File size: 3,019 Bytes
97b6013 |
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 |
# Copyright 2017 Google Inc.
#
# 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.
"""Provides data for the MNIST-M dataset.
The dataset scripts used to create the dataset can be found at:
tensorflow_models/domain_adaptation_/datasets/download_and_convert_mnist_m_dataset.py
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
# Dependency imports
import tensorflow as tf
from slim.datasets import dataset_utils
slim = tf.contrib.slim
_FILE_PATTERN = 'mnist_m_%s.tfrecord'
_SPLITS_TO_SIZES = {'train': 58001, 'valid': 1000, 'test': 9001}
_NUM_CLASSES = 10
_ITEMS_TO_DESCRIPTIONS = {
'image': 'A [32 x 32 x 1] RGB image.',
'label': 'A single integer between 0 and 9',
}
def get_split(split_name, dataset_dir, file_pattern=None, reader=None):
"""Gets a dataset tuple with instructions for reading MNIST.
Args:
split_name: A train/test split name.
dataset_dir: The base directory of the dataset sources.
Returns:
A `Dataset` namedtuple.
Raises:
ValueError: if `split_name` is not a valid train/test split.
"""
if split_name not in _SPLITS_TO_SIZES:
raise ValueError('split name %s was not recognized.' % split_name)
if not file_pattern:
file_pattern = _FILE_PATTERN
file_pattern = os.path.join(dataset_dir, file_pattern % split_name)
# Allowing None in the signature so that dataset_factory can use the default.
if reader is None:
reader = tf.TFRecordReader
keys_to_features = {
'image/encoded':
tf.FixedLenFeature((), tf.string, default_value=''),
'image/format':
tf.FixedLenFeature((), tf.string, default_value='png'),
'image/class/label':
tf.FixedLenFeature(
[1], tf.int64, default_value=tf.zeros([1], dtype=tf.int64)),
}
items_to_handlers = {
'image': slim.tfexample_decoder.Image(shape=[32, 32, 3], channels=3),
'label': slim.tfexample_decoder.Tensor('image/class/label', shape=[]),
}
decoder = slim.tfexample_decoder.TFExampleDecoder(
keys_to_features, items_to_handlers)
labels_to_names = None
if dataset_utils.has_labels(dataset_dir):
labels_to_names = dataset_utils.read_label_file(dataset_dir)
return slim.dataset.Dataset(
data_sources=file_pattern,
reader=reader,
decoder=decoder,
num_samples=_SPLITS_TO_SIZES[split_name],
num_classes=_NUM_CLASSES,
items_to_descriptions=_ITEMS_TO_DESCRIPTIONS,
labels_to_names=labels_to_names)
|