feat(YOLOX): lint code and add a simple workflow (#400)

.github/workflows/ci.yaml

@@ -0,0 +1,39 @@
+# This is a basic workflow to help you get started with Actions
+
+name: CI
+
+# Controls when the action will run. Triggers the workflow on push or pull request
+# events but only for the master branch
+on:
+  push:
+  pull_request:
+
+# A workflow run is made up of one or more jobs that can run sequentially or in parallel
+jobs:
+  # This workflow contains a single job called "build"
+  build:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6, 3.7, 3.8]
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+    # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it
+    - uses: actions/checkout@v2
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v1
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -r requirements.txt
+        pip install isort==4.3.21
+        pip install flake8==3.8.3
+    # Runs a set of commands using the runners shell
+    - name: Format check
+      run: ./.github/workflows/format_check.sh

.github/workflows/format_check.sh

@@ -0,0 +1,16 @@
+#!/bin/bash -e
+
+set -e
+
+export PYTHONPATH=$PWD:$PYTHONPATH
+
+flake8 yolox || flake8_ret=$?
+if [ "$flake8_ret" ]; then
+    exit $flake8_ret
+fi
+echo "All flake check passed!"
+isort --check-only -rc yolox || isort_ret=$?
+if [ "$isort_ret" ]; then
+    exit $isort_ret
+fi
+echo "All isort check passed!"

demo/MegEngine/python/build.py

@@ -3,7 +3,6 @@
 
 import megengine as mge
 import megengine.module as M
-from megengine import jit
 
 from models.yolo_fpn import YOLOFPN
 from models.yolo_head import YOLOXHead

demo/MegEngine/python/coco_classes.py

@@ -1,86 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding:utf-8 -*-
-# Copyright (c) Megvii, Inc. and its affiliates.
-
-COCO_CLASSES = (
-    "person",
-    "bicycle",
-    "car",
-    "motorcycle",
-    "airplane",
-    "bus",
-    "train",
-    "truck",
-    "boat",
-    "traffic light",
-    "fire hydrant",
-    "stop sign",
-    "parking meter",
-    "bench",
-    "bird",
-    "cat",
-    "dog",
-    "horse",
-    "sheep",
-    "cow",
-    "elephant",
-    "bear",
-    "zebra",
-    "giraffe",
-    "backpack",
-    "umbrella",
-    "handbag",
-    "tie",
-    "suitcase",
-    "frisbee",
-    "skis",
-    "snowboard",
-    "sports ball",
-    "kite",
-    "baseball bat",
-    "baseball glove",
-    "skateboard",
-    "surfboard",
-    "tennis racket",
-    "bottle",
-    "wine glass",
-    "cup",
-    "fork",
-    "knife",
-    "spoon",
-    "bowl",
-    "banana",
-    "apple",
-    "sandwich",
-    "orange",
-    "broccoli",
-    "carrot",
-    "hot dog",
-    "pizza",
-    "donut",
-    "cake",
-    "chair",
-    "couch",
-    "potted plant",
-    "bed",
-    "dining table",
-    "toilet",
-    "tv",
-    "laptop",
-    "mouse",
-    "remote",
-    "keyboard",
-    "cell phone",
-    "microwave",
-    "oven",
-    "toaster",
-    "sink",
-    "refrigerator",
-    "book",
-    "clock",
-    "vase",
-    "scissors",
-    "teddy bear",
-    "hair drier",
-    "toothbrush",
-)

demo/MegEngine/python/demo.py

@@ -11,9 +11,10 @@ import megengine as mge
 import megengine.functional as F
 from loguru import logger
 
-from coco_classes import COCO_CLASSES
-from process import postprocess, preprocess
-from visualize import vis
+from yolox.data.datasets import COCO_CLASSES
+from yolox.utils import vis
+from yolox.data.data_augment import preproc as preprocess
+
 from build import build_and_load
 
 IMAGE_EXT = [".jpg", ".jpeg", ".webp", ".bmp", ".png"]
@@ -51,6 +52,43 @@ def get_image_list(path):
     return image_names
 
