1# Copyright 2016 The TensorFlow Authors. All Rights Reserved. 2# 3# Licensed under the Apache License, Version 2.0 (the "License"); 4# you may not use this file except in compliance with the License. 5# You may obtain a copy of the License at 6# 7# http://www.apache.org/licenses/LICENSE-2.0 8# 9# Unless required by applicable law or agreed to in writing, software 10# distributed under the License is distributed on an "AS IS" BASIS, 11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12# See the License for the specific language governing permissions and 13# limitations under the License. 14# ============================================================================== 15"""Functions for downloading and reading MNIST data (deprecated). 16 17This module and all its submodules are deprecated. See 18[contrib/learn/README.md](https://www.tensorflow.org/code/tensorflow/contrib/learn/README.md) 19for migration instructions. 20""" 21 22from __future__ import absolute_import 23from __future__ import division 24from __future__ import print_function 25 26import gzip 27 28import numpy 29from six.moves import xrange # pylint: disable=redefined-builtin 30 31from tensorflow.contrib.learn.python.learn.datasets import base 32from tensorflow.python.framework import dtypes 33from tensorflow.python.framework import random_seed 34from tensorflow.python.platform import gfile 35from tensorflow.python.util.deprecation import deprecated 36 37# CVDF mirror of http://yann.lecun.com/exdb/mnist/ 38DEFAULT_SOURCE_URL = 'https://storage.googleapis.com/cvdf-datasets/mnist/' 39 40 41def _read32(bytestream): 42 dt = numpy.dtype(numpy.uint32).newbyteorder('>') 43 return numpy.frombuffer(bytestream.read(4), dtype=dt)[0] 44 45 46@deprecated(None, 'Please use tf.data to implement this functionality.') 47def extract_images(f): 48 """Extract the images into a 4D uint8 numpy array [index, y, x, depth]. 49 50 Args: 51 f: A file object that can be passed into a gzip reader. 52 53 Returns: 54 data: A 4D uint8 numpy array [index, y, x, depth]. 55 56 Raises: 57 ValueError: If the bytestream does not start with 2051. 58 59 """ 60 print('Extracting', f.name) 61 with gzip.GzipFile(fileobj=f) as bytestream: 62 magic = _read32(bytestream) 63 if magic != 2051: 64 raise ValueError('Invalid magic number %d in MNIST image file: %s' % 65 (magic, f.name)) 66 num_images = _read32(bytestream) 67 rows = _read32(bytestream) 68 cols = _read32(bytestream) 69 buf = bytestream.read(rows * cols * num_images) 70 data = numpy.frombuffer(buf, dtype=numpy.uint8) 71 data = data.reshape(num_images, rows, cols, 1) 72 return data 73 74 75@deprecated(None, 'Please use tf.one_hot on tensors.') 76def dense_to_one_hot(labels_dense, num_classes): 77 """Convert class labels from scalars to one-hot vectors.""" 78 num_labels = labels_dense.shape[0] 79 index_offset = numpy.arange(num_labels) * num_classes 80 labels_one_hot = numpy.zeros((num_labels, num_classes)) 81 labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1 82 return labels_one_hot 83 84 85@deprecated(None, 'Please use tf.data to implement this functionality.') 86def extract_labels(f, one_hot=False, num_classes=10): 87 """Extract the labels into a 1D uint8 numpy array [index]. 88 89 Args: 90 f: A file object that can be passed into a gzip reader. 91 one_hot: Does one hot encoding for the result. 92 num_classes: Number of classes for the one hot encoding. 93 94 Returns: 95 labels: a 1D uint8 numpy array. 96 97 Raises: 98 ValueError: If the bystream doesn't start with 2049. 99 """ 100 print('Extracting', f.name) 101 with gzip.GzipFile(fileobj=f) as bytestream: 102 magic = _read32(bytestream) 103 if magic != 2049: 104 raise ValueError('Invalid magic number %d in MNIST label file: %s' % 105 (magic, f.name)) 106 num_items = _read32(bytestream) 107 buf = bytestream.read(num_items) 108 labels = numpy.frombuffer(buf, dtype=numpy.uint8) 109 if one_hot: 110 return dense_to_one_hot(labels, num_classes) 111 return labels 112 113 114class DataSet(object): 115 """Container class for a dataset (deprecated). 116 117 THIS CLASS IS DEPRECATED. See 118 [contrib/learn/README.md](https://www.tensorflow.org/code/tensorflow/contrib/learn/README.md) 119 for general migration instructions. 120 """ 121 122 @deprecated(None, 'Please use alternatives such as official/mnist/dataset.py' 123 ' from tensorflow/models.') 124 def __init__(self, 125 images, 126 labels, 127 fake_data=False, 128 one_hot=False, 129 dtype=dtypes.float32, 130 reshape=True, 131 seed=None): 132 """Construct a DataSet. 133 one_hot arg is used only if fake_data is true. `dtype` can be either 134 `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into 135 `[0, 1]`. Seed arg provides for convenient deterministic testing. 