v04 update

.gitignore

@@ -0,0 +1,45 @@
+# 图片格式
+*.jpg
+*.jpeg
+*.png
+*.svg
+*.gif
+
+# 视频格式
+*.mp4
+*.avi
+.ipynb_checkpoints
+*/__pycache__
+
+# 日志格式
+*.log
+*.data
+*.txt
+*.csv
+
+# 参数文件
+*.yaml
+*.json
+
+# 压缩文件格式
+*.zip
+*.tar
+*.tar.gz
+*.rar
+
+# 字体格式
+*.ttc
+*.ttf
+*.otf
+
+*.pt
+*.db
+
+/flagged
+/run
+!requirements.txt
+!cls_name/*
+!model_config/*
+!img_example/*
+
+app copy.py

README.md

@@ -1,6 +1,6 @@
 ---
 title: Gradio_YOLOv5_Det_v4
-emoji: 🌖
+emoji: 🚀
 colorFrom: yellow
 colorTo: indigo
 sdk: gradio
@@ -11,3 +11,5 @@ license: gpl-3.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference
+
+🚀 Project homepage：https://gitee.com/CV_Lab/gradio_yolov5_det

__init__.py

@@ -0,0 +1,2 @@
+__author__ = "曾逸夫（Zeng Yifu）"
+__email__ = "[email protected]"