 
+def postprocess(prediction, num_classes, conf_thre=0.7, nms_thre=0.45):
+    box_corner = F.zeros_like(prediction)
+    box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
+    box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
+    box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
+    box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
+    prediction[:, :, :4] = box_corner[:, :, :4]
+
+    output = [None for _ in range(len(prediction))]
+    for i, image_pred in enumerate(prediction):
+
+        # If none are remaining => process next image
+        if not image_pred.shape[0]:
+            continue
+        # Get score and class with highest confidence
+        class_conf = F.max(image_pred[:, 5: 5 + num_classes], 1, keepdims=True)
+        class_pred = F.argmax(image_pred[:, 5: 5 + num_classes], 1, keepdims=True)
+
+        class_conf_squeeze = F.squeeze(class_conf)
+        conf_mask = image_pred[:, 4] * class_conf_squeeze >= conf_thre
+        detections = F.concat((image_pred[:, :5], class_conf, class_pred), 1)
+        detections = detections[conf_mask]
+        if not detections.shape[0]:
+            continue
+
+        nms_out_index = F.vision.nms(
+            detections[:, :4], detections[:, 4] * detections[:, 5], nms_thre,
+        )
+        detections = detections[nms_out_index]
+        if output[i] is None:
+            output[i] = detections
+        else:
+            output[i] = F.concat((output[i], detections))
+
+    return output
+
+
 class Predictor(object):
     def __init__(
         self,
@@ -168,7 +206,6 @@ def imageflow_demo(predictor, vis_folder, current_time, args):
 
 
 def main(args):
-
     file_name = os.path.join("./yolox_outputs", args.name)
     os.makedirs(file_name, exist_ok=True)
 

demo/MegEngine/python/process.py

@@ -1,76 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding:utf-8 -*-
-# Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
-
-import cv2
-import megengine.functional as F
-import numpy as np
-
-__all__ = [
-    "preprocess",
-    "postprocess",
-]
-
-
-def preprocess(image, input_size, mean, std, swap=(2, 0, 1)):
-    if len(image.shape) == 3:
-        padded_img = np.ones((input_size[0], input_size[1], 3)) * 114.0
-    else:
-        padded_img = np.ones(input_size) * 114.0
-    img = np.array(image)
-    r = min(input_size[0] / img.shape[0], input_size[1] / img.shape[1])
-    resized_img = cv2.resize(
-        img,
-        (int(img.shape[1] * r), int(img.shape[0] * r)),
-        interpolation=cv2.INTER_LINEAR,
-    ).astype(np.float32)
-    padded_img[: int(img.shape[0] * r), : int(img.shape[1] * r)] = resized_img
-    image = padded_img
-
-    image = image.astype(np.float32)
-    image = image[:, :, ::-1]
-    image /= 255.0
-    if mean is not None:
-        image -= mean
-    if std is not None:
-        image /= std
-    image = image.transpose(swap)
-    image = np.ascontiguousarray(image, dtype=np.float32)
-    return image, r
-
-
-def postprocess(prediction, num_classes, conf_thre=0.7, nms_thre=0.45):
-    box_corner = F.zeros_like(prediction)
-    box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
-    box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
-    box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
-    box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
-    prediction[:, :, :4] = box_corner[:, :, :4]
-
-    output = [None for _ in range(len(prediction))]
-    for i, image_pred in enumerate(prediction):
-
-        # If none are remaining => process next image
-        if not image_pred.shape[0]:
-            continue
-        # Get score and class with highest confidence
-        class_conf = F.max(image_pred[:, 5 : 5 + num_classes], 1, keepdims=True)
-        class_pred = F.argmax(image_pred[:, 5 : 5 + num_classes], 1, keepdims=True)
-
-        class_conf_squeeze = F.squeeze(class_conf)
-        conf_mask = image_pred[:, 4] * class_conf_squeeze >= conf_thre
-        detections = F.concat((image_pred[:, :5], class_conf, class_pred), 1)
-        detections = detections[conf_mask]
-        if not detections.shape[0]:
-            continue
-
-        nms_out_index = F.vision.nms(
-            detections[:, :4], detections[:, 4] * detections[:, 5], nms_thre,
-        )
-        detections = detections[nms_out_index]
-        if output[i] is None:
-            output[i] = detections
-        else:
-            output[i] = F.concat((output[i], detections))
-
-    return output

