paddledetection yolo格式数据转换_paddle segment 格式转换

1 json转单个xml

from pycocotools.coco import COCO
import numpy as np
import tqdm
import argparse


def arg_parser():
    parser = argparse.ArgumentParser('code by rbj')
    parser.add_argument('--annotation_path', type=str,
                        default='/data/m/365/365/annotations/train/zhiyuan_objv2_train.json')
    parser.add_argument('--save_base_path', type=str, default='/data/m/365/365/annotations/txt/')
    args = parser.parse_args()
    return args


if __name__ == '__main__':
    args = arg_parser()
    annotation_path = args.annotation_path
    save_base_path = args.save_base_path

    data_source = COCO(annotation_file=annotation_path)
    catIds = data_source.getCatIds()
    categories = data_source.loadCats(catIds)
    categories.sort(key=lambda x: x['id'])
    classes = {}
    coco_labels = {}
    coco_labels_inverse = {}
    for c in categories:
        coco_labels[len(classes)] = c['id']
        coco_labels_inverse[c['id']] = len(classes)
        classes[c['name']] = len(classes)

    img_ids = data_source.getImgIds()
    for index, img_id in tqdm.tqdm(enumerate(img_ids), desc='change .json file to .txt file'):
        img_info = data_source.loadImgs(img_id)[0]
        file_name = img_info['file_name'].split('.')[0]
        file_name = file_name[file_name.rfind('/') + 1:]
        # print(file_name)
        height = img_info['height']
        width = img_info['width']

        save_path = save_base_path + file_name + '.txt'
        print(save_path)
        with open(save_path, mode='w') as fp:
            annotation_id = data_source.getAnnIds(img_id)
            boxes = np.zeros((0, 5))
            if len(annotation_id) == 0:
                fp.write('')
                continue
            annotations = data_source.loadAnns(annotation_id)
            lines = ''
            for annotation in annotations:
                box = annotation['bbox']
                # some annotations have basically no width / height, skip them
                if box[2] < 1 or box[3] < 1:
                    continue
                #top_x,top_y,width,height---->cen_x,cen_y,width,height
                box[0] = round((box[0] + box[2] / 2) / width, 6)
                box[1] = round((box[1] + box[3] / 2) / height, 6)
                box[2] = round(box[2] / width, 6)
                box[3] = round(box[3] / height, 6)
                # label = coco_labels_inverse[annotation['category_id']]
                label = 1
                lines = lines + str(label)
                for i in box:
                    lines += ' ' + str(i)
                lines += '\n'
            fp.writelines(lines)
    print('finish')
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69

2 txt转xml

import os  
  
def txt_to_xml(txt_dir_path, xml_dir_path):  
    
    for filename in os.listdir(txt_dir_path):  
        if not filename.endswith('.txt'):  
            continue  
        
        img_name = os.path.splitext(filename)[0]  
       
        xml_file_path = os.path.join(xml_dir_path, img_name + '.xml')  
      
        with open(os.path.join(txt_dir_path, filename), 'r') as f:  
            lines = f.readlines()  
            
            xml_content = '<?xml version="1.0" encoding="UTF-8"?>\n'  
            xml_content += '<annotation>'  
            
            for line in lines:  
                 
                fields = line.strip().split(' ')  
                
                width = int(float(fields[0]))  
                height = int(float(fields[1]))  
                
                xml_line = '<object class="{}" x="{}" y="{}" width="{}" height="{}"></object>'.format(  
                    fields[2], fields[3], fields[4], width, height)  
               
                xml_content += xml_line  
          
            xml_content += '</annotation>'  
            with open(xml_file_path, 'w') as f:  
                f.write(xml_content)  
                print('XML文件已保存：', xml_file_path)  

if __name__ == '__main__':
    txtDir = '/data/m/365/365/txt'
    xmlDir = '/data/m/365/365/annotations/'

    txt_to_xml(txtDir, xmlDir)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40