app.py

@@ -0,0 +1,615 @@
+# Gradio YOLOv5 Det v0.4
+# author: Zeng Yifu（曾逸夫）
+# creation time: 2022-05-28
+# email: [email protected]
+# project homepage: https://gitee.com/CV_Lab/gradio_yolov5_det
+
+import argparse
+import csv
+import gc
+import json
+import os
+import sys
+from collections import Counter
+from pathlib import Path
+
+import cv2
+import gradio as gr
+import numpy as np
+import pandas as pd
+import torch
+import yaml
+from PIL import Image, ImageDraw, ImageFont
+
+from util.fonts_opt import is_fonts
+from util.pdf_opt import pdf_generate
+
+ROOT_PATH = sys.path[0]  # root directory
+
+# model path
+model_path = "ultralytics/yolov5"
+
+# Gradio YOLOv5 Det version
+GYD_VERSION = "Gradio YOLOv5 Det v0.4"
+
+# model name temporary variable
+model_name_tmp = ""
+
+# Device temporary variables
+device_tmp = ""
+
+# File extension
+suffix_list = [".csv", ".yaml"]
+
+# font size
+FONTSIZE = 25
+
+# object style
+obj_style = ["Small Object", "Medium Object", "Large Object"]
+
+
+def parse_args(known=False):
+    parser = argparse.ArgumentParser(description="Gradio YOLOv5 Det v0.4")
+    parser.add_argument("--source", "-src", default="upload", type=str, help="input source")
+    parser.add_argument("--source_video", "-src_v", default="upload", type=str, help="video input source")
+    parser.add_argument("--img_tool", "-it", default="editor", type=str, help="input image tool")
+    parser.add_argument("--model_name", "-mn", default="yolov5s", type=str, help="model name")
+    parser.add_argument(
+        "--model_cfg",
+        "-mc",
+        default="./model_config/model_name_p5_p6_all.yaml",
+        type=str,
+        help="model config",
+    )
+    parser.add_argument(
+        "--cls_name",
+        "-cls",
+        default="./cls_name/cls_name_en.yaml",
+        type=str,
+        help="cls name",
+    )
+    parser.add_argument(
+        "--nms_conf",
+        "-conf",
+        default=0.5,
+        type=float,
+        help="model NMS confidence threshold",
+    )
+    parser.add_argument("--nms_iou", "-iou", default=0.45, type=float, help="model NMS IoU threshold")
+    parser.add_argument(
+        "--device",
+        "-dev",
+        default="cpu",
+        type=str,
+        help="cuda or cpu",
+    )
+    parser.add_argument("--inference_size", "-isz", default=640, type=int, help="model inference size")
+    parser.add_argument("--max_detnum", "-mdn", default=50, type=float, help="model max det num")
+    parser.add_argument("--slider_step", "-ss", default=0.05, type=float, help="slider step")
+    parser.add_argument(
+        "--is_login",
+        "-isl",
+        action="store_true",
+        default=False,
+        help="is login",
+    )
+    parser.add_argument('--usr_pwd',
+                        "-up",
+                        nargs='+',
+                        type=str,
+                        default=["admin", "admin"],
+                        help="user & password for login")
+    parser.add_argument(
+        "--is_share",
+        "-is",
+        action="store_true",
+        default=False,
+        help="is login",
+    )
+
+    args = parser.parse_known_args()[0] if known else parser.parse_args()
+    return args
+
+
+# yaml file parsing
+def yaml_parse(file_path):
+    return yaml.safe_load(open(file_path, encoding="utf-8").read())
+
+
+# yaml csv file parsing
+def yaml_csv(file_path, file_tag):
+    file_suffix = Path(file_path).suffix
+    if file_suffix == suffix_list[0]:
+        # model name
+        file_names = [i[0] for i in list(csv.reader(open(file_path)))]  # csv version
+    elif file_suffix == suffix_list[1]:
+        # model name
+        file_names = yaml_parse(file_path).get(file_tag)  # yaml version
+    else:
+        print(f"{file_path} is not in the correct format! Program exits!")
+        sys.exit()
+
+    return file_names
+
+
+# model loading
+def model_loading(model_name, device):
+
+    # load model
+    model = torch.hub.load(model_path, model_name, force_reload=True, device=device, _verbose=False)
+
+    return model
+
+
+# check information
+def export_json(results, img_size):
+
+    return [[{
+        "ID": i,
+        "CLASS": int(result[i][5]),
+        "CLASS_NAME": model_cls_name_cp[int(result[i][5])],
+        "BOUNDING_BOX": {
+            "XMIN": round(result[i][:4].tolist()[0], 6),
+            "YMIN": round(result[i][:4].tolist()[1], 6),
+            "XMAX": round(result[i][:4].tolist()[2], 6),
+            "YMAX": round(result[i][:4].tolist()[3], 6),},
+        "CONF": round(float(result[i][4]), 2),
+        "FPS": round(1000 / float(results.t[1]), 2),
+        "IMG_WIDTH": img_size[0],
+        "IMG_HEIGHT": img_size[1],} for i in range(len(result))] for result in results.xyxyn]
+
+
+# frame conversion
+def pil_draw(img, countdown_msg, textFont, xyxy, font_size, opt):
+
+    img_pil = ImageDraw.Draw(img)
+
+    img_pil.rectangle(xyxy, fill=None, outline="green")  # bounding box
+
+    if "label" in opt:
+        text_w, text_h = textFont.getsize(countdown_msg)  # Label size
+        img_pil.rectangle(
+            (xyxy[0], xyxy[1], xyxy[0] + text_w, xyxy[1] + text_h),
+            fill="green",
+            outline="green",
+        )  # label background
+        img_pil.multiline_text(
+            (xyxy[0], xyxy[1]),
+            countdown_msg,
+            fill=(205, 250, 255),
+            font=textFont,
+            align="center",
+        )
+
+    return img
+
+
+# YOLOv5 image detection function
+def yolo_det_img(img, device, model_name, infer_size, conf, iou, max_num, model_cls, opt):
+
+    global model, model_name_tmp, device_tmp
+
+    # object size num
+    s_obj, m_obj, l_obj = 0, 0, 0
+    # object area list
+    area_obj_all = []
+    # cls num stat
+    cls_det_stat = []
+
+    if model_name_tmp != model_name:
+        # Model judgment to avoid repeated loading
+        model_name_tmp = model_name
+        model = model_loading(model_name_tmp, device)
+    elif device_tmp != device:
+        device_tmp = device
+        model = model_loading(model_name_tmp, device)
+
+    # -------------Model tuning -------------
+    model.conf = conf  # NMS confidence threshold
+    model.iou = iou  # NMS IoU threshold
+    model.max_det = int(max_num)  # Maximum number of detection frames
+    model.classes = model_cls  # model classes
+
+    img_size = img.size  # frame size
+
+    results = model(img, size=infer_size)  # detection
+
+    # Data Frame
+    dataframe = results.pandas().xyxy[0].round(2)
+
+    # ----------------Load fonts----------------
+    yaml_index = cls_name.index(".yaml")
+    cls_name_lang = cls_name[yaml_index - 2:yaml_index]
+
+    if cls_name_lang == "zh":
+        # Chinese
+        textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/SimSun.ttf"), size=FONTSIZE)
+    elif cls_name_lang in ["en", "ru", "es", "ar"]:
+        # English, Russian, Spanish, Arabic
+        textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/TimesNewRoman.ttf"), size=FONTSIZE)
+    elif cls_name_lang == "ko":
+        # Korean
+        textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/malgun.ttf"), size=FONTSIZE)
+
+    for result in results.xyxyn:
