File: imagenet_utils.py

package info (click to toggle)
keras-applications 1.0.8%2Bds-1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, bullseye
  • size: 600 kB
  • sloc: python: 3,490; makefile: 11; sh: 3
file content (336 lines) | stat: -rw-r--r-- 12,634 bytes parent folder | download | duplicates (2)
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
"""Utilities for ImageNet data preprocessing & prediction decoding.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import json
import warnings
import numpy as np

from . import get_submodules_from_kwargs

CLASS_INDEX = None
CLASS_INDEX_PATH = ('https://storage.googleapis.com/download.tensorflow.org/'
                    'data/imagenet_class_index.json')

# Global tensor of imagenet mean for preprocessing symbolic inputs
_IMAGENET_MEAN = None


def _preprocess_numpy_input(x, data_format, mode, **kwargs):
    """Preprocesses a Numpy array encoding a batch of images.

    # Arguments
        x: Input array, 3D or 4D.
        data_format: Data format of the image array.
        mode: One of "caffe", "tf" or "torch".
            - caffe: will convert the images from RGB to BGR,
                then will zero-center each color channel with
                respect to the ImageNet dataset,
                without scaling.
            - tf: will scale pixels between -1 and 1,
                sample-wise.
            - torch: will scale pixels between 0 and 1 and then
                will normalize each channel with respect to the
                ImageNet dataset.

    # Returns
        Preprocessed Numpy array.
    """
    backend, _, _, _ = get_submodules_from_kwargs(kwargs)
    if not issubclass(x.dtype.type, np.floating):
        x = x.astype(backend.floatx(), copy=False)

    if mode == 'tf':
        x /= 127.5
        x -= 1.
        return x

    if mode == 'torch':
        x /= 255.
        mean = [0.485, 0.456, 0.406]
        std = [0.229, 0.224, 0.225]
    else:
        if data_format == 'channels_first':
            # 'RGB'->'BGR'
            if x.ndim == 3:
                x = x[::-1, ...]
            else:
                x = x[:, ::-1, ...]
        else:
            # 'RGB'->'BGR'
            x = x[..., ::-1]
        mean = [103.939, 116.779, 123.68]
        std = None

    # Zero-center by mean pixel
    if data_format == 'channels_first':
        if x.ndim == 3:
            x[0, :, :] -= mean[0]
            x[1, :, :] -= mean[1]
            x[2, :, :] -= mean[2]
            if std is not None:
                x[0, :, :] /= std[0]
                x[1, :, :] /= std[1]
                x[2, :, :] /= std[2]
        else:
            x[:, 0, :, :] -= mean[0]
            x[:, 1, :, :] -= mean[1]
            x[:, 2, :, :] -= mean[2]
            if std is not None:
                x[:, 0, :, :] /= std[0]
                x[:, 1, :, :] /= std[1]
                x[:, 2, :, :] /= std[2]
    else:
        x[..., 0] -= mean[0]
        x[..., 1] -= mean[1]
        x[..., 2] -= mean[2]
        if std is not None:
            x[..., 0] /= std[0]
            x[..., 1] /= std[1]
            x[..., 2] /= std[2]
    return x


def _preprocess_symbolic_input(x, data_format, mode, **kwargs):
    """Preprocesses a tensor encoding a batch of images.

    # Arguments
        x: Input tensor, 3D or 4D.
        data_format: Data format of the image tensor.
        mode: One of "caffe", "tf" or "torch".
            - caffe: will convert the images from RGB to BGR,
                then will zero-center each color channel with
                respect to the ImageNet dataset,
                without scaling.
            - tf: will scale pixels between -1 and 1,
                sample-wise.
            - torch: will scale pixels between 0 and 1 and then
                will normalize each channel with respect to the
                ImageNet dataset.

