File size: 4,552 Bytes
29f689c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
import io

import cv2
import numpy as np
from PIL import Image

from .db_resize_for_test import DetResizeForTest


class NormalizeImage(object):
    """normalize image such as substract mean, divide std"""

    def __init__(self, scale=None, mean=None, std=None, order='chw', **kwargs):
        if isinstance(scale, str):
            scale = eval(scale)
        self.scale = np.float32(scale if scale is not None else 1.0 / 255.0)
        mean = mean if mean is not None else [0.485, 0.456, 0.406]
        std = std if std is not None else [0.229, 0.224, 0.225]

        shape = (3, 1, 1) if order == 'chw' else (1, 1, 3)
        self.mean = np.array(mean).reshape(shape).astype('float32')
        self.std = np.array(std).reshape(shape).astype('float32')

    def __call__(self, data):
        img = data['image']
        from PIL import Image

        if isinstance(img, Image.Image):
            img = np.array(img)
        assert isinstance(img,
                          np.ndarray), "invalid input 'img' in NormalizeImage"
        data['image'] = (img.astype('float32') * self.scale -
                         self.mean) / self.std
        return data


class ToCHWImage(object):
    """convert hwc image to chw image"""

    def __init__(self, **kwargs):
        pass

    def __call__(self, data):
        img = data['image']
        from PIL import Image

        if isinstance(img, Image.Image):
            img = np.array(img)
        data['image'] = img.transpose((2, 0, 1))
        return data


class KeepKeys(object):

    def __init__(self, keep_keys, **kwargs):
        self.keep_keys = keep_keys

    def __call__(self, data):
        data_list = []
        for key in self.keep_keys:
            data_list.append(data[key])
        return data_list


def transform(data, ops=None):
    """transform."""
    if ops is None:
        ops = []
    for op in ops:
        data = op(data)
        if data is None:
            return None
    return data


class DecodeImage(object):
    """decode image."""

    def __init__(self,
                 img_mode='RGB',
                 channel_first=False,
                 ignore_orientation=False,
                 **kwargs):
        self.img_mode = img_mode
        self.channel_first = channel_first
        self.ignore_orientation = ignore_orientation

    def __call__(self, data):
        img = data['image']

        assert type(img) is bytes and len(
            img) > 0, "invalid input 'img' in DecodeImage"
        img = np.frombuffer(img, dtype='uint8')
        if self.ignore_orientation:
            img = cv2.imdecode(
                img, cv2.IMREAD_IGNORE_ORIENTATION | cv2.IMREAD_COLOR)
        else:
            img = cv2.imdecode(img, 1)
        if img is None:
            return None
        if self.img_mode == 'GRAY':
            img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
        elif self.img_mode == 'RGB':
            assert img.shape[2] == 3, 'invalid shape of image[%s]' % (
                img.shape)
            img = img[:, :, ::-1]

        if self.channel_first:
            img = img.transpose((2, 0, 1))

        data['image'] = img
        return data


class DecodeImagePIL(object):
    """decode image."""

    def __init__(self, img_mode='RGB', **kwargs):
        self.img_mode = img_mode

    def __call__(self, data):
        img = data['image']
        assert type(img) is bytes and len(
            img) > 0, "invalid input 'img' in DecodeImage"
        img = data['image']
        buf = io.BytesIO(img)
        img = Image.open(buf).convert('RGB')
        if self.img_mode == 'Gray':
            img = img.convert('L')
        elif self.img_mode == 'BGR':
            img = np.array(img)[:, :, ::-1]  # 将图片转为numpy格式,并将最后一维通道倒序
            img = Image.fromarray(np.uint8(img))
        data['image'] = img
        return data


def create_operators(op_param_list, global_config=None):
    """create operators based on the config.

    Args:
        params(list): a dict list, used to create some operators
    """
    assert isinstance(op_param_list, list), 'operator config should be a list'
    ops = []
    for operator in op_param_list:
        assert isinstance(operator,
                          dict) and len(operator) == 1, 'yaml format error'
        op_name = list(operator)[0]
        param = {} if operator[op_name] is None else operator[op_name]
        if global_config is not None:
            param.update(global_config)
        op = eval(op_name)(**param)
        ops.append(op)
    return ops