yolov5、yolov7、yolov8实例分割训练自己的数据集

1 代码下载

yolov5实例分割代码：https://github.com/ultralytics/yolov5

链接：https://pan.baidu.com/s/1wu0Ig3LpvI2jsPy2BZ1QnQ?pwd=0dj5 
提取码：0dj5 
 yolov7实例分割代码：https://github.com/RizwanMunawar/yolov7-segmentation

链接：https://pan.baidu.com/s/1v5yr-MkeSolLl8IFormuOQ?pwd=qp6r 
提取码：qp6r 

 yolov8实例分割代码：https://github.com/ultralytics/ultralytics

链接：https://pan.baidu.com/s/1GpYHYjGyXysmqPPwMSb9VA?pwd=8j2j 
提取码：8j2j 
 

2 数据集转换格式

       对数据集进行转换和划分。注意：在数据标注的时候将图片和json文件放在不同的文件夹里。如下图所示，另外新建两个文件夹txt 和split。

2.1 将json格式转化为txt格式

新建json2txt.py,修改文件路径为自己的路径

# -*- coding: utf-8 -*-
import json
import os
import argparse
from tqdm import tqdm


def convert_label_json(json_dir, save_dir, classes):
    json_paths = os.listdir(json_dir)
    classes = classes.split(',')

    for json_path in tqdm(json_paths):
        # for json_path in json_paths:
        path = os.path.join(json_dir, json_path)
        with open(path, 'r') as load_f:
            json_dict = json.load(load_f)
        h, w = json_dict['imageHeight'], json_dict['imageWidth']

        # save txt path
        txt_path = os.path.join(save_dir, json_path.replace('json', 'txt'))
        txt_file = open(txt_path, 'w')

        for shape_dict in json_dict['shapes']:
            label = shape_dict['label']
            label_index = classes.index(label)
            points = shape_dict['points']

            points_nor_list = []

            for point in points:
                points_nor_list.append(point[0] / w)
                points_nor_list.append(point[1] / h)

            points_nor_list = list(map(lambda x: str(x), points_nor_list))
            points_nor_str = ' '.join(points_nor_list)

            label_str = str(label_index) + ' ' + points_nor_str + '\n'
            txt_file.writelines(label_str)


if __name__ == "__main__":
    """
    python json2txt_nomalize.py --json-dir my_datasets/color_rings/jsons --save-dir my_datasets/color_rings/txts --classes "cat,dogs"
    """
    parser = argparse.ArgumentParser(description='json convert to txt params')
    parser.add_argument('--json-dir', type=str, default='I:/fenge2v/peach json/json', help='json path dir')
    parser.add_argument('--save-dir', type=str, default='I:/fenge2v/peach json/txt', help='txt save dir')
    parser.add_argument('--classes', type=str, default='_background_,peach', help='classes')      #先填背景（_background_），后面才是你的目标标签
    args = parser.parse_args()
    json_dir = args.json_dir
    save_dir = args.save_dir
    classes = args.classes
    convert_label_json(json_dir, save_dir, classes)

2.2 数据划分

新建split.py,修改文件路径为自己的路径

# 将图片和标注数据按比例切分为 训练集和测试集
import shutil
import random
import os
import argparse


# 检查文件夹是否存在
def mkdir(path):
    if not os.path.exists(path):
        os.makedirs(path)


def main(image_dir, txt_dir, save_dir):
    # 创建文件夹
    mkdir(save_dir)
    images_dir = os.path.join(save_dir, 'images')
    labels_dir = os.path.join(save_dir, 'labels')

    img_train_path = os.path.join(images_dir, 'train')
    img_test_path = os.path.join(images_dir, 'test')
    img_val_path = os.path.join(images_dir, 'val')

    label_train_path = os.path.join(labels_dir, 'train')
    label_test_path = os.path.join(labels_dir, 'test')
    label_val_path = os.path.join(labels_dir, 'val')

    mkdir(images_dir);
    mkdir(labels_dir);
    mkdir(img_train_path);
    mkdir(img_test_path);
    mkdir(img_val_path);
    mkdir(label_train_path);
    mkdir(label_test_path);
    mkdir(label_val_path);