    # Returns
        Preprocessed tensor.
    """
    global _IMAGENET_MEAN

    backend, _, _, _ = get_submodules_from_kwargs(kwargs)

    if mode == 'tf':
        x /= 127.5
        x -= 1.
        return x

    if mode == 'torch':
        x /= 255.
        mean = [0.485, 0.456, 0.406]
        std = [0.229, 0.224, 0.225]
    else:
        if data_format == 'channels_first':
            # 'RGB'->'BGR'
            if backend.ndim(x) == 3:
                x = x[::-1, ...]
            else:
                x = x[:, ::-1, ...]
        else:
            # 'RGB'->'BGR'
            x = x[..., ::-1]
        mean = [103.939, 116.779, 123.68]
        std = None

    if _IMAGENET_MEAN is None:
        _IMAGENET_MEAN = backend.constant(-np.array(mean))

    # Zero-center by mean pixel
    if backend.dtype(x) != backend.dtype(_IMAGENET_MEAN):
        x = backend.bias_add(
            x, backend.cast(_IMAGENET_MEAN, backend.dtype(x)),
            data_format=data_format)
    else:
        x = backend.bias_add(x, _IMAGENET_MEAN, data_format)
    if std is not None:
        x /= std
    return x


def preprocess_input(x, data_format=None, mode='caffe', **kwargs):
    """Preprocesses a tensor or Numpy array encoding a batch of images.

    # Arguments
        x: Input Numpy or symbolic tensor, 3D or 4D.
            The preprocessed data is written over the input data
            if the data types are compatible. To avoid this
            behaviour, `numpy.copy(x)` can be used.
        data_format: Data format of the image tensor/array.
        mode: One of "caffe", "tf" or "torch".
            - caffe: will convert the images from RGB to BGR,
                then will zero-center each color channel with
                respect to the ImageNet dataset,
                without scaling.
            - tf: will scale pixels between -1 and 1,
                sample-wise.
            - torch: will scale pixels between 0 and 1 and then
                will normalize each channel with respect to the
                ImageNet dataset.

    # Returns
        Preprocessed tensor or Numpy array.

    # Raises
        ValueError: In case of unknown `data_format` argument.
    """
    backend, _, _, _ = get_submodules_from_kwargs(kwargs)

    if data_format is None:
        data_format = backend.image_data_format()
    if data_format not in {'channels_first', 'channels_last'}:
        raise ValueError('Unknown data_format ' + str(data_format))

    if isinstance(x, np.ndarray):
        return _preprocess_numpy_input(x, data_format=data_format,
                                       mode=mode, **kwargs)
    else:
        return _preprocess_symbolic_input(x, data_format=data_format,
                                          mode=mode, **kwargs)


def decode_predictions(preds, top=5, **kwargs):
    """Decodes the prediction of an ImageNet model.

    # Arguments
        preds: Numpy tensor encoding a batch of predictions.
        top: Integer, how many top-guesses to return.

    # Returns
        A list of lists of top class prediction tuples
        `(class_name, class_description, score)`.
        One list of tuples per sample in batch input.

    # Raises
        ValueError: In case of invalid shape of the `pred` array
            (must be 2D).
    """
    global CLASS_INDEX

    backend, _, _, keras_utils = get_submodules_from_kwargs(kwargs)

    if len(preds.shape) != 2 or preds.shape[1] != 1000:
        raise ValueError('`decode_predictions` expects '
                         'a batch of predictions '
                         '(i.e. a 2D array of shape (samples, 1000)). '
                         'Found array with shape: ' + str(preds.shape))
    if CLASS_INDEX is None:
        fpath = keras_utils.get_file(
            'imagenet_class_index.json',
            CLASS_INDEX_PATH,
            cache_subdir='models',
            file_hash='c2c37ea517e94d9795004a39431a14cb')
        with open(fpath) as f:
            CLASS_INDEX = json.load(f)
    results = []
    for pred in preds:
        top_indices = pred.argsort()[-top:][::-1]
        result = [tuple(CLASS_INDEX[str(i)]) + (pred[i],) for i in top_indices]
        result.sort(key=lambda x: x[2], reverse=True)
        results.append(result)
    return results


def _obtain_input_shape(input_shape,
                        default_size,
                        min_size,
                        data_format,
                        require_flatten,
                        weights=None):
    """Internal utility to compute/validate a model's input shape.