+        for i in range(len(result)):
+            id = int(i)  # instance ID
+            obj_cls_index = int(result[i][5])  # category index
+            obj_cls = model_cls_name_cp[obj_cls_index]  # category
+            cls_det_stat.append(obj_cls)
+
+            # ------------ border coordinates ------------
+            x0 = float(result[i][:4].tolist()[0])
+            y0 = float(result[i][:4].tolist()[1])
+            x1 = float(result[i][:4].tolist()[2])
+            y1 = float(result[i][:4].tolist()[3])
+
+            # ------------ Actual coordinates of the border ------------
+            x0 = int(img_size[0] * x0)
+            y0 = int(img_size[1] * y0)
+            x1 = int(img_size[0] * x1)
+            y1 = int(img_size[1] * y1)
+
+            conf = float(result[i][4])  # confidence
+            # fps = f"{(1000 / float(results.t[1])):.2f}" # FPS
+
+            det_img = pil_draw(
+                img,
+                f"{id}-{obj_cls}:{conf:.2f}",
+                textFont,
+                [x0, y0, x1, y1],
+                FONTSIZE,
+                opt,
+            )
+
+            # ----------add object size----------
+            w_obj = x1 - x0
+            h_obj = y1 - y0
+            area_obj = w_obj * h_obj
+            area_obj_all.append(area_obj)
+
+    # ------------JSON generate------------
+    det_json = export_json(results, img.size)[0]  # Detection information
+    det_json_format = json.dumps(det_json, sort_keys=False, indent=4, separators=(",", ":"),
+                                 ensure_ascii=False)  # JSON formatting
+
+    if "json" not in opt:
+        det_json = None
+
+    # -------PDF generate-------
+    report = "./Det_Report.pdf"
+    if "pdf" in opt:
+        pdf_generate(f"{det_json_format}", report, GYD_VERSION)
+    else:
+        report = None
+
+    # --------------object size compute--------------
+    for i in range(len(area_obj_all)):
+        if (0 < area_obj_all[i] <= 32 ** 2):
+            s_obj = s_obj + 1
+        elif (32 ** 2 < area_obj_all[i] <= 96 ** 2):
+            m_obj = m_obj + 1
+        elif (area_obj_all[i] > 96 ** 2):
+            l_obj = l_obj + 1
+
+    sml_obj_total = s_obj + m_obj + l_obj
+
+    objSize_dict = {obj_style[i]: [s_obj, m_obj, l_obj][i] / sml_obj_total for i in range(3)}
+
+    # ------------cls stat------------
+    clsRatio_dict = {}
+    clsDet_dict = Counter(cls_det_stat)
+    clsDet_dict_sum = sum(clsDet_dict.values())
+
+    for k, v in clsDet_dict.items():
+        clsRatio_dict[k] = v / clsDet_dict_sum
+
+    return det_img, objSize_dict, clsRatio_dict, det_json, report, dataframe
+
+
+# YOLOv5 video detection function
+def yolo_det_video(video, device, model_name, infer_size, conf, iou, max_num, model_cls, opt):
+
+    global model, model_name_tmp, device_tmp
+
+    os.system("""
+        if [ -e './output.mp4' ]; then
+        rm ./output.mp4
+        fi
+        """)
+
+    if model_name_tmp != model_name:
+        # Model judgment to avoid repeated loading
+        model_name_tmp = model_name
+        model = model_loading(model_name_tmp, device)
+    elif device_tmp != device:
+        device_tmp = device
+        model = model_loading(model_name_tmp, device)
+
+    # -------------Model tuning -------------
+    model.conf = conf  # NMS confidence threshold
+    model.iou = iou  # NMS IOU threshold
+    model.max_det = int(max_num)  # Maximum number of detection frames
+    model.classes = model_cls  # model classes
+
+    # ----------------Load fonts----------------
+    yaml_index = cls_name.index(".yaml")
+    cls_name_lang = cls_name[yaml_index - 2:yaml_index]
+
+    if cls_name_lang == "zh":
+        # Chinese
+        textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/SimSun.ttf"), size=FONTSIZE)
+    elif cls_name_lang in ["en", "ru", "es", "ar"]:
+        # English, Russian, Spanish, Arabic
+        textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/TimesNewRoman.ttf"), size=FONTSIZE)
+    elif cls_name_lang == "ko":
+        # Korean
+        textFont = ImageFont.truetype(str(f"{ROOT_PATH}/fonts/malgun.ttf"), size=FONTSIZE)
+
+    # video->frame
+    gc.collect()
+    output_video_path = "./output.avi"
+    cap = cv2.VideoCapture(video)
+    fourcc = cv2.VideoWriter_fourcc(*"I420")  # encoder
+
+    out = cv2.VideoWriter(output_video_path, fourcc, 30.0, (int(cap.get(3)), int(cap.get(4))))
+    while cap.isOpened():
+        ret, frame = cap.read()
+        # Determine empty frame
+        if not ret:
+            break
+
+        frame2 = frame.copy()
+        results = model(frame2, size=infer_size)  # detection
+        h, w, _ = frame.shape  # frame size
+        img_size = (w, h)  # frame size
+
+        for result in results.xyxyn:
+            for i in range(len(result)):
+                id = int(i)  # instance ID
+                obj_cls_index = int(result[i][5])  # category index
+                obj_cls = model_cls_name_cp[obj_cls_index]  # category
+
+                # ------------ border coordinates ------------
+                x0 = float(result[i][:4].tolist()[0])
+                y0 = float(result[i][:4].tolist()[1])
+                x1 = float(result[i][:4].tolist()[2])
+                y1 = float(result[i][:4].tolist()[3])
+
+                # ------------ Actual coordinates of the border ------------
+                x0 = int(img_size[0] * x0)
+                y0 = int(img_size[1] * y0)
+                x1 = int(img_size[0] * x1)
+                y1 = int(img_size[1] * y1)
+
+                conf = float(result[i][4])  # confidence
+                # fps = f"{(1000 / float(results.t[1])):.2f}" # FPS
+
+                frame = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
+                frame = pil_draw(
+                    frame,
+                    f"{id}-{obj_cls}:{conf:.2f}",
+                    textFont,
+                    [x0, y0, x1, y1],
+                    FONTSIZE,
+                    opt,
+                )
+
+                frame = cv2.cvtColor(np.asarray(frame), cv2.COLOR_RGB2BGR)
+
+            # frame->video
+            out.write(frame)
+    out.release()
+    cap.release()
+    cv2.destroyAllWindows()
+
+    return output_video_path
+
+
+def main(args):
+    gr.close_all()
+
+    global model, model_cls_name_cp, cls_name
+
+    source = args.source
+    source_video = args.source_video
+    img_tool = args.img_tool
+    nms_conf = args.nms_conf
+    nms_iou = args.nms_iou
+    model_name = args.model_name
+    model_cfg = args.model_cfg
+    cls_name = args.cls_name
+    device = args.device
+    inference_size = args.inference_size
+    max_detnum = args.max_detnum
+    slider_step = args.slider_step
+    is_login = args.is_login
+    usr_pwd = args.usr_pwd
+    is_share = args.is_share
+
+    is_fonts(f"{ROOT_PATH}/fonts")  # Check font files
+
+    # model loading
+    model = model_loading(model_name, device)
+
+    model_names = yaml_csv(model_cfg, "model_names")  # model names
+    model_cls_name = yaml_csv(cls_name, "model_cls_name")  # class name
+
+    model_cls_name_cp = model_cls_name.copy()  # class name
+
+    # ------------------- Input Components -------------------