demo/MegEngine/python/visualize.py

@@ -1,128 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding:utf-8 -*-
-# Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
-
-import cv2
-import numpy as np
-
-__all__ = ["vis"]
-
-
-def vis(img, boxes, scores, cls_ids, conf=0.5, class_names=None):
-
-    for i in range(len(boxes)):
-        box = boxes[i]
-        cls_id = int(cls_ids[i])
-        score = scores[i]
-        if score < conf:
-            continue
-        x0 = int(box[0])
-        y0 = int(box[1])
-        x1 = int(box[2])
-        y1 = int(box[3])
-
-        color = (_COLORS[cls_id] * 255).astype(np.uint8).tolist()
-        text = '{}:{:.1f}%'.format(class_names[cls_id], score * 100)
-        txt_color = (0, 0, 0) if np.mean(_COLORS[cls_id]) > 0.5 else (255, 255, 255)
-        font = cv2.FONT_HERSHEY_SIMPLEX
-
-        txt_size = cv2.getTextSize(text, font, 0.4, 1)[0]
-        cv2.rectangle(img, (x0, y0), (x1, y1), color, 2)
-
-        txt_bk_color = (_COLORS[cls_id] * 255 * 0.7).astype(np.uint8).tolist()
-        cv2.rectangle(
-            img,
-            (x0, y0 + 1),
-            (x0 + txt_size[0] + 1, y0 + int(1.5*txt_size[1])),
-            txt_bk_color,
-            -1
-        )
-        cv2.putText(img, text, (x0, y0 + txt_size[1]), font, 0.4, txt_color, thickness=1)
-
-    return img
-
-
-_COLORS = np.array(
-    [
-        0.000, 0.447, 0.741,
-        0.850, 0.325, 0.098,
-        0.929, 0.694, 0.125,
-        0.494, 0.184, 0.556,
-        0.466, 0.674, 0.188,
-        0.301, 0.745, 0.933,
-        0.635, 0.078, 0.184,
-        0.300, 0.300, 0.300,
-        0.600, 0.600, 0.600,
-        1.000, 0.000, 0.000,
-        1.000, 0.500, 0.000,
-        0.749, 0.749, 0.000,
-        0.000, 1.000, 0.000,
-        0.000, 0.000, 1.000,
-        0.667, 0.000, 1.000,
-        0.333, 0.333, 0.000,
-        0.333, 0.667, 0.000,
-        0.333, 1.000, 0.000,
-        0.667, 0.333, 0.000,
-        0.667, 0.667, 0.000,
-        0.667, 1.000, 0.000,
-        1.000, 0.333, 0.000,
-        1.000, 0.667, 0.000,
-        1.000, 1.000, 0.000,
-        0.000, 0.333, 0.500,
-        0.000, 0.667, 0.500,
-        0.000, 1.000, 0.500,
-        0.333, 0.000, 0.500,
-        0.333, 0.333, 0.500,
-        0.333, 0.667, 0.500,
-        0.333, 1.000, 0.500,
-        0.667, 0.000, 0.500,
-        0.667, 0.333, 0.500,
-        0.667, 0.667, 0.500,
-        0.667, 1.000, 0.500,
-        1.000, 0.000, 0.500,
-        1.000, 0.333, 0.500,
-        1.000, 0.667, 0.500,
-        1.000, 1.000, 0.500,
-        0.000, 0.333, 1.000,
-        0.000, 0.667, 1.000,
-        0.000, 1.000, 1.000,
-        0.333, 0.000, 1.000,
-        0.333, 0.333, 1.000,
-        0.333, 0.667, 1.000,
-        0.333, 1.000, 1.000,
-        0.667, 0.000, 1.000,
-        0.667, 0.333, 1.000,
-        0.667, 0.667, 1.000,
-        0.667, 1.000, 1.000,
-        1.000, 0.000, 1.000,
-        1.000, 0.333, 1.000,
-        1.000, 0.667, 1.000,
-        0.333, 0.000, 0.000,
-        0.500, 0.000, 0.000,
-        0.667, 0.000, 0.000,
-        0.833, 0.000, 0.000,
-        1.000, 0.000, 0.000,
-        0.000, 0.167, 0.000,
-        0.000, 0.333, 0.000,
-        0.000, 0.500, 0.000,
-        0.000, 0.667, 0.000,
-        0.000, 0.833, 0.000,
-        0.000, 1.000, 0.000,
-        0.000, 0.000, 0.167,
-        0.000, 0.000, 0.333,
-        0.000, 0.000, 0.500,
-        0.000, 0.000, 0.667,
-        0.000, 0.000, 0.833,
-        0.000, 0.000, 1.000,
-        0.000, 0.000, 0.000,
-        0.143, 0.143, 0.143,
-        0.286, 0.286, 0.286,
-        0.429, 0.429, 0.429,
-        0.571, 0.571, 0.571,
-        0.714, 0.714, 0.714,
-        0.857, 0.857, 0.857,
-        0.000, 0.447, 0.741,
-        0.314, 0.717, 0.741,
-        0.50, 0.5, 0
-    ]
-).astype(np.float32).reshape(-1, 3)