    # Arguments
        input_shape: Either None (will return the default network input shape),
            or a user-provided shape to be validated.
        default_size: Default input width/height for the model.
        min_size: Minimum input width/height accepted by the model.
        data_format: Image data format to use.
        require_flatten: Whether the model is expected to
            be linked to a classifier via a Flatten layer.
        weights: One of `None` (random initialization)
            or 'imagenet' (pre-training on ImageNet).
            If weights='imagenet' input channels must be equal to 3.

    # Returns
        An integer shape tuple (may include None entries).

    # Raises
        ValueError: In case of invalid argument values.
    """
    if weights != 'imagenet' and input_shape and len(input_shape) == 3:
        if data_format == 'channels_first':
            if input_shape[0] not in {1, 3}:
                warnings.warn(
                    'This model usually expects 1 or 3 input channels. '
                    'However, it was passed an input_shape with ' +
                    str(input_shape[0]) + ' input channels.')
            default_shape = (input_shape[0], default_size, default_size)
        else:
            if input_shape[-1] not in {1, 3}:
                warnings.warn(
                    'This model usually expects 1 or 3 input channels. '
                    'However, it was passed an input_shape with ' +
                    str(input_shape[-1]) + ' input channels.')
            default_shape = (default_size, default_size, input_shape[-1])
    else:
        if data_format == 'channels_first':
            default_shape = (3, default_size, default_size)
        else:
            default_shape = (default_size, default_size, 3)
    if weights == 'imagenet' and require_flatten:
        if input_shape is not None:
            if input_shape != default_shape:
                raise ValueError('When setting `include_top=True` '
                                 'and loading `imagenet` weights, '
                                 '`input_shape` should be ' +
                                 str(default_shape) + '.')
        return default_shape
    if input_shape:
        if data_format == 'channels_first':
            if input_shape is not None:
                if len(input_shape) != 3:
                    raise ValueError(
                        '`input_shape` must be a tuple of three integers.')
                if input_shape[0] != 3 and weights == 'imagenet':
                    raise ValueError('The input must have 3 channels; got '
                                     '`input_shape=' + str(input_shape) + '`')
                if ((input_shape[1] is not None and input_shape[1] < min_size) or
                   (input_shape[2] is not None and input_shape[2] < min_size)):
                    raise ValueError('Input size must be at least ' +
                                     str(min_size) + 'x' + str(min_size) +
                                     '; got `input_shape=' +
                                     str(input_shape) + '`')
        else:
            if input_shape is not None:
                if len(input_shape) != 3:
                    raise ValueError(
                        '`input_shape` must be a tuple of three integers.')
                if input_shape[-1] != 3 and weights == 'imagenet':
                    raise ValueError('The input must have 3 channels; got '
                                     '`input_shape=' + str(input_shape) + '`')
                if ((input_shape[0] is not None and input_shape[0] < min_size) or
                   (input_shape[1] is not None and input_shape[1] < min_size)):
                    raise ValueError('Input size must be at least ' +
                                     str(min_size) + 'x' + str(min_size) +
                                     '; got `input_shape=' +
                                     str(input_shape) + '`')
    else:
        if require_flatten:
            input_shape = default_shape
        else:
            if data_format == 'channels_first':
                input_shape = (3, None, None)
            else:
                input_shape = (None, None, 3)
    if require_flatten:
        if None in input_shape:
            raise ValueError('If `include_top` is True, '
                             'you should specify a static `input_shape`. '
                             'Got `input_shape=' + str(input_shape) + '`')
    return input_shape