read tfrecords with slim

本文则通过slim来读取生成的tfrecord。读取和解码操作由tf.TFRecordReader完成

详细部分可参考 https://warmspringwinds.github.io/tensorflow/tf-slim/2016/12/21/tfrecords-guide/

import tensorflow as tf
slim = tf.contrib.slim
file_pattern = './pascal_train_*.tfrecord' #文件名格式

# 适配器1:将example反序列化成存储之前的格式。由tf完成
keys_to_features = {
    'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
    'image/format': tf.FixedLenFeature((), tf.string, default_value='jpeg'),
    'image/height': tf.FixedLenFeature([1], tf.int64),
    'image/width': tf.FixedLenFeature([1], tf.int64),
    'image/channels': tf.FixedLenFeature([1], tf.int64),
    'image/shape': tf.FixedLenFeature([3], tf.int64),
    'image/object/bbox/xmin': tf.VarLenFeature(dtype=tf.float32),
    'image/object/bbox/ymin': tf.VarLenFeature(dtype=tf.float32),
    'image/object/bbox/xmax': tf.VarLenFeature(dtype=tf.float32),
    'image/object/bbox/ymax': tf.VarLenFeature(dtype=tf.float32),
    'image/object/bbox/label': tf.VarLenFeature(dtype=tf.int64),
    'image/object/bbox/difficult': tf.VarLenFeature(dtype=tf.int64),
    'image/object/bbox/truncated': tf.VarLenFeature(dtype=tf.int64),
}

#适配器2:将反序列化的数据组装成更高级的格式。由slim完成,即可以将上面的几个数据包装成一个新数据
items_to_handlers = {
    'image': slim.tfexample_decoder.Image('image/encoded', 'image/format'),
    'shape': slim.tfexample_decoder.Tensor('image/shape'),
    'object/bbox': slim.tfexample_decoder.BoundingBox(
            ['ymin', 'xmin', 'ymax', 'xmax'], 'image/object/bbox/'),
    'object/label': slim.tfexample_decoder.Tensor('image/object/bbox/label'),
    'object/difficult': slim.tfexample_decoder.Tensor('image/object/bbox/difficult'),
    'object/truncated': slim.tfexample_decoder.Tensor('image/object/bbox/truncated'),
}

# 解码器
decoder = slim.tfexample_decoder.TFExampleDecoder(keys_to_features, items_to_handlers)

# dataset对象定义了数据集的文件位置,解码方式等元信息
dataset = slim.dataset.Dataset(
            data_sources=file_pattern,
            reader=tf.TFRecordReader,
            num_samples = 3, # 手动生成了三个文件, 每个文件里只包含一个example
            decoder=decoder,
            items_to_descriptions = {},
            num_classes=21)

#provider对象根据dataset信息读取数据
provider = slim.dataset_data_provider.DatasetDataProvider(
                    dataset,
                    num_readers=3,
                    shuffle=False)

[image, shape, glabels, gbboxes] = provider.get(['image', 'shape',
                                                             'object/label',
                                                             'object/bbox'])
print type(image)
print image.shape
<class 'tensorflow.python.framework.ops.Tensor'>
(?, ?, 3)

到目前为止,返回的image是一个tensor,而且是一个3维的,一次只有一张。需要组成一个batch。组成batch之前图片要预处理,一是为了将图片size变成固定大小, 二是数据增长。上面的示例代码来自https://github.com/balancap/SSD-Tensorflow/blob/master/datasets/pascalvoc_common.py#L49
。下面的示例代码来自 https://github.com/balancap/SSD-Tensorflow/blob/master/train_ssd_network.py#L203

# Pre-processing image, labels and bboxes.
image, glabels, gbboxes = \
    image_preprocessing_fn(image, glabels, gbboxes,
                           out_shape=ssd_shape,
                           data_format=DATA_FORMAT)
# Encode groundtruth labels and bboxes.
gclasses, glocalisations, gscores = \
    ssd_net.bboxes_encode(glabels, gbboxes, ssd_anchors)
batch_shape = [1] + [len(ssd_anchors)] * 3

# Training batches and queue.
r = tf.train.batch(
    tf_utils.reshape_list([image, gclasses, glocalisations, gscores]),
    batch_size=FLAGS.batch_size,
    num_threads=FLAGS.num_preprocessing_threads,
    capacity=5 * FLAGS.batch_size)
b_image, b_gclasses, b_glocalisations, b_gscores = \
    tf_utils.reshape_list(r, batch_shape)

# Intermediate queueing: unique batch computation pipeline for all
# GPUs running the training.
batch_queue = slim.prefetch_queue.prefetch_queue(
    tf_utils.reshape_list([b_image, b_gclasses, b_glocalisations, b_gscores]),
    capacity=2 * deploy_config.num_clones)

发表评论

电子邮件地址不会被公开。 必填项已用*标注