136 """ 137 seed1, seed2 = random_seed.get_seed(seed) 138 # If op level seed is not set, use whatever graph level seed is returned 139 numpy.random.seed(seed1 if seed is None else seed2) 140 dtype = dtypes.as_dtype(dtype).base_dtype 141 if dtype not in (dtypes.uint8, dtypes.float32): 142 raise TypeError( 143 'Invalid image dtype %r, expected uint8 or float32' % dtype) 144 if fake_data: 145 self._num_examples = 10000 146 self.one_hot = one_hot 147 else: 148 assert images.shape[0] == labels.shape[0], ( 149 'images.shape: %s labels.shape: %s' % (images.shape, labels.shape)) 150 self._num_examples = images.shape[0] 151 152 # Convert shape from [num examples, rows, columns, depth] 153 # to [num examples, rows*columns] (assuming depth == 1) 154 if reshape: 155 assert images.shape[3] == 1 156 images = images.reshape(images.shape[0], 157 images.shape[1] * images.shape[2]) 158 if dtype == dtypes.float32: 159 # Convert from [0, 255] -> [0.0, 1.0]. 160 images = images.astype(numpy.float32) 161 images = numpy.multiply(images, 1.0 / 255.0) 162 self._images = images 163 self._labels = labels 164 self._epochs_completed = 0 165 self._index_in_epoch = 0 166 167 @property 168 def images(self): 169 return self._images 170 171 @property 172 def labels(self): 173 return self._labels 174 175 @property 176 def num_examples(self): 177 return self._num_examples 178 179 @property 180 def epochs_completed(self): 181 return self._epochs_completed 182 183 def next_batch(self, batch_size, fake_data=False, shuffle=True): 184 """Return the next `batch_size` examples from this data set.""" 185 if fake_data: 186 fake_image = [1] * 784 187 if self.one_hot: 188 fake_label = [1] + [0] * 9 189 else: 190 fake_label = 0 191 return [fake_image for _ in xrange(batch_size)], [ 192 fake_label for _ in xrange(batch_size) 193 ] 194 start = self._index_in_epoch 195 # Shuffle for the first epoch 196 if self._epochs_completed == 0 and start == 0 and shuffle: 197 perm0 = numpy.arange(self._num_examples) 198 numpy.random.shuffle(perm0) 199 self._images = self.images[perm0] 200 self._labels = self.labels[perm0] 201 # Go to the next epoch 202 if start + batch_size > self._num_examples: 203 # Finished epoch 204 self._epochs_completed += 1 205 # Get the rest examples in this epoch 206 rest_num_examples = self._num_examples - start 207 images_rest_part = self._images[start:self._num_examples] 208 labels_rest_part = self._labels[start:self._num_examples] 209 # Shuffle the data 210 if shuffle: 211 perm = numpy.arange(self._num_examples) 212 numpy.random.shuffle(perm) 213 self._images = self.images[perm] 214 self._labels = self.labels[perm] 215 # Start next epoch 216 start = 0 217 self._index_in_epoch = batch_size - rest_num_examples 218 end = self._index_in_epoch 219 images_new_part = self._images[start:end] 220 labels_new_part = self._labels[start:end] 221 return numpy.concatenate( 222 (images_rest_part, images_new_part), axis=0), numpy.concatenate( 223 (labels_rest_part, labels_new_part), axis=0) 224 else: 225 self._index_in_epoch += batch_size 226 end = self._index_in_epoch 227 return self._images[start:end], self._labels[start:end] 228 229 230@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py' 231 ' from tensorflow/models.') 232def read_data_sets(train_dir, 233 fake_data=False, 234 one_hot=False, 235 dtype=dtypes.float32, 236 reshape=True, 237 validation_size=5000, 238 seed=None, 239 source_url=DEFAULT_SOURCE_URL): 240 if fake_data: 241 242 def fake(): 243 return DataSet( 244 [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed) 245 246 train = fake() 247 validation = fake() 248 test = fake() 249 return base.Datasets(train=train, validation=validation, test=test) 250 251 if not source_url: # empty string check 252 source_url = DEFAULT_SOURCE_URL 253 254 TRAIN_IMAGES = 'train-images-idx3-ubyte.gz' 255 TRAIN_LABELS = 'train-labels-idx1-ubyte.gz' 256 TEST_IMAGES = 't10k-images-idx3-ubyte.gz' 257 TEST_LABELS = 't10k-labels-idx1-ubyte.gz' 258 259 local_file = base.maybe_download(TRAIN_IMAGES, train_dir, 260 source_url + TRAIN_IMAGES) 261 with gfile.Open(local_file, 'rb') as f: 262 train_images = extract_images(f) 263 264 local_file = base.maybe_download(TRAIN_LABELS, train_dir, 265 source_url + TRAIN_LABELS) 266 with gfile.Open(local_file, 'rb') as f: 267 train_labels = extract_labels(f, one_hot=one_hot) 268 269 local_file = base.maybe_download(TEST_IMAGES, train_dir, 270 source_url + TEST_IMAGES) 271 with gfile.Open(local_file, 'rb') as f: 272 test_images = extract_images(f) 273 274 local_file = base.maybe_download(TEST_LABELS, train_dir, 275 source_url + TEST_LABELS) 276 with gfile.Open(local_file, 'rb') as f: 277 test_labels = extract_labels(f, one_hot=one_hot) 278 279 if not 0 <= validation_size <= len(train_images): 280 raise ValueError('Validation size should be between 0 and {}. Received: {}.' 281 .format(len(train_images), validation_size)) 282 283 validation_images = train_images[:validation_size] 284 validation_labels = train_labels[:validation_size] 285 train_images = train_images[validation_size:] 286 train_labels = train_labels[validation_size:] 287 288 options = dict(dtype=dtype, reshape=reshape, seed=seed) 289 290 train = DataSet(train_images, train_labels, **options) 291 validation = DataSet(validation_images, validation_labels, **options) 292 test = DataSet(test_images, test_labels, **options) 293 294 return base.Datasets(train=train, validation=validation, test=test) 295 296 297@deprecated(None, 'Please use alternatives such as official/mnist/dataset.py' 298 ' from tensorflow/models.') 299def load_mnist(train_dir='MNIST-data'): 300 return read_data_sets(train_dir) 301