matplotlib>=3.2.2

numpy>=1.18.5

opencv-python>=4.1.2

pillow

PyYAML>=5.3

scipy>=1.4.1

tensorboard>=2.2

torch>=1.6.0

torchvision>=0.7.0

tqdm>=4.41.0

import os

import numpy as np

import json

from glob import glob

import cv2

from sklearn.model_selection import train_test_split

from os import getcwd
classes = ["aircraft", "oiltank"]

# 1.标签路径

labelme_path = "LabelmeData/"

isUseTest = True  # 是否创建test集

# 3.获取待处理文件

files = glob(labelme_path + "*.json")

files = [i.replace("\\", "/").split("/")[-1].split(".json")[0] for i in files]

print(files)

if isUseTest:

    trainval_files, test_files = train_test_split(files, test_size=0.1, random_state=55)

else:

    trainval_files = files

# split

train_files, val_files = train_test_split(trainval_files, test_size=0.1, random_state=55)
def convert(size, box):

    dw = 1. / (size[0])

    dh = 1. / (size[1])

    x = (box[0] + box[1]) / 2.0 - 1

    y = (box[2] + box[3]) / 2.0 - 1

    w = box[1] - box[0]

    h = box[3] - box[2]

    x = x * dw

    w = w * dw

    y = y * dh

    h = h * dh

    return (x, y, w, h)
wd = getcwd()

print(wd)
def ChangeToYolo5(files, txt_Name):

    if not os.path.exists('tmp/'):

        os.makedirs('tmp/')

    list_file = open('tmp/%s.txt' % (txt_Name), 'w')

    for json_file_ in files:

        json_filename = labelme_path + json_file_ + ".json"

        imagePath = labelme_path + json_file_ + ".jpg"

        list_file.write('%s/%s\n' % (wd, imagePath))

        out_file = open('%s/%s.txt' % (labelme_path, json_file_), 'w')

        json_file = json.load(open(json_filename, "r", encoding="utf-8"))

        height, width, channels = cv2.imread(labelme_path + json_file_ + ".jpg").shape

        for multi in json_file["shapes"]:

            points = np.array(multi["points"])

            xmin = min(points[:, 0]) if min(points[:, 0]) > 0 else 0

            xmax = max(points[:, 0]) if max(points[:, 0]) > 0 else 0

            ymin = min(points[:, 1]) if min(points[:, 1]) > 0 else 0

            ymax = max(points[:, 1]) if max(points[:, 1]) > 0 else 0

            label = multi["label"]

            if xmax <= xmin:

                pass

            elif ymax <= ymin:

                pass

            else:

                cls_id = classes.index(label)

                b = (float(xmin), float(xmax), float(ymin), float(ymax))

                bb = convert((width, height), b)

                out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

                print(json_filename, xmin, ymin, xmax, ymax, cls_id)

ChangeToYolo5(train_files, "train")

ChangeToYolo5(val_files, "val")

ChangeToYolo5(test_files, "test")

import shutil
import os

file_List = ["train", "val", "test"]
for file in file_List:
    if not os.path.exists('../VOC/images/%s' % file):
        os.makedirs('../VOC/images/%s' % file)
    if not os.path.exists('../VOC/labels/%s' % file):
        os.makedirs('../VOC/labels/%s' % file)
    print(os.path.exists('../tmp/%s.txt' % file))
    f = open('../tmp/%s.txt' % file, 'r')
    lines = f.readlines()
    for line in lines:
        print(line)
        line = "/".join(line.split('/')[-5:]).strip()
        shutil.copy(line, "../VOC/images/%s" % file)
        line = line.replace('JPEGImages', 'labels')
        line = line.replace('jpg', 'txt')
        shutil.copy(line, "../VOC/labels/%s/" % file)

打开voc.yaml文件，修改里面的配置参数

train: VOC/images/train/  # 训练集图片的路径

val: VOC/images/val/  # 验证集图片的路径

# number of classes

nc: 2 #检测的类别，本次数据集有两个类别所以写2
# class names

names: ["aircraft", "oiltank"]#类别的名称，和转换数据集时的list对应

cfg参数是YoloV5 模型的配置文件，模型的文件存放在models文件夹下面，按照需求填写不同的文件。

weights参数是YoloV5的预训练模型，和cfg对应，例：cfg配置的是yolov5s.yaml，weights就要配置yolov5s.pt

data是配置数据集的配置文件，我们选用的是voc.yaml，所以配置data/voc.yaml

修改上面三个参数就可以开始训练了，其他的参数根据自己的需求修改。修改后的参数配置如下：

parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')

parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml path')

parser.add_argument('--data', type=str, default='data/voc.yaml', help='data.yaml path')