exps/default/nano.py

@@ -3,6 +3,7 @@
 # Copyright (c) Megvii, Inc. and its affiliates.
 
 import os
+
 import torch.nn as nn
 
 from yolox.exp import Exp as MyExp

exps/default/yolov3.py

@@ -3,6 +3,7 @@
 # Copyright (c) Megvii, Inc. and its affiliates.
 
 import os
+
 import torch
 import torch.nn as nn
 

exps/example/custom/nano.py

@@ -3,6 +3,7 @@
 # Copyright (c) Megvii, Inc. and its affiliates.
 
 import os
+
 import torch.nn as nn
 
 from yolox.exp import Exp as MyExp

exps/example/custom/yolox_s.py

@@ -2,7 +2,6 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 import os
-from pathlib import Path
 
 from yolox.exp import Exp as MyExp
 

exps/example/yolox_voc/yolox_voc_s.py

@@ -1,12 +1,12 @@
 # encoding: utf-8
 import os
-import random
+
 import torch
-import torch.nn as nn
 import torch.distributed as dist
 
-from yolox.exp import Exp as MyExp
 from yolox.data import get_yolox_datadir
+from yolox.exp import Exp as MyExp
+
 
 class Exp(MyExp):
     def __init__(self):

setup.py

@@ -9,7 +9,7 @@ import torch
 from torch.utils.cpp_extension import CppExtension
 
 torch_ver = [int(x) for x in torch.__version__.split(".")[:2]]
-assert torch_ver >= [1, 3], "Requires PyTorch >= 1.3"
+assert torch_ver >= [1, 7], "Requires PyTorch >= 1.7"
 
 
 def get_extensions():

tools/demo.py

@@ -2,6 +2,9 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import argparse
+import os
+import time
 from loguru import logger
 
 import cv2
@@ -13,10 +16,6 @@ from yolox.data.datasets import COCO_CLASSES
 from yolox.exp import get_exp
 from yolox.utils import fuse_model, get_model_info, postprocess, vis
 
-import argparse
-import os
-import time
-
 IMAGE_EXT = [".jpg", ".jpeg", ".webp", ".bmp", ".png"]
 