+    inputs_img = gr.Image(image_mode="RGB", source=source, tool=img_tool, type="pil", label="original image")
+    inputs_device01 = gr.Radio(choices=["cuda:0", "cpu"], value=device, label="device")
+    inputs_model01 = gr.Dropdown(choices=model_names, value=model_name, type="value", label="model")
+    inputs_size01 = gr.Radio(choices=[320, 640, 1280], value=inference_size, label="inference size")
+    input_conf01 = gr.Slider(0, 1, step=slider_step, value=nms_conf, label="confidence threshold")
+    inputs_iou01 = gr.Slider(0, 1, step=slider_step, value=nms_iou, label="IoU threshold")
+    inputs_maxnum01 = gr.Number(value=max_detnum, label="Maximum number of detections")
+    inputs_clsName01 = gr.CheckboxGroup(choices=model_cls_name, value=model_cls_name, type="index", label="category")
+    inputs_opt01 = gr.CheckboxGroup(choices=["label", "pdf", "json"],
+                                    value=["label", "pdf"],
+                                    type="value",
+                                    label="operate")
+
+    # ------------------- Input Components -------------------
+    inputs_video = gr.Video(format="mp4", source=source_video, label="original video")  # webcam
+    inputs_device02 = gr.Radio(choices=["cuda:0", "cpu"], value=device, label="device")
+    inputs_model02 = gr.Dropdown(choices=model_names, value=model_name, type="value", label="model")
+    inputs_size02 = gr.Radio(choices=[320, 640, 1280], value=inference_size, label="inference size")
+    input_conf02 = gr.Slider(0, 1, step=slider_step, value=nms_conf, label="confidence threshold")
+    inputs_iou02 = gr.Slider(0, 1, step=slider_step, value=nms_iou, label="IoU threshold")
+    inputs_maxnum02 = gr.Number(value=max_detnum, label="Maximum number of detections")
+    inputs_clsName02 = gr.CheckboxGroup(choices=model_cls_name, value=model_cls_name, type="index", label="category")
+    inputs_opt02 = gr.CheckboxGroup(choices=["label"], value=["label"], type="value", label="operate")
+
+    # Input parameters
+    inputs_img_list = [
+        inputs_img,  # input image
+        inputs_device01,  # device
+        inputs_model01,  # model
+        inputs_size01,  # inference size
+        input_conf01,  # confidence threshold
+        inputs_iou01,  # IoU threshold
+        inputs_maxnum01,  # maximum number of detections
+        inputs_clsName01,  # category
+        inputs_opt01,  # detect operations
+    ]
+
+    inputs_video_list = [
+        inputs_video,  # input image
+        inputs_device02,  # device
+        inputs_model02,  # model
+        inputs_size02,  # inference size
+        input_conf02,  # confidence threshold
+        inputs_iou02,  # IoU threshold
+        inputs_maxnum02,  # maximum number of detections
+        inputs_clsName02,  # category
+        inputs_opt02,  # detect operation
+    ]
+
+    # -------------------output component-------------------
+    outputs_img = gr.Image(type="pil", label="Detection image")
+    outputs_json = gr.JSON(label="Detection information")
+    outputs_pdf = gr.File(label="Download test report")
+    outputs_df = gr.Dataframe(max_rows=5,
+                              overflow_row_behaviour="paginate",
+                              type="pandas",
+                              label="List of detection information")
+    outputs_objSize = gr.Label(label="Object size ratio statistics")
+    outputs_clsSize = gr.Label(label="Category detection proportion statistics")
+
+    # -------------------output component-------------------
+    outputs_video = gr.Video(format='mp4', label="Detection video")
+
+    # output parameters
+    outputs_img_list = [outputs_img, outputs_objSize, outputs_clsSize, outputs_json, outputs_pdf, outputs_df]
+    outputs_video_list = [outputs_video]
+
+    # title
+    title = "Gradio YOLOv5 Det v0.4"
+
+    # describe
+    description = "<div align='center'>Customizable target detection model, easy to install, easy to use</div>"
+    # article="https://gitee.com/CV_Lab/gradio_yolov5_det"
+
+    # example image
+    examples = [
+        [
+            "./img_example/bus.jpg",
+            "cpu",
+            "yolov5s",
+            640,
+            0.6,
+            0.5,
+            10,
+            ["person", "bus"],
+            ["label", "pdf"],],
+        [
+            "./img_example/giraffe.jpg",
+            "cpu",
+            "yolov5l",
+            320,
+            0.5,
+            0.45,
+            12,
+            ["giraffe"],
+            ["label", "pdf"],],
+        [
+            "./img_example/zidane.jpg",
+            "cpu",
+            "yolov5m",
+            640,
+            0.25,
+            0.5,
+            15,
+            ["person", "tie"],
+            ["pdf", "json"],],
+        [
+            "./img_example/Millenial-at-work.jpg",
+            "cpu",
+            "yolov5s6",
+            1280,
+            0.5,
+            0.5,
+            20,
+            ["person", "chair", "cup", "laptop"],
+            ["label", "pdf"],],]
+
+    # interface
+    gyd_img = gr.Interface(
+        fn=yolo_det_img,
+        inputs=inputs_img_list,
+        outputs=outputs_img_list,
+        title=title,
+        description=description,
+        # article=article,
+        # examples=examples,
+        # theme="seafoam",
+        # live=True, # Change output in real time
+        flagging_dir="run",  # output directory
+        # allow_flagging="manual",
+        # flagging_options=["good", "generally", "bad"],
+    )
+
+    gyd_video = gr.Interface(
+        # fn=yolo_det_video_test,
+        fn=yolo_det_video,
+        inputs=inputs_video_list,
+        outputs=outputs_video_list,
+        title=title,
+        description=description,
+        # article=article,
+        # examples=examples,
+        # theme="seafoam",
+        # live=True, # Change output in real time
+        flagging_dir="run",  # output directory
+        allow_flagging="never",
+        # flagging_options=["good", "generally", "bad"],
+    )
+
+    gyd = gr.TabbedInterface(interface_list=[gyd_img, gyd_video], tab_names=["Image Mode", "Video Mode"])
+
+    if not is_login:
+        gyd.launch(
+            inbrowser=True,  # Automatically open default browser
+            show_tips=True,  # Automatically display the latest features of gradio
+            share=is_share,  # Project sharing, other devices can access
+            favicon_path="./icon/logo.ico",  # web icon
+            show_error=True,  # Display error message in browser console
+            quiet=True,  # Suppress most print statements
+        )
+    else:
+        gyd.launch(
+            inbrowser=True,  # Automatically open default browser
+            show_tips=True,  # Automatically display the latest features of gradio
+            auth=usr_pwd,  # login interface
+            share=is_share,  # Project sharing, other devices can access
+            favicon_path="./icon/logo.ico",  # web icon
+            show_error=True,  # Display error message in browser console
+            quiet=True,  # Suppress most print statements
+        )
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    main(args)

