FCN语义分割训练自己的数据（依据VOC2012数据集格式）（更）

旧城等待， 2022-04-23 02:52 396阅读 0赞

制作数据：

更新1：为了实现labelme批量json\_to\_dataset方法，特地修改d:\\users\\pangzhennan\\anaconda3\\envs\\labelme\\lib\\site-packages\\labelme\\cli\\json\_to\_dataset.py文件，原文件内容为：

import argparse
    import base64
    import json
    import os
    import os.path as osp
    import warnings
    
    import PIL.Image
    import yaml
    
    from labelme import utils
    
    
    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)
    
        data = json.load(open(json_file))
    
        if data['imageData']:
            imageData = data['imageData']
        else:
            imagePath = os.path.join(os.path.dirname(json_file), 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)
    
        PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png'))
        PIL.Image.fromarray(lbl).save(osp.join(out_dir, 'label.png'))
        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()

经过修改后变为：

# -*- coding: utf-8 -*-
    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
        # 该段代码在此处无意义
        '''
        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)
        '''
        list = os.listdir(json_file)
        for i in range(0, len(list)):
            path = os.path.join(json_file, list[i])
            if os.path.isfile(path):
                data = json.load(open(path))
                img = utils.img_b64_to_array(data['imageData'])
                lbl, lbl_names = utils.labelme_shapes_to_label(img.shape, data['shapes'])
    
                captions = ['%d: %s' % (l, name) for l, name in enumerate(lbl_names)]
                lbl_viz = utils.draw_label(lbl, img, captions)
                out_dir = osp.basename(list[i]).replace('.', '_')
                out_dir = osp.join(osp.dirname(list[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'))
                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 lbl_names:
                        f.write(lbl_name + '\n')
    
                warnings.warn('info.yaml is being replaced by label_names.txt')
                info = dict(label_names=lbl_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()

原来的操作处理方式为：

针对.json文件，在终端输入指令：labelme\_json\_to\_dataset 路径/文件名.json 即可生成dataset文件夹。  
现在的操作处理方式为：

把所有的待处理的json文件放在同一目录下，**cd 进入该目录，因为生成的结果会被自动保存在当前目录下，**

在labelme环境下，输入指令：labelme\_json\_to\_dataset 文件夹名，即可批量生成dataset文件夹。