因实验需要将将visdrone2019数据集转换为COCO格式，但是在网上找了很多代码都会出各样的问题，这是目前找到的可以正确运行的代码

网上下载的压缩包进行解压后会出现如下的目录

转换代码如下

""""将visdrone数据集转换为COCO格式"""
import os
import cv2
from PIL import Image
from tqdm import tqdm
import json
def convert_to_cocodetection(dir, output_dir):
    # 数据目录
    train_dir = os.path.join(dir, "VisDrone2019-DET-train")
    val_dir = os.path.join(dir, "VisDrone2019-DET-val")
    test_dir = os.path.join(dir, "VisDrone2019-DET-test-dev")
    # 数据标注目录
    train_annotations = os.path.join(train_dir, "annotations")
    val_annotations = os.path.join(val_dir, "annotations")
    test_annotations = os.path.join(test_dir, "annotations")
    # 数据影像目录
    train_images = os.path.join(train_dir, "images")
    val_images = os.path.join(val_dir, "images")
    test_images = os.path.join(test_dir, "images")

    id_num = 0

    categories = [

        {"id": 0, "name": "pedestrian"},
        {"id": 1, "name": "people"},
        {"id": 2, "name": "bicycle"},
        {"id": 3, "name": "car"},
        {"id": 4, "name": "van"},
        {"id": 5, "name": "truck"},
        {"id": 6, "name": "tricycle"},
        {"id": 7, "name": "awning-tricycle"},
        {"id": 8, "name": "bus"},
        {"id": 9, "name": "motor"},

    ]

    for mode in ["test"]:
    #for mode in ["train", "val","test"]:
        images = []
        annotations = []

        print(f"start loading {mode} data...")
        if mode == "train":
            set = os.listdir(train_annotations)
            annotations_path = train_annotations
            images_path = train_images
        elif mode == "test":
            set = os.listdir(test_annotations)
            annotations_path = test_annotations
            images_path = test_images
        else:
            set = os.listdir(val_annotations)
            annotations_path = val_annotations
            images_path = val_images

        for i in tqdm(set):
            f = open(annotations_path + "/" + i, "r")
            name = i.replace(".txt", "")

            # images属性
            image = {}
            image_file_path = images_path + os.sep + name + ".jpg"
            print(image_file_path)

            img_size = Image.open((images_path + os.sep + name + ".jpg")).size
            width, height = img_size
            # height, width = cv2.imread(images_path + os.sep + name + ".jpg").shape[:2]
            file_name = name + ".jpg"
            image["id"] = name
            image["height"] = height
            image["width"] = width
            image["file_name"] = file_name
            images.append(image)

            for line in f.readlines():
                # annotation属性
                annotation = {}
                line = line.replace("\n", "")
                if line.endswith(","):  # filter data
                    line = line.rstrip(",")
                line_list = [int(i) for i in line.split(",")]
                if (line_list[4] == 1 and 0 < line_list[5] < 11):  # class 0 为 ignore region class 11 为others  目标检测任务中忽略
                    bbox_xywh = [line_list[0], line_list[1], line_list[2], line_list[3]]
                    annotation["id"] = id_num
                    annotation["image_id"] = name
                    annotation["category_id"] = int(line_list[5] - 1)  # yolo检测结果标签从0开始 为了与结果对齐 -1
                    annotation["area"] = bbox_xywh[2] * bbox_xywh[3]
                    # annotation["score"] = line_list[4]
                    annotation["bbox"] = bbox_xywh
                    annotation["iscrowd"] = 0
                    id_num += 1
                    annotations.append(annotation)
        dataset_dict = {}
        dataset_dict = {}
        dataset_dict["images"] = images
        dataset_dict["annotations"] = annotations
        dataset_dict["categories"] = categories
        json_str = json.dumps(dataset_dict)
        with open(f'{output_dir}/VisDrone2019-DET_{mode}_coco_start.json', 'w') as json_file:
            json_file.write(json_str)
    print("json file write done...")


def get_test_namelist(dir, out_dir):
    full_path = out_dir + "/" + "test.txt"
    file = open(full_path, 'w')
    for name in tqdm(os.listdir(dir)):
        name = name.replace(".txt", "")
        file.write(name + "\n")
    file.close()
    return None


def centerxywh_to_xyxy(boxes):
    """
    args:
        boxes:list of center_x,center_y,width,height,
    return:
        boxes:list of x,y,x,y,cooresponding to top left and bottom right
    """
    x_top_left = boxes[0] - boxes[2] / 2
    y_top_left = boxes[1] - boxes[3] / 2
    x_bottom_right = boxes[0] + boxes[2] / 2
    y_bottom_right = boxes[1] + boxes[3] / 2
    return [x_top_left, y_top_left, x_bottom_right, y_bottom_right]


def centerxywh_to_topleftxywh(boxes):
    """
    args:
        boxes:list of center_x,center_y,width,height,
    return:
        boxes:list of x,y,x,y,cooresponding to top left and bottom right
    """
    x_top_left = boxes[0] - boxes[2] / 2
    y_top_left = boxes[1] - boxes[3] / 2
    width = boxes[2]
    height = boxes[3]
    return [x_top_left, y_top_left, width, height]


def clamp(coord, width, height):
    if coord[0] < 0:
        coord[0] = 0
    if coord[1] < 0:
        coord[1] = 0
    if coord[2] > width:
        coord[2] = width
    if coord[3] > height:
        coord[3] = height
    return coord


if __name__ == '__main__':
    # 第一个参数输入上面目录的路径，第二个参数是要输出的路径
    convert_to_cocodetection("D:\yolov5\datasets\VisDrone","D:\yolov5\datasets\VisDrone")

如何获得获得大中小目标的AP和AR指标（visdrone2019数据集）？

1,需要先在环境中安装pycocotools

pip install pycocotools

2,修改文件

修改val文件
 1.'--save-json' 添加 default=True 
parser.add_argument('--save-json', default=True, action='store_true', help='save a COCO-JSON results    file')
  
 2.注释下句    # opt.save_json |= opt.data.endswith('coco.yaml')
   

经过上述代码后可在runs\val\exp#找到生成的.json文件best_predictions.json

3利用上述转换代码获得visdrone2019数据集的标注文件.json文件形式

4运行下列代码可获得大中小目标的AP值

from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
import numpy as np
#import skimage.io as io
import pylab, json

if __name__ == "__main__":
    cocoGt = COCO(r"D:\datasets\VisDrone\annotations\VisDrone2019-DET_test_coco.json")  # 标注文件的路径及文件名，json文件形式
    cocoDt = cocoGt.loadRes(
        r"D:\yolo\runs\val\exp48\best_predictions.json")  # 自己的生成的结果的路径及文件名，json文件形式
    cocoEval = COCOeval(cocoGt, cocoDt, "bbox")
    cocoEval.evaluate()
    cocoEval.accumulate()
    cocoEval.summarize()

4结果如下所示