# Copyright 2015 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. # ============================================================================== """Converts MNIST data to TFRecords file format with Example protos.""" from __future__ import absolute_import from __future__ import division from __future__ import print_function import argparse import os import sys import tensorflow as tf from tensorflow.contrib.learn.python.learn.datasets import mnist FLAGS = None def _int64_feature(value): return tf.train.Feature(int64_list=tf.train.Int64List(value=[value])) def _bytes_feature(value): return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value])) def convert_to(data_set, name): """Converts a dataset to tfrecords.""" images = data_set.images labels = data_set.labels num_examples = data_set.num_examples if images.shape[0] != num_examples: raise ValueError('Images size %d does not match label size %d.' % (images.shape[0], num_examples)) rows = images.shape[1] cols = images.shape[2] depth = images.shape[3] filename = os.path.join(FLAGS.directory, name + '.tfrecords') print('Writing', filename) writer = tf.python_io.TFRecordWriter(filename) for index in range(num_examples): image_raw = images[index].tostring() example = tf.train.Example(features=tf.train.Features(feature={ 'height': _int64_feature(rows), 'width': _int64_feature(cols), 'depth': _int64_feature(depth), 'label': _int64_feature(int(labels[index])), 'image_raw': _bytes_feature(image_raw)})) writer.write(example.SerializeToString()) writer.close() def main(unused_argv): # Get the data. data_sets = mnist.read_data_sets(FLAGS.directory, dtype=tf.uint8, reshape=False, validation_size=FLAGS.validation_size) # Convert to Examples and write the result to TFRecords. convert_to(data_sets.train, 'train') convert_to(data_sets.validation, 'validation') convert_to(data_sets.test, 'test') if __name__ == '__main__': parser = argparse.ArgumentParser() parser.add_argument( '--directory', type=str, default='/tmp/data', help='Directory to download data files and write the converted result' ) parser.add_argument( '--validation_size', type=int, default=5000, help="""\ Number of examples to separate from the training data for the validation set.\ """ ) FLAGS, unparsed = parser.parse_known_args() tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
这段代码是用来转换MNIST到标准的tensorflow格式——TFRecords的,默认路径写在了/tmp/data下。我这里直接改成了MNIST_data/ ,然后里面放上MNIST的那四个gz文件就可以了。这是修改路径的方法。运行结果是
Extracting MNIST_data/train-images-idx3-ubyte.gz
Extracting MNIST_data/train-labels-idx1-ubyte.gz
Extracting MNIST_data/t10k-images-idx3-ubyte.gz
Extracting MNIST_data/t10k-labels-idx1-ubyte.gz
Writing MNIST_data/train.tfrecords
Writing MNIST_data/validation.tfrecords
Writing MNIST_data/test.tfrecords
然后在MNIST_data/ 下可以看到生成的三个TFRecords文件。
最终目标是训练自己的图片,初步怀疑gz解压缩以后就是原始图片,明天可以尝试把自己的图片也弄成gz文件然后生成TFRecords。另外,接着尝试从队列中读取数据。对比教程和官方教程。
convert_to_records.py路径修改
最新推荐文章于 2023-02-07 17:12:40 发布