    # 数据集划分比例，训练集75%，验证集15%，测试集15%，按需修改
    train_percent = 0.8
    val_percent = 0.2
    # test_percent = 0.1

    total_txt = os.listdir(txt_dir)
    num_txt = len(total_txt)
    list_all_txt = range(num_txt)  # 范围 range(0, num)

    num_train = int(num_txt * train_percent)
    num_val = int(num_txt * val_percent)
    num_test = num_txt - num_train - num_val

    train = random.sample(list_all_txt, num_train)
    # 在全部数据集中取出train
    val_test = [i for i in list_all_txt if not i in train]
    # 再从val_test取出num_val个元素，val_test剩下的元素就是test
    val = random.sample(val_test, num_val)

    print("训练集数目：{}, 验证集数目：{},测试集数目：{}".format(len(train), len(val), len(val_test) - len(val)))
    for i in list_all_txt:
        name = total_txt[i][:-4]

        srcImage = os.path.join(image_dir, name + '.jpg')
        srcLabel = os.path.join(txt_dir, name + '.txt')

        if i in train:
            dst_train_Image = os.path.join(img_train_path, name + '.jpg')
            dst_train_Label = os.path.join(label_train_path, name + '.txt')
            shutil.copyfile(srcImage, dst_train_Image)
            shutil.copyfile(srcLabel, dst_train_Label)
        elif i in val:
            dst_val_Image = os.path.join(img_val_path, name + '.jpg')
            dst_val_Label = os.path.join(label_val_path, name + '.txt')
            shutil.copyfile(srcImage, dst_val_Image)
            shutil.copyfile(srcLabel, dst_val_Label)
        else:
            dst_test_Image = os.path.join(img_test_path, name + '.jpg')
            dst_test_Label = os.path.join(label_test_path, name + '.txt')
            shutil.copyfile(srcImage, dst_test_Image)
            shutil.copyfile(srcLabel, dst_test_Label)


if __name__ == '__main__':
    """
    python split_datasets.py --image-dir my_datasets/color_rings/imgs --txt-dir my_datasets/color_rings/txts --save-dir my_datasets/color_rings/train_data
    """
    parser = argparse.ArgumentParser(description='split datasets to train,val,test params')
    parser.add_argument('--image-dir', type=str, default='I:/fenge2v/peach json/images', help='image path dir')
    parser.add_argument('--txt-dir', type=str, default='I:/fenge2v/peach json/txt', help='txt path dir')
    parser.add_argument('--save-dir', default='I:/fenge2v/peach json/split', type=str, help='save dir')
    args = parser.parse_args()
    image_dir = args.image_dir
    txt_dir = args.txt_dir
    save_dir = args.save_dir

    main(image_dir, txt_dir, save_dir)

3 训练设置

3.1 新建seg.yaml文件

train: I:/ultralytics-main/data/split/images/train  # train images (relative to 'path') 128 images
val: I:/ultralytics-main/data/split/images/val  # val images (relative to 'path') 128 images
test: I:/ultralytics-main/data/split/images/test # test images (optional)
 
# Classes
names:
  0: _background_
  1: peach
 

3.2 训练参数设置开始训练

task: segment  # YOLO task, i.e. detect, segment, classify, pose
mode: train  # YOLO mode, i.e. train, val, predict, export, track, benchmark
 
# Train settings -------------------------------------------------------------------------------------------------------
model: yolov8s-seg.yaml  # path to model file, i.e. yolov8n.pt, yolov8n.yaml
#model:runs/detect/yolov8s/weights/best.pt
data: seg.yaml # path to data file, i.e. coco128.yaml
epochs: 10  # number of epochs to train for
patience: 50  # epochs to wait for no observable improvement for early stopping of training
batch: 16  # number of images per batch (-1 for AutoBatch)

开始训练