579287b839
For an example of where it's broken, see: https://www.tensorflow.org/api_docs/python/tf/keras/datasets/boston_housing/load_data?hl=en&version=nightly PiperOrigin-RevId: 292604843 Change-Id: I8425808b211306bf60ff5a58beeedb11c01f7a2f
92 lines
3.0 KiB
Python
92 lines
3.0 KiB
Python
# Copyright 2017 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.
|
|
# ==============================================================================
|
|
"""Fashion-MNIST dataset.
|
|
"""
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import gzip
|
|
import os
|
|
|
|
import numpy as np
|
|
|
|
from tensorflow.python.keras.utils.data_utils import get_file
|
|
from tensorflow.python.util.tf_export import keras_export
|
|
|
|
|
|
@keras_export('keras.datasets.fashion_mnist.load_data')
|
|
def load_data():
|
|
"""Loads the Fashion-MNIST dataset.
|
|
|
|
This is a dataset of 60,000 28x28 grayscale images of 10 fashion categories,
|
|
along with a test set of 10,000 images. This dataset can be used as
|
|
a drop-in replacement for MNIST. The class labels are:
|
|
|
|
| Label | Description |
|
|
|:-----:|-------------|
|
|
| 0 | T-shirt/top |
|
|
| 1 | Trouser |
|
|
| 2 | Pullover |
|
|
| 3 | Dress |
|
|
| 4 | Coat |
|
|
| 5 | Sandal |
|
|
| 6 | Shirt |
|
|
| 7 | Sneaker |
|
|
| 8 | Bag |
|
|
| 9 | Ankle boot |
|
|
|
|
Returns:
|
|
Tuple of Numpy arrays: `(x_train, y_train), (x_test, y_test)`.
|
|
|
|
**x_train, x_test**: uint8 arrays of grayscale image data with shape
|
|
(num_samples, 28, 28).
|
|
|
|
**y_train, y_test**: uint8 arrays of labels (integers in range 0-9)
|
|
with shape (num_samples,).
|
|
|
|
License:
|
|
The copyright for Fashion-MNIST is held by Zalando SE.
|
|
Fashion-MNIST is licensed under the [MIT license](
|
|
https://github.com/zalandoresearch/fashion-mnist/blob/master/LICENSE).
|
|
|
|
"""
|
|
dirname = os.path.join('datasets', 'fashion-mnist')
|
|
base = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/'
|
|
files = [
|
|
'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
|
|
't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
|
|
]
|
|
|
|
paths = []
|
|
for fname in files:
|
|
paths.append(get_file(fname, origin=base + fname, cache_subdir=dirname))
|
|
|
|
with gzip.open(paths[0], 'rb') as lbpath:
|
|
y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)
|
|
|
|
with gzip.open(paths[1], 'rb') as imgpath:
|
|
x_train = np.frombuffer(
|
|
imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)
|
|
|
|
with gzip.open(paths[2], 'rb') as lbpath:
|
|
y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)
|
|
|
|
with gzip.open(paths[3], 'rb') as imgpath:
|
|
x_test = np.frombuffer(
|
|
imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)
|
|
|
|
return (x_train, y_train), (x_test, y_test)
|