 

tools/eval.py

@@ -2,6 +2,10 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import argparse
+import os
+import random
+import warnings
 from loguru import logger
 
 import torch
@@ -10,12 +14,7 @@ from torch.nn.parallel import DistributedDataParallel as DDP
 
 from yolox.core import launch
 from yolox.exp import get_exp
-from yolox.utils import configure_nccl, fuse_model, get_local_rank, get_model_info, setup_logger
-
-import argparse
-import os
-import random
-import warnings
+from yolox.utils import fuse_model, get_model_info, setup_logger
 
 
 def make_parser():

tools/export_onnx.py

@@ -2,6 +2,8 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import argparse
+import os
 from loguru import logger
 
 import torch
@@ -11,9 +13,6 @@ from yolox.exp import get_exp
 from yolox.models.network_blocks import SiLU
 from yolox.utils import replace_module
 
-import argparse
-import os
-
 
 def make_parser():
     parser = argparse.ArgumentParser("YOLOX onnx deploy")

tools/train.py

@@ -2,6 +2,9 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import argparse
+import random
+import warnings
 from loguru import logger
 
 import torch
@@ -10,10 +13,6 @@ import torch.backends.cudnn as cudnn
 from yolox.core import Trainer, launch
 from yolox.exp import get_exp
 
-import argparse
-import random
-import warnings
-
 
 def make_parser():
     parser = argparse.ArgumentParser("YOLOX train parser")

tools/trt.py

@@ -2,6 +2,9 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import argparse
+import os
+import shutil
 from loguru import logger
 
 import tensorrt as trt
@@ -10,10 +13,6 @@ from torch2trt import torch2trt
 
 from yolox.exp import get_exp
 
-import argparse
-import os
-import shutil
-
 
 def make_parser():
     parser = argparse.ArgumentParser("YOLOX ncnn deploy")

yolox/core/launch.py

@@ -5,19 +5,20 @@
 # Copyright (c) Facebook, Inc. and its affiliates.
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import os
+import subprocess
+import sys
+import time
 from loguru import logger
 
 import torch
 import torch.distributed as dist
-import torch.multiprocessing as mp
 
 import yolox.utils.dist as comm
 from yolox.utils import configure_nccl
 
-import os
-import subprocess
-import sys
-import time
+# import torch.multiprocessing as mp
+
 
 __all__ = ["launch"]
 

yolox/core/trainer.py

@@ -2,6 +2,9 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import datetime
+import os
+import time
 from loguru import logger
 
 import apex
@@ -25,10 +28,6 @@ from yolox.utils import (
     synchronize
 )
 
-import datetime
-import os
-import time
-
 
 class Trainer:
     def __init__(self, exp, args):

yolox/data/data_augment.py

@@ -9,16 +9,14 @@ The data augmentation procedures were interpreted from @weiliu89's SSD paper
 http://arxiv.org/abs/1512.02325
 """
 
+import math
+import random
+
 import cv2
 import numpy as np
 
-import torch
-
 from yolox.utils import xyxy2cxcywh
 
-import math
-import random
-
 
 def augment_hsv(img, hgain=0.015, sgain=0.7, vgain=0.4):
     r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains

yolox/data/data_prefetcher.py

@@ -2,13 +2,13 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import random
+
 import torch
 import torch.distributed as dist
 
 from yolox.utils import synchronize
 
-import random
-
 
 class DataPrefetcher:
     """

yolox/data/dataloading.py

@@ -2,13 +2,13 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import os
+import random
+
 import torch
 from torch.utils.data.dataloader import DataLoader as torchDataLoader
 from torch.utils.data.dataloader import default_collate
 
-import os
-import random
-
 from .samplers import YoloBatchSampler
 
 

yolox/data/datasets/coco.py

@@ -2,12 +2,12 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import os
+
 import cv2
 import numpy as np
 from pycocotools.coco import COCO
 
-import os
-
 from ..dataloading import get_yolox_datadir
 from .datasets_wrapper import Dataset
 

yolox/data/datasets/datasets_wrapper.py

@@ -2,12 +2,12 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
-from torch.utils.data.dataset import ConcatDataset as torchConcatDataset
-from torch.utils.data.dataset import Dataset as torchDataset
-
 import bisect
 from functools import wraps
 
