Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
xml_style.py 3 KB
Newer Older
bailuo's avatar
readme  
bailuo committed
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86 
import os.path as osp
import xml.etree.ElementTree as ET

import mmcv
import numpy as np

from .custom import CustomDataset
from .registry import DATASETS


@DATASETS.register_module
class XMLDataset(CustomDataset):

    def __init__(self, min_size=None, **kwargs):
        super(XMLDataset, self).__init__(**kwargs)
        self.cat2label = {cat: i + 1 for i, cat in enumerate(self.CLASSES)}
        self.min_size = min_size

    def load_annotations(self, ann_file):
        img_infos = []
        img_ids = mmcv.list_from_file(ann_file)
        for img_id in img_ids:
            filename = 'JPEGImages/{}.jpg'.format(img_id)
            xml_path = osp.join(self.img_prefix, 'Annotations',
                                '{}.xml'.format(img_id))
            tree = ET.parse(xml_path)
            root = tree.getroot()
            size = root.find('size')
            width = int(size.find('width').text)
            height = int(size.find('height').text)
            img_infos.append(
                dict(id=img_id, filename=filename, width=width, height=height))
        return img_infos

    def get_ann_info(self, idx):
        img_id = self.img_infos[idx]['id']
        xml_path = osp.join(self.img_prefix, 'Annotations',
                            '{}.xml'.format(img_id))
        tree = ET.parse(xml_path)
        root = tree.getroot()
        bboxes = []
        labels = []
        bboxes_ignore = []
        labels_ignore = []
        for obj in root.findall('object'):
            name = obj.find('name').text
            label = self.cat2label[name]
            difficult = int(obj.find('difficult').text)
            bnd_box = obj.find('bndbox')
            bbox = [
                int(bnd_box.find('xmin').text),
                int(bnd_box.find('ymin').text),
                int(bnd_box.find('xmax').text),
                int(bnd_box.find('ymax').text)
            ]
            ignore = False
            if self.min_size:
                assert not self.test_mode
                w = bbox[2] - bbox[0]
                h = bbox[3] - bbox[1]
                if w < self.min_size or h < self.min_size:
                    ignore = True
            if difficult or ignore:
                bboxes_ignore.append(bbox)
                labels_ignore.append(label)
            else:
                bboxes.append(bbox)
                labels.append(label)
        if not bboxes:
            bboxes = np.zeros((0, 4))
            labels = np.zeros((0, ))
        else:
            bboxes = np.array(bboxes, ndmin=2) - 1
            labels = np.array(labels)
        if not bboxes_ignore:
            bboxes_ignore = np.zeros((0, 4))
            labels_ignore = np.zeros((0, ))
        else:
            bboxes_ignore = np.array(bboxes_ignore, ndmin=2) - 1
            labels_ignore = np.array(labels_ignore)
        ann = dict(
            bboxes=bboxes.astype(np.float32),
            labels=labels.astype(np.int64),
            bboxes_ignore=bboxes_ignore.astype(np.float32),
            labels_ignore=labels_ignore.astype(np.int64))
        return ann