cls_name/cls_name.csv

@@ -0,0 +1,80 @@
+人
+自行车
+汽车
+摩托车
+飞机
+公交车
+火车
+卡车
+船
+红绿灯
+消防栓
+停止标志
+停车收费表
+长凳
+鸟
+猫
+狗
+马
+羊
+牛
+象
+熊
+斑马
+长颈鹿
+背包
+雨伞
+手提包
+领带
+手提箱
+飞盘
+滑雪板
+单板滑雪
+运动球
+风筝
+棒球棒
+棒球手套
+滑板
+冲浪板
+网球拍
+瓶子
+红酒杯
+杯子
+叉子
+刀
+勺
+碗
+香蕉
+苹果
+三明治
+橙子
+西兰花
+胡萝卜
+热狗
+比萨
+甜甜圈
+蛋糕
+椅子
+长椅
+盆栽
+床
+餐桌
+马桶
+电视
+笔记本电脑
+鼠标
+遥控器
+键盘
+手机
+微波炉
+烤箱
+烤面包机
+洗碗槽
+冰箱
+书
+时钟
+花瓶
+剪刀
+泰迪熊
+吹风机
+牙刷

cls_name/cls_name.yaml

@@ -0,0 +1,7 @@
+model_cls_name: ['人', '自行车', '汽车', '摩托车', '飞机', '公交车', '火车', '卡车', '船', '红绿灯', '消防栓', '停止标志',
+                '停车收费表', '长凳', '鸟', '猫', '狗', '马', '羊', '牛', '象', '熊', '斑马', '长颈鹿', '背包', '雨伞', '手提包', '领带',
+                '手提箱', '飞盘', '滑雪板', '单板滑雪', '运动球', '风筝', '棒球棒', '棒球手套', '滑板', '冲浪板', '网球拍', '瓶子', '红酒杯',
+                '杯子', '叉子', '刀', '勺', '碗', '香蕉', '苹果', '三明治', '橙子', '西兰花', '胡萝卜', '热狗', '比萨', '甜甜圈', '蛋糕',
+                '椅子', '长椅', '盆栽', '床', '餐桌', '马桶', '电视', '笔记本电脑', '鼠标', '遥控器', '键盘', '手机', '微波炉', '烤箱',
+                '烤面包机', '洗碗槽', '冰箱', '书', '时钟', '花瓶', '剪刀', '泰迪熊', '吹风机', '牙刷'
+            ]