+from torch.utils.data.dataset import ConcatDataset as torchConcatDataset
+from torch.utils.data.dataset import Dataset as torchDataset
+
 
 class ConcatDataset(torchConcatDataset):
     def __init__(self, datasets):

yolox/data/datasets/mosaicdetection.py

@@ -2,13 +2,13 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import random
+
 import cv2
 import numpy as np
 
 from yolox.utils import adjust_box_anns
 
-import random
-
 from ..data_augment import box_candidates, random_perspective
 from .datasets_wrapper import Dataset
 

yolox/data/datasets/voc.py

@@ -6,16 +6,16 @@
 # Copyright (c) Ellis Brown, Max deGroot.
 # Copyright (c) Megvii, Inc. and its affiliates.
 
-import cv2
-import numpy as np
-
-from yolox.evaluators.voc_eval import voc_eval
-
 import os
 import os.path
 import pickle
 import xml.etree.ElementTree as ET
 
+import cv2
+import numpy as np
+
+from yolox.evaluators.voc_eval import voc_eval
+
 from .datasets_wrapper import Dataset
 from .voc_classes import VOC_CLASSES
 

yolox/data/samplers.py

@@ -2,14 +2,14 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import itertools
+from typing import Optional
+
 import torch
 import torch.distributed as dist
 from torch.utils.data.sampler import BatchSampler as torchBatchSampler
 from torch.utils.data.sampler import Sampler
 
-import itertools
-from typing import Optional
-
 
 class YoloBatchSampler(torchBatchSampler):
     """

yolox/evaluators/coco_evaluator.py

@@ -2,6 +2,12 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import contextlib
+import io
+import itertools
+import json
+import tempfile
+import time
 from loguru import logger
 from tqdm import tqdm
 
@@ -16,13 +22,6 @@ from yolox.utils import (
     xyxy2xywh
 )
 
-import contextlib
-import io
-import itertools
-import json
-import tempfile
-import time
-
 
 class COCOEvaluator:
     """

yolox/evaluators/voc_eval.py

@@ -5,12 +5,12 @@
 # Copyright (c) Bharath Hariharan.
 # Copyright (c) Megvii, Inc. and its affiliates.
 
-import numpy as np
-
 import os
 import pickle
 import xml.etree.ElementTree as ET
 
+import numpy as np
+
 
 def parse_rec(filename):
     """ Parse a PASCAL VOC xml file """

yolox/evaluators/voc_evaluator.py

@@ -2,6 +2,10 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) Megvii, Inc. and its affiliates.
 
+import sys
+import tempfile
+import time
+from collections import ChainMap
 from loguru import logger
 from tqdm import tqdm
 
@@ -11,11 +15,6 @@ import torch
 
 from yolox.utils import gather, is_main_process, postprocess, synchronize, time_synchronized
 
-import sys
-import tempfile
-import time
-from collections import ChainMap
-
 
 class VOCEvaluator:
     """

yolox/exp/base_exp.py

@@ -2,16 +2,16 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
-import torch
-from torch.nn import Module
-
-from yolox.utils import LRScheduler
-
 import ast
 import pprint
 from abc import ABCMeta, abstractmethod
-from tabulate import tabulate
 from typing import Dict
+from tabulate import tabulate
+
+import torch
+from torch.nn import Module
+
+from yolox.utils import LRScheduler
 
 
 class BaseExp(metaclass=ABCMeta):

yolox/layers/fast_coco_eval_api.py

@@ -5,6 +5,9 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
+import copy
+import time
+
 import numpy as np
 from pycocotools.cocoeval import COCOeval
 
@@ -12,9 +15,6 @@ from pycocotools.cocoeval import COCOeval
 # in YOLOX, env is already set in __init__.py.
 from yolox import _C
 
