bucket_name)
-#     blob = bucket.blob(destination_blob_name)
-#
-#     blob.upload_from_filename(source_file_name)
-#
-#     print('File {} uploaded to {}.'.format(
-#         source_file_name,
-#         destination_blob_name))
-#
-#
-# def download_blob(bucket_name, source_blob_name, destination_file_name):
-#     # Uploads a blob from a bucket
-#     storage_client = storage.Client()
-#     bucket = storage_client.get_bucket(bucket_name)
-#     blob = bucket.blob(source_blob_name)
-#
-#     blob.download_to_filename(destination_file_name)
-#
-#     print('Blob {} downloaded to {}.'.format(
-#         source_blob_name,
-#         destination_file_name))

ultralytics/yolov5/utils/flask_rest_api/README.md

@@ -1,73 +0,0 @@
-# Flask REST API
-
-[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are
-commonly used to expose Machine Learning (ML)  models to other services. This folder contains an example REST API
-created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
-
-## Requirements
-
-[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
-
-```shell
-$ pip install Flask
-```
-
-## Run
-
-After Flask installation run:
-
-```shell
-$ python3 restapi.py --port 5000
-```
-
-Then use [curl](https://curl.se/) to perform a request:
-
-```shell
-$ curl -X POST -F [email protected] 'http://localhost:5000/v1/object-detection/yolov5s'
-```
-
-The model inference results are returned as a JSON response:
-
-```json
-[
-  {
-    "class": 0,
-    "confidence": 0.8900438547,
-    "height": 0.9318675399,
-    "name": "person",
-    "width": 0.3264600933,
-    "xcenter": 0.7438579798,
-    "ycenter": 0.5207948685
-  },
-  {
-    "class": 0,
-    "confidence": 0.8440024257,
-    "height": 0.7155083418,
-    "name": "person",
-    "width": 0.6546785235,
-    "xcenter": 0.427829951,
-    "ycenter": 0.6334488392
-  },
-  {
-    "class": 27,
-    "confidence": 0.3771208823,
-    "height": 0.3902671337,
-    "name": "tie",
-    "width": 0.0696444362,
-    "xcenter": 0.3675483763,
-    "ycenter": 0.7991207838
-  },
-  {
-    "class": 27,
-    "confidence": 0.3527112305,
-    "height": 0.1540903747,
-    "name": "tie",
-    "width": 0.0336618312,
-    "xcenter": 0.7814827561,
-    "ycenter": 0.5065554976
-  }
-]
-```
-
-An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given
-in `example_request.py`