cls_name/cls_name_ar.yaml

@@ -0,0 +1,9 @@
+model_cls_name: [" الناس " , " الدراجات " , " السيارات " , " الدراجات النارية " , " الطائرات " , " الحافلات " , " القطارات " , " الشاحنات " , " السفن " , " إشارات المرور " ,
+" صنبور " , " علامة " , " موقف سيارات " , " الجدول " , " مقعد " , " الطيور " , " القط " , " الكلب " , " الحصان " , " الأغنام " , " الثور " , " الفيل " ,
+" الدب " , " حمار وحشي " , " الزرافة " , " حقيبة " , " مظلة " , " حقيبة يد " , " ربطة عنق " , " حقيبة " , " الفريسبي " , " الزلاجات " , " الزلاجات " ,
+" الكرة الرياضية " , " طائرة ورقية " , " مضرب بيسبول " , " قفازات البيسبول " , " لوح التزلج " , " ركوب الأمواج " , " مضرب تنس " , " زجاجة " ,
+" كأس " , " كأس " , " شوكة " , " سكين " , " ملعقة " , " وعاء " , " الموز " , " التفاح " , " ساندويتش " , " البرتقال " , " القرنبيط " ,
+" الجزر " , " الكلاب الساخنة " , " البيتزا " , " دونات " , " كعكة " , " كرسي " , " أريكة " , " بوعاء " , " السرير " , " طاولة الطعام " , " المرحاض " ,
+التلفزيون , الكمبيوتر المحمول , الفأرة , وحدة تحكم عن بعد , لوحة المفاتيح , الهاتف المحمول , فرن الميكروويف , محمصة خبز كهربائية , بالوعة , ثلاجة ,
+" كتاب " , " ساعة " , " زهرية " , " مقص " , " دمية دب " , " مجفف الشعر " , " فرشاة الأسنان "
+]

cls_name/cls_name_en.yaml

@@ -0,0 +1,9 @@
+model_cls_name: ['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'
+]

cls_name/cls_name_es.yaml

@@ -0,0 +1,9 @@
+model_cls_name: ['persona', 'bicicleta', 'coche', 'motocicleta', 'avión', 'autobús', 'tren', 'camión', 'barco', 'semáforo',
+     'boca de incendios', 'señal de alto', 'parquímetro', 'banco', 'pájaro', 'gato', 'perro', 'caballo', 'oveja', 'vaca', 'elefante',
+     'oso', 'cebra', 'jirafa', 'mochila', 'paraguas', 'bolso', 'corbata', 'maleta', 'frisbee', 'esquís', 'snowboard',
+     'pelota deportiva', 'cometa', 'bate de béisbol', 'guante de béisbol', 'monopatín', 'tabla de surf', 'raqueta de tenis', 'botella',
+     'copa de vino', 'taza', 'tenedor', 'cuchillo', 'cuchara', 'tazón', 'plátano', 'manzana', 'sándwich', 'naranja', 'brócoli',
+     'zanahoria', 'perrito caliente', 'pizza', 'rosquilla', 'pastel', 'silla', 'sofá', 'planta en maceta', 'cama', 'mesa de comedor', 'inodoro',
+     'tv', 'laptop', 'ratón', 'control remoto', 'teclado', 'celular', 'microondas', 'horno', 'tostadora', 'fregadero', 'nevera',
+     'libro', 'reloj', 'jarrón', 'tijeras', 'oso de peluche', 'secador de pelo', 'cepillo de dientes'
+]

cls_name/cls_name_ko.yaml

@@ -0,0 +1,9 @@
+model_cls_name: ['사람', '자전거', '자동차', '오토바이', '비행기', '버스', '기차', '트럭', '보트', '신호등',
+     '소화전', '정지 신호', '주차 미터기', '벤치', '새', '고양이', '개', '말', '양', '소', '코끼리',
+     '곰', '얼룩말', '기린', '배낭', '우산', '핸드백', '타이', '여행가방', '프리스비', '스키', '스노우보드',
+     '스포츠 공', '연', '야구 방망이', '야구 글러브', '스케이트보드', '서프보드', '테니스 라켓', '병',
+     '와인잔', '컵', '포크', '나이프', '숟가락', '그릇', '바나나', '사과', '샌드위치', '오렌지', '브로콜리',
+     '당근', '핫도그', '피자', '도넛', '케이크', '의자', '소파', '화분', '침대', '식탁', '화장실',
+     'tv', '노트북', '마우스', '리모컨', '키보드', '휴대전화', '전자레인지', '오븐', '토스터', '싱크대', '냉장고',
+     '책', '시계', '꽃병', '가위', '테디베어', '드라이기', '칫솔'
+]

cls_name/cls_name_ru.yaml

@@ -0,0 +1,9 @@
+model_cls_name: ['человек', 'велосипед', 'автомобиль', 'мотоцикл', 'самолет', 'автобус', 'поезд', 'грузовик', 'лодка', 'светофор',
+     'пожарный гидрант', 'стоп', 'паркомат', 'скамейка', 'птица', 'кошка', 'собака', 'лошадь', 'овца', 'корова', 'слон',
+     'медведь', 'зебра', 'жираф', 'рюкзак', 'зонт', 'сумочка', 'галстук', 'чемодан', 'фрисби', 'лыжи', 'сноуборд',
+     'спортивный мяч', 'воздушный змей', 'бейсбольная бита', 'бейсбольная перчатка', 'скейтборд', 'доска для серфинга', 'теннисная ракетка', 'бутылка',
+     'бокал', 'чашка', 'вилка', 'нож', 'ложка', 'миска', 'банан', 'яблоко', 'бутерброд', 'апельсин', 'брокколи',
+     'морковь', 'хот-дог', 'пицца', 'пончик', 'торт', 'стул', 'диван', 'растение в горшке', 'кровать', 'обеденный стол', 'туалет',
+     'телевизор', 'ноутбук', 'мышь', 'пульт', 'клавиатура', 'мобильный телефон', 'микроволновая печь', 'духовка', 'тостер', 'раковина', 'холодильник',
+     'книга', 'часы', 'ваза', 'ножницы', 'плюшевый мишка', 'фен', 'зубная щетка'
+]

