1# Copyright 2015 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"""CIFAR10 small images classification dataset.
16"""
17from __future__ import absolute_import
18from __future__ import division
19from __future__ import print_function
20
21import os
22
23import numpy as np
24
25from tensorflow.python.keras import backend as K
26from tensorflow.python.keras.datasets.cifar import load_batch
27from tensorflow.python.keras.utils.data_utils import get_file
28from tensorflow.python.util.tf_export import keras_export
29
30
31@keras_export('keras.datasets.cifar10.load_data')
32def load_data():
33  """Loads [CIFAR10 dataset](https://www.cs.toronto.edu/~kriz/cifar.html).
34
35  This is a dataset of 50,000 32x32 color training images and 10,000 test
36  images, labeled over 10 categories. See more info at the
37  [CIFAR homepage](https://www.cs.toronto.edu/~kriz/cifar.html).
38
39  Returns:
40      Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
41
42      **x_train, x_test**: uint8 arrays of RGB image data with shape
43        `(num_samples, 3, 32, 32)` if `tf.keras.backend.image_data_format()` is
44        `'channels_first'`, or `(num_samples, 32, 32, 3)` if the data format
45        is `'channels_last'`.
46
47      **y_train, y_test**: uint8 arrays of category labels
48        (integers in range 0-9) each with shape (num_samples, 1).
49  """
50  dirname = 'cifar-10-batches-py'
51  origin = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'
52  path = get_file(
53      dirname,
54      origin=origin,
55      untar=True,
56      file_hash=
57      '6d958be074577803d12ecdefd02955f39262c83c16fe9348329d7fe0b5c001ce')
58
59  num_train_samples = 50000
60
61  x_train = np.empty((num_train_samples, 3, 32, 32), dtype='uint8')
62  y_train = np.empty((num_train_samples,), dtype='uint8')
63
64  for i in range(1, 6):
65    fpath = os.path.join(path, 'data_batch_' + str(i))
66    (x_train[(i - 1) * 10000:i * 10000, :, :, :],
67     y_train[(i - 1) * 10000:i * 10000]) = load_batch(fpath)
68
69  fpath = os.path.join(path, 'test_batch')
70  x_test, y_test = load_batch(fpath)
71
72  y_train = np.reshape(y_train, (len(y_train), 1))
73  y_test = np.reshape(y_test, (len(y_test), 1))
74
75  if K.image_data_format() == 'channels_last':
76    x_train = x_train.transpose(0, 2, 3, 1)
77    x_test = x_test.transpose(0, 2, 3, 1)
78
79  x_test = x_test.astype(x_train.dtype)
80  y_test = y_test.astype(y_train.dtype)
81
82  return (x_train, y_train), (x_test, y_test)
83