{{ message }}
-
-
Notifications
You must be signed in to change notification settings - Fork 51.1k
Expand file tree
/
Copy pathinput_data.py
More file actions
343 lines (290 loc) · 11.8 KB
/
Copy pathinput_data.py
File metadata and controls
343 lines (290 loc) · 11.8 KB
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
337
338
339
340
341
342
343
# Copyright 2016 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Functions for downloading and reading MNIST data (deprecated).
This module and all its submodules are deprecated.
"""
import gzip
import os
import typing
import urllib
import urllib.request
import numpy as np
from tensorflow.python.framework import dtypes, random_seed
from tensorflow.python.platform import gfile
from tensorflow.python.util.deprecation import deprecated
class _Datasets(typing.NamedTuple):
train: "_DataSet"
validation: "_DataSet"
test: "_DataSet"
# CVDF mirror of http://yann.lecun.com/exdb/mnist/
DEFAULT_SOURCE_URL = "https://storage.googleapis.com/cvdf-datasets/mnist/"
def _read32(bytestream):
dt = np.dtype(np.uint32).newbyteorder(">")
return np.frombuffer(bytestream.read(4), dtype=dt)[0]
@deprecated(None, "Please use tf.data to implement this functionality.")
def _extract_images(f):
"""Extract the images into a 4D uint8 numpy array [index, y, x, depth].
Args:
f: A file object that can be passed into a gzip reader.
Returns:
data: A 4D uint8 numpy array [index, y, x, depth].
Raises:
ValueError: If the bytestream does not start with 2051.
"""
print("Extracting", f.name)
with gzip.GzipFile(fileobj=f) as bytestream:
magic = _read32(bytestream)
if magic != 2051:
msg = f"Invalid magic number {magic} in MNIST image file: {f.name}"
raise ValueError(msg)
num_images = _read32(bytestream)
rows = _read32(bytestream)
cols = _read32(bytestream)
buf = bytestream.read(rows * cols * num_images)
data = np.frombuffer(buf, dtype=np.uint8)
data = data.reshape(num_images, rows, cols, 1)
return data
@deprecated(None, "Please use tf.one_hot on tensors.")
def _dense_to_one_hot(labels_dense, num_classes):
"""Convert class labels from scalars to one-hot vectors."""
num_labels = labels_dense.shape[0]
index_offset = np.arange(num_labels) * num_classes
labels_one_hot = np.zeros((num_labels, num_classes))
labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
return labels_one_hot
@deprecated(None, "Please use tf.data to implement this functionality.")
def _extract_labels(f, one_hot=False, num_classes=10):
"""Extract the labels into a 1D uint8 numpy array [index].
Args:
f: A file object that can be passed into a gzip reader.
one_hot: Does one hot encoding for the result.
num_classes: Number of classes for the one hot encoding.
Returns:
labels: a 1D uint8 numpy array.
Raises:
ValueError: If the bystream doesn't start with 2049.
"""
print("Extracting", f.name)
with gzip.GzipFile(fileobj=f) as bytestream:
magic = _read32(bytestream)
if magic != 2049:
msg = f"Invalid magic number {magic} in MNIST label file: {f.name}"
raise ValueError(msg)
num_items = _read32(bytestream)
buf = bytestream.read(num_items)
labels = np.frombuffer(buf, dtype=np.uint8)
if one_hot:
return _dense_to_one_hot(labels, num_classes)
return labels
class _DataSet:
"""Container class for a _DataSet (deprecated).
THIS CLASS IS DEPRECATED.
"""
@deprecated(
None,
"Please use alternatives such as official/mnist/_DataSet.py"
" from tensorflow/models.",
)
def __init__(
self,
images,
labels,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
seed=None,
) -> None:
"""Construct a _DataSet.
one_hot arg is used only if fake_data is true. `dtype` can be either
`uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
`[0, 1]`. Seed arg provides for convenient deterministic testing.
Args:
images: The images
labels: The labels
fake_data: Ignore inages and labels, use fake data.
one_hot: Bool, return the labels as one hot vectors (if True) or ints (if
False).
dtype: Output image dtype. One of [uint8, float32]. `uint8` output has
range [0,255]. float32 output has range [0,1].
reshape: Bool. If True returned images are returned flattened to vectors.
seed: The random seed to use.