cls_name/cls_name_zh.yaml

@@ -0,0 +1,7 @@
+model_cls_name: ['人', '自行车', '汽车', '摩托车', '飞机', '公交车', '火车', '卡车', '船', '红绿灯', '消防栓', '停止标志',
+                '停车收费表', '长凳', '鸟', '猫', '狗', '马', '羊', '牛', '象', '熊', '斑马', '长颈鹿', '背包', '雨伞', '手提包', '领带',
+                '手提箱', '飞盘', '滑雪板', '单板滑雪', '运动球', '风筝', '棒球棒', '棒球手套', '滑板', '冲浪板', '网球拍', '瓶子', '红酒杯',
+                '杯子', '叉子', '刀', '勺', '碗', '香蕉', '苹果', '三明治', '橙子', '西兰花', '胡萝卜', '热狗', '比萨', '甜甜圈', '蛋糕',
+                '椅子', '长椅', '盆栽', '床', '餐桌', '马桶', '电视', '笔记本电脑', '鼠标', '遥控器', '键盘', '手机', '微波炉', '烤箱',
+                '烤面包机', '洗碗槽', '冰箱', '书', '时钟', '花瓶', '剪刀', '泰迪熊', '吹风机', '牙刷'
+            ]

model_config/model_name_p5_all.csv

@@ -0,0 +1,5 @@
+yolov5n
+yolov5s
+yolov5m
+yolov5l
+yolov5x

model_config/model_name_p5_all.yaml

@@ -0,0 +1 @@
+model_names: ["yolov5n", "yolov5s", "yolov5m", "yolov5l", "yolov5x"]

model_config/model_name_p5_n.csv

@@ -0,0 +1 @@
+yolov5n

model_config/model_name_p5_n.yaml

@@ -0,0 +1 @@
+model_names: ["yolov5n"]

model_config/model_name_p5_p6_all.yaml

@@ -0,0 +1 @@
+model_names: ["yolov5n", "yolov5s", "yolov5m", "yolov5l", "yolov5x", "yolov5n6", "yolov5s6", "yolov5m6", "yolov5l6", "yolov5x6"]

model_config/model_name_p6_all.csv

@@ -0,0 +1,5 @@
+yolov5n6
+yolov5s6
+yolov5m6
+yolov5l6
+yolov5x6

model_config/model_name_p6_all.yaml

@@ -0,0 +1 @@
+model_names: ["yolov5n6", "yolov5s6", "yolov5m6", "yolov5l6", "yolov5x6"]

model_download/yolov5_model_p5_all.sh

@@ -0,0 +1,8 @@
+cd ./yolov5
+
+# 下载YOLOv5模型
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5n.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5m.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5l.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5x.pt

model_download/yolov5_model_p5_n.sh

@@ -0,0 +1,4 @@
+cd ./yolov5
+
+# 下载YOLOv5模型
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5n.pt

model_download/yolov5_model_p6_all.sh

@@ -0,0 +1,8 @@
+cd ./yolov5
+
+# 下载YOLOv5模型
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5n6.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5s6.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5m6.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5l6.pt
+wget -c -t 0 https://github.com/ultralytics/yolov5/releases/download/v6.1/yolov5x6.pt

requirements.txt

@@ -0,0 +1,38 @@
+# Base ----------------------------------------
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python-headless>=4.5.5.64
+Pillow>=7.1.2
+PyYAML>=5.3.1
+requests>=2.23.0
+scipy>=1.4.1
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.41.0
+wget>=3.2
+rich>=12.2.0
+fpdf>=1.7.2
+
+# Logging -------------------------------------
+tensorboard>=2.4.1
+# wandb
+
+# Plotting ------------------------------------
+pandas>=1.1.4
+seaborn>=0.11.0
+
+# Export --------------------------------------
+# coremltools>=4.1  # CoreML export
+# onnx>=1.9.0  # ONNX export
+# onnx-simplifier>=0.3.6  # ONNX simplifier
+# scikit-learn==0.19.2  # CoreML quantization
+# tensorflow>=2.4.1  # TFLite export
+# tensorflowjs>=3.9.0  # TF.js export
+# openvino-dev  # OpenVINO export
+
+# Extras --------------------------------------
+# albumentations>=1.0.3
+# Cython  # for pycocotools https://github.com/cocodataset/cocoapi/issues/172
+# pycocotools>=2.0  # COCO mAP
+# roboflow
+thop  # FLOPs computation

