语义分割制作自己的数据集

1、修改D:\Anaconda3\Lib\site-packages\labelme\cli下的json_to_dataset.py.

import argparse
import json
import os
import os.path as osp
import warnings

import PIL.Image
import yaml

from labelme import utils
import base64


def main():
    warnings.warn("This script is aimed to demonstrate how to convert the\n"
                  "JSON file to a single image dataset, and not to handle\n"
                  "multiple JSON files to generate a real-use dataset.")
    parser = argparse.ArgumentParser()
    parser.add_argument('json_file')
    parser.add_argument('-o', '--out', default=None)
    args = parser.parse_args()

    json_file = args.json_file
    if args.out is None:
        out_dir = osp.basename(json_file).replace('.', '_')
        out_dir = osp.join(osp.dirname(json_file), out_dir)
    else:
        out_dir = args.out
    if not osp.exists(out_dir):
        os.mkdir(out_dir)

    count = os.listdir(json_file)
    for i in range(0, len(count)):
        path = os.path.join(json_file, count[i])
        if os.path.isfile(path):
            data = json.load(open(path))

            if data['imageData']:
                imageData = data['imageData']
            else:
                imagePath = os.path.join(os.path.dirname(path), data['imagePath'])
                with open(imagePath, 'rb') as f:
                    imageData = f.read()
                    imageData = base64.b64encode(imageData).decode('utf-8')
            img = utils.img_b64_to_arr(imageData)
            label_name_to_value = {'_background_': 0}
            for shape in data['shapes']:
                label_name = shape['label']
                if label_name in label_name_to_value:
                    label_value = label_name_to_value[label_name]
                else:
                    label_value = len(label_name_to_value)
                    label_name_to_value[label_name] = label_value

            # label_values must be dense
            label_values, label_names = [], []
            for ln, lv in sorted(label_name_to_value.items(), key=lambda x: x[1]):
                label_values.append(lv)
                label_names.append(ln)
            assert label_values == list(range(len(label_values)))

            lbl = utils.shapes_to_label(img.shape, data['shapes'], label_name_to_value)

            captions = ['{}: {}'.format(lv, ln)
                        for ln, lv in label_name_to_value.items()]
            lbl_viz = utils.draw_label(lbl, img, captions)

            out_dir = osp.basename(count[i]).replace('.', '_')
            out_dir = osp.join(osp.dirname(count[i]), out_dir)
            if not osp.exists(out_dir):
                os.mkdir(out_dir)

            PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png'))
            # PIL.Image.fromarray(lbl).save(osp.join(out_dir, 'label.png'))
            utils.lblsave(osp.join(out_dir, 'label.png'), lbl)
            PIL.Image.fromarray(lbl_viz).save(osp.join(out_dir, 'label_viz.png'))

            with open(osp.join(out_dir, 'label_names.txt'), 'w') as f:
                for lbl_name in label_names:
                    f.write(lbl_name + '\n')

            warnings.warn('info.yaml is being replaced by label_names.txt')
            info = dict(label_names=label_names)
            with open(osp.join(out_dir, 'info.yaml'), 'w') as f:
                yaml.safe_dump(info, f, default_flow_style=False)

            print('Saved to: %s' % out_dir)


if __name__ == '__main__':
    main()

2、将所有json文件放在一个文件夹中E:\oralcell\test327\json 进入环境D:\Anaconda3\Scripts 这个目录下有labelme_json_to_dataset.exe 执行

labelme_json_to_dataset.exe E:\oralcell\test327\json

生成的文件夹在D:\Anaconda3\Scripts中，将他们放在E:\oralcell\test327\package中

每个json文件生成一个json文件夹，文件夹中有五项，要用的是label.png。

 如果出错可能是labelme版本不对

pip install labelme==3.16.7

 3、将每个json文件夹中的label取出来放在一个文件夹中E:\oralcell\test327\png,并重命名为原图的名字。

# -*- coding: utf-8 -*-
import os
import numpy as np
import json
import shutil


def find_dir_path(path, keyword_name, dir_list):
    files = os.listdir(path)
    for file_name in files:
        file_path = os.path.join(path, file_name)
        if os.path.isdir(file_path) and keyword_name not in file_path:
            find_dir_path(file_path, keyword_name, dir_list)
        elif os.path.isdir(file_path) and keyword_name in file_path:
            dir_list.append(file_path)


all_result_path = []
src_path = r'E:\oralcell\test327\package'#json文件夹的目录
label_save_path = r'E:\oralcell\test327\png'#png存放的目录
find_dir_path(src_path, '_json', all_result_path)  # 找出所有带着关键词(_json)的所有目标文件夹
# print(all_result_path)


for dir_path in all_result_path:
    # print(dir_path)
    file_name = dir_path.split('\\')[-1]
    key_word = file_name[:-5]
    # print(key_word)
    label_file = dir_path + "\\" + "label.png"
    new_label_save_path = label_save_path + "\\" + key_word + ".png"  # 复制生成的label.png到新的文件夹
    # print(new_label_save_path)
    shutil.copyfile(label_file, new_label_save_path)

4、改通道数

#批量图片转换：将RGB模式或P模式转换为L灰度拉伸值(可以自定义拉伸大小)
import numpy as np
from PIL import Image
import os
def Mode_P_to_L(img_file,stretch_value):
    """
将当前文件下的所有图片进行灰度值转换
    :param img_file: 图片文件存放目录
    :param stretch_value: 拉伸值， 图片原始值*stretch_value的结果理论上应该小于255
    """
    ##获取目录下所有文件名
    file_name_list = os.listdir(img_file)
    #遍历所有图片文件
    for file in file_name_list:
        #获取某个图片的全路径
        img_path = os.path.join(img_file, file)
        #打开图片
        image = Image.open(img_path)
        print(image.mode) #p模式
        img_arry = Image.fromarray(np.uint8(image))
        print(img_arry.mode)#L模式
        img_L = img_arry.convert("L")
        print(img_L.mode)
        #灰度拉伸
        img_end = Image.fromarray(np.uint8(img_L) * stretch_value)
        print(img_end.mode)
        #保存图片，并覆盖原图
        img_end.save(img_path)
        #提示
        print("完成对图片：",file," 的转换！")
    print("所有图片均已完成转换！")

#程序主入口
if __name__ == "__main__":
    # 需要转换的图片所在文件目录
    img_file = r"E:\oralcell\label327\png\segmentations"#自己输入上一步生成的png格式的标签图
    stretch_value = 1#自定义拉伸值，但要注意，图片标签值*stretch_value的结果理论上应该小于255
    Mode_P_to_L(img_file, stretch_value)#调用自定义的转换方法