"""
seed1, seed2 = random_seed.get_seed(seed)
# If op level seed is not set, use whatever graph level seed is returned
self._rng = np.random.default_rng(seed1 if seed is None else seed2)
dtype = dtypes.as_dtype(dtype).base_dtype
if dtype not in (dtypes.uint8, dtypes.float32):
msg = f"Invalid image dtype {dtype!r}, expected uint8 or float32"
raise TypeError(msg)
if fake_data:
self._num_examples = 10000
self.one_hot = one_hot
else:
assert images.shape[0] == labels.shape[0], (
f"images.shape: {images.shape} labels.shape: {labels.shape}"
)
self._num_examples = images.shape[0]
# Convert shape from [num examples, rows, columns, depth]
# to [num examples, rows*columns] (assuming depth == 1)
if reshape:
assert images.shape[3] == 1
images = images.reshape(
images.shape[0], images.shape[1] * images.shape[2]
)
if dtype == dtypes.float32:
# Convert from [0, 255] -> [0.0, 1.0].
images = images.astype(np.float32)
images = np.multiply(images, 1.0 / 255.0)
self._images = images
self._labels = labels
self._epochs_completed = 0
self._index_in_epoch = 0
@property
def images(self):
return self._images
@property
def labels(self):
return self._labels
@property
def num_examples(self):
return self._num_examples
@property
def epochs_completed(self):
return self._epochs_completed
def next_batch(self, batch_size, fake_data=False, shuffle=True):
"""Return the next `batch_size` examples from this data set."""
if fake_data:
fake_image = [1] * 784
fake_label = [1] + [0] * 9 if self.one_hot else 0
return (
[fake_image for _ in range(batch_size)],
[fake_label for _ in range(batch_size)],
)
start = self._index_in_epoch
# Shuffle for the first epoch
if self._epochs_completed == 0 and start == 0 and shuffle:
perm0 = np.arange(self._num_examples)
self._rng.shuffle(perm0)
self._images = self.images[perm0]
self._labels = self.labels[perm0]
# Go to the next epoch
if start + batch_size > self._num_examples:
# Finished epoch
self._epochs_completed += 1
# Get the rest examples in this epoch
rest_num_examples = self._num_examples - start
images_rest_part = self._images[start : self._num_examples]
labels_rest_part = self._labels[start : self._num_examples]
# Shuffle the data
if shuffle:
perm = np.arange(self._num_examples)
self._rng.shuffle(perm)
self._images = self.images[perm]
self._labels = self.labels[perm]
# Start next epoch
start = 0
self._index_in_epoch = batch_size - rest_num_examples
end = self._index_in_epoch
images_new_part = self._images[start:end]
labels_new_part = self._labels[start:end]
return (
np.concatenate((images_rest_part, images_new_part), axis=0),
np.concatenate((labels_rest_part, labels_new_part), axis=0),
)
else:
self._index_in_epoch += batch_size
end = self._index_in_epoch
return self._images[start:end], self._labels[start:end]
@deprecated(None, "Please write your own downloading logic.")
def _maybe_download(filename, work_directory, source_url):
"""Download the data from source url, unless it's already here.
Args:
filename: string, name of the file in the directory.
work_directory: string, path to working directory.
source_url: url to download from if file doesn't exist.
Returns:
Path to resulting file.
"""
if not gfile.Exists(work_directory):
gfile.MakeDirs(work_directory)
filepath = os.path.join(work_directory, filename)
if not gfile.Exists(filepath):
urllib.request.urlretrieve(source_url, filepath) # noqa: S310
with gfile.GFile(filepath) as f:
size = f.size()
print("Successfully downloaded", filename, size, "bytes.")
return filepath
@deprecated(None, "Please use alternatives such as: tensorflow_datasets.load('mnist')")
def read_data_sets(
train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
validation_size=5000,
seed=None,
source_url=DEFAULT_SOURCE_URL,
):
if fake_data:
def fake():
return _DataSet(
[], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed
)
train = fake()
validation = fake()
test = fake()
return _Datasets(train=train, validation=validation, test=test)
if not source_url: # empty string check
source_url = DEFAULT_SOURCE_URL
train_images_file = "train-images-idx3-ubyte.gz"
train_labels_file = "train-labels-idx1-ubyte.gz"
test_images_file = "t10k-images-idx3-ubyte.gz"
test_labels_file = "t10k-labels-idx1-ubyte.gz"
local_file = _maybe_download(
train_images_file, train_dir, source_url + train_images_file
)
with gfile.Open(local_file, "rb") as f:
train_images = _extract_images(f)
local_file = _maybe_download(
train_labels_file, train_dir, source_url + train_labels_file
)
with gfile.Open(local_file, "rb") as f:
train_labels = _extract_labels(f, one_hot=one_hot)
local_file = _maybe_download(
test_images_file, train_dir, source_url + test_images_file
)
with gfile.Open(local_file, "rb") as f:
test_images = _extract_images(f)
local_file = _maybe_download(
test_labels_file, train_dir, source_url + test_labels_file
)
with gfile.Open(local_file, "rb") as f:
test_labels = _extract_labels(f, one_hot=one_hot)
if not 0 <= validation_size <= len(train_images):
msg = (
"Validation size should be between 0 and "
f"{len(train_images)}. Received: {validation_size}."
)
raise ValueError(msg)
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
options = {"dtype": dtype, "reshape": reshape, "seed": seed}
train = _DataSet(train_images, train_labels, **options)
validation = _DataSet(validation_images, validation_labels, **options)
test = _DataSet(test_images, test_labels, **options)
return _Datasets(train=train, validation=validation, test=test)
You can’t perform that action at this time.