util/fonts_opt.py

@@ -0,0 +1,69 @@
+# font management
+# author: Zeng Yifu（曾逸夫）
+# creation time: 2022-05-01
+# email: [email protected]
+# project homepage: https://gitee.com/CV_Lab/gradio_yolov5_det
+
+import os
+import sys
+from pathlib import Path
+
+import wget
+from rich.console import Console
+
+ROOT_PATH = sys.path[0] # Project root directory
+
+# Chinese, English, Russian, Spanish, Arabic, Korean
+fonts_list = ["SimSun.ttf", "TimesNewRoman.ttf", "malgun.ttf"] # font list
+fonts_suffix = ["ttc", "ttf", "otf"] # font suffix
+
+data_url_dict = {
+    "SimSun.ttf": "https://gitee.com/CV_Lab/gradio_yolov5_det/attach_files/1053539/download/SimSun.ttf",
+    "TimesNewRoman.ttf": "https://gitee.com/CV_Lab/gradio_yolov5_det/attach_files/1053537/download/TimesNewRoman.ttf",
+    "malgun.ttf": "https://gitee.com/CV_Lab/gradio_yolov5_det/attach_files/1053538/download/malgun.ttf",}
+
+console = Console()
+
+
+# create font library
+def add_fronts(font_diff):
+
+    global font_name
+
+    for k, v in data_url_dict.items():
+        if k in font_diff:
+            font_name = v.split("/")[-1] # font name
+            Path(f"{ROOT_PATH}/fonts").mkdir(parents=True, exist_ok=True) # Create a directory
+
+            file_path = f"{ROOT_PATH}/fonts/{font_name}" # font path
+
+            try:
+                # Download font file
+                wget.download(v, file_path)
+            except Exception as e:
+                print("Path error! Program ended!")
+                print(e)
+                sys.exit()
+            else:
+                print()
+                console.print(f"{font_name} [bold green]font file download complete![/bold green] has been saved to: {file_path}")
+
+
+# Determine the font file
+def is_fonts(fonts_dir):
+    if os.path.isdir(fonts_dir):
+        # if the font library exists
+        f_list = os.listdir(fonts_dir) # local font library
+
+        font_diff = list(set(fonts_list).difference(set(f_list)))
+
+        if font_diff != []:
+            # font does not exist
+            console.print("[bold red] font does not exist, loading...[/bold red]")
+            add_fronts(font_diff) # Create a font library
+        else:
+            console.print(f"{fonts_list}[bold green]font already exists![/bold green]")
+    else:
+        # The font library does not exist, create a font library
+        console.print("[bold red]font library does not exist, creating...[/bold red]")
+        add_fronts(fonts_list) # Create a font library

util/pdf_opt.py

@@ -0,0 +1,78 @@
+# PDF management
+# author: Zeng Yifu
+# creation time: 2022-05-05
+
+from fpdf import FPDF
+
+
+# PDF generation class
+class PDF(FPDF):
+    # Reference: https://pyfpdf.readthedocs.io/en/latest/Tutorial/index.html
+    def header(self):
+        # Set Chinese font
+        self.add_font("SimSun", "", "./fonts/SimSun.ttf", uni=True)
+        self.set_font("SimSun", "", 16)
+        # Calculate width of title and position
+        w = self.get_string_width(title) + 6
+        self.set_x((210 - w) / 2)
+        # Colors of frame, background and text
+        self.set_draw_color(255, 255, 255)
+        self.set_fill_color(255, 255, 255)
+        self.set_text_color(0, 0, 0)
+        # Thickness of frame (1 mm)
+        # self.set_line_width(1)
+        # Title
+        self.cell(w, 9, title, 1, 1, "C", 1)
+        # Line break
+        self.ln(10)
+
+    def footer(self):
+        # Position at 1.5 cm from bottom
+        self.set_y(-15)
+        # Set Chinese font
+        self.add_font("SimSun", "", "./fonts/SimSun.ttf", uni=True)
+        self.set_font("SimSun", "", 12)
+        # Text color in gray
+        self.set_text_color(128)
+        # Page number
+        self.cell(0, 10, "Page " + str(self.page_no()), 0, 0, "C")
+
+    def chapter_title(self, num, label):
+        # Set Chinese font
+        self.add_font("SimSun", "", "./fonts/SimSun.ttf", uni=True)
+        self.set_font("SimSun", "", 12)
+        # Background color
+        self.set_fill_color(200, 220, 255)
+        # Title
+        # self.cell(0, 6, 'Chapter %d : %s' % (num, label), 0, 1, 'L', 1)
+        self.cell(0, 6, "Test result:", 0, 1, "L", 1)
+        # Line break
+        self.ln(4)
+
+    def chapter_body(self, name):
+
+        # Set Chinese font
+        self.add_font("SimSun", "", "./fonts/SimSun.ttf", uni=True)
+        self.set_font("SimSun", "", 12)
+        # Output justified text
+        self.multi_cell(0, 5, name)
+        # Line break
+        self.ln()
+        self.cell(0, 5, "--------------------------------------")
+
+    def print_chapter(self, num, title, name):
+        self.add_page()
+        self.chapter_title(num, title)
+        self.chapter_body(name)
+
+
+# pdf generation function
+def pdf_generate(input_file, output_file, title_):
+    global title
+
+    title = title_
+    pdf = PDF()
+    pdf.set_title(title)
+    pdf.set_author("Zeng Yifu")
+    pdf.print_chapter(1, "A RUNAWAY REEF", input_file)
+    pdf.output(output_file)