-import copy
-import time
-
 
 class COCOeval_opt(COCOeval):
     """

yolox/models/yolo_head.py

@@ -2,6 +2,7 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
+import math
 from loguru import logger
 
 import torch
@@ -10,8 +11,6 @@ import torch.nn.functional as F
 
 from yolox.utils import bboxes_iou
 
-import math
-
 from .losses import IOUloss
 from .network_blocks import BaseConv, DWConv
 

yolox/utils/allreduce_norm.py

@@ -2,13 +2,13 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
+import pickle
+from collections import OrderedDict
+
 import torch
 from torch import distributed as dist
 from torch import nn
 
-import pickle
-from collections import OrderedDict
-
 from .dist import _get_global_gloo_group, get_world_size
 
 ASYNC_NORM = (

yolox/utils/boxes.py

@@ -44,12 +44,9 @@ def postprocess(prediction, num_classes, conf_thre=0.7, nms_thre=0.45):
         if not image_pred.size(0):
             continue
         # Get score and class with highest confidence
-        class_conf, class_pred = torch.max(
-            image_pred[:, 5 : 5 + num_classes], 1, keepdim=True
-        )
+        class_conf, class_pred = torch.max(image_pred[:, 5: 5 + num_classes], 1, keepdim=True)
 
         conf_mask = (image_pred[:, 4] * class_conf.squeeze() >= conf_thre).squeeze()
-        # _, conf_mask = torch.topk((image_pred[:, 4] * class_conf.squeeze()), 1000)
         # Detections ordered as (x1, y1, x2, y2, obj_conf, class_conf, class_pred)
         detections = torch.cat((image_pred[:, :5], class_conf, class_pred.float()), 1)
         detections = detections[conf_mask]

yolox/utils/checkpoint.py

@@ -1,13 +1,12 @@
 #!/usr/bin/env python3
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
+import os
+import shutil
 from loguru import logger
 
 import torch
 
-import os
-import shutil
-
 
 def load_ckpt(model, ckpt):
     model_state_dict = model.state_dict()

yolox/utils/demo_utils.py

@@ -2,10 +2,10 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
-import numpy as np
-
 import os
 
+import numpy as np
+
 __all__ = ["mkdir", "nms", "multiclass_nms", "demo_postprocess"]
 
 

yolox/utils/dist.py

@@ -9,16 +9,16 @@ This file contains primitives for multi-gpu communication.
 This is useful when doing distributed training.
 """
 
-import numpy as np
-
-import torch
-from torch import distributed as dist
-
 import functools
 import logging
 import pickle
 import time
 
+import numpy as np
+
+import torch
+from torch import distributed as dist
+
 __all__ = [
     "is_main_process",
     "synchronize",

yolox/utils/ema.py

@@ -1,12 +1,12 @@
 #!/usr/bin/env python3
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
-import torch
-import torch.nn as nn
-
 import math
 from copy import deepcopy
 
+import torch
+import torch.nn as nn
+
 
 def is_parallel(model):
     """check if model is in parallel mode."""

yolox/utils/logger.py

@@ -2,11 +2,10 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
-from loguru import logger
-
 import inspect
 import os
 import sys
+from loguru import logger
 
 
 def get_caller_name(depth=0):

yolox/utils/metric.py

@@ -1,15 +1,15 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
-import numpy as np
-
-import torch
-
 import functools
 import os
 import time
 from collections import defaultdict, deque
 
+import numpy as np
+
+import torch
+
 __all__ = [
     "AverageMeter",
     "MeterBuffer",

yolox/utils/model_utils.py

@@ -2,12 +2,12 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
+from copy import deepcopy
+
 import torch
 import torch.nn as nn
 from thop import profile
 
-from copy import deepcopy
-
 __all__ = [
     "fuse_conv_and_bn",
     "fuse_model",

yolox/utils/setup_env.py

@@ -2,11 +2,11 @@
 # -*- coding:utf-8 -*-
 # Copyright (c) 2014-2021 Megvii Inc. All rights reserved.
 
-import cv2
-
 import os
 import subprocess
 
+import cv2
+
 __all__ = ["configure_nccl", "configure_module"]