TensorFlow:当批次完成训练时，tf.train.batch 是否会自动加载下一批? [英] TensorFlow: does tf.train.batch automatically load the next batch when the batch has finished training?
问题描述
例如，在我创建了操作后，通过操作输入批处理数据并运行操作，tf.train.batch 是否会自动输入另一批处理数据到会话?
For instance, after I have created my operations, fed the batch data through the operation and run the operation, does tf.train.batch automatically feed in another batch of data to the session?
我问这个是因为 tf.train.batch 有一个 allow_smaller_final_batch 属性，这使得最终批次可以以小于指定批次大小的大小加载.这是否意味着即使没有循环，下一批也可以自动喂食?从教程代码中我很困惑.当我加载单个批次时，我实际上得到一个批次大小的形状 [batch_size, height, width, num_channels]，但是 documentation 说它在张量中创建批量张量. 另外，当我阅读 tf-slim 演练教程，里面有个叫load_batch的函数，只返回3个张量:图像，images_raw，标签.文档中解释的批次"数据在哪里?
I ask this because tf.train.batch has an attribute of allow_smaller_final_batch which makes it possible for the final batch to be loaded as a size lesser than the indicated batch size. Does this mean even without a loop, the next batch could be automatically fed? From the tutorial codes I am rather confused. When I load a single batch, I get literally a single batch size of shape [batch_size, height, width, num_channels], but the documentation says it Creates batches of tensors in tensors. Also, when I read the tutorial code in the tf-slim walkthrough tutorial, where there is a function called load_batch, there are only 3 tensors returned: images, images_raw, labels. Where are 'batches' of data as explained in the documentation?
感谢您的帮助.
推荐答案
... tf.train.batch 是否会自动将另一批数据输入会话?
... does tf.train.batch automatically feeds in another batch of data to the session?
没有.没有任何事情会自动发生.您必须再次调用 sess.run(...) 才能加载新批次.
No. Nothing happens automatically. You must call sess.run(...) again to load a new batch.
这是否意味着即使没有循环，下一批也可以自动喂食?
Does this mean even without a loop, the next batch could be automatically fed?
没有.tf.train.batch(..) 将始终加载 batch_size 张量.例如，如果您有 100 张图像和一个 batch_size=30 那么您将有 3*30 个批次，因为您可以在输入之前调用 sess.run(batch) 三次队列将从头开始(如果 epoch=1 则停止).这意味着您在训练中错过了 100-3*30=10 个样本.如果您不想错过它们，您可以执行 tf.train.batch(..., allow_smaller_final_batch=True) 所以现在您将拥有 3x 30-sample-batches 和 1x 10-sample-在输入队列重新启动之前进行批处理.
No. tf.train.batch(..) will always load batch_size tensors. If you have for example 100 images and a batch_size=30 then you will have 3*30 batches as in you can call sess.run(batch) three times before the input queue will start from the beginning (or stop if epoch=1). This means that you miss out 100-3*30=10 samples from training. In case you do not want to miss them you can do tf.train.batch(..., allow_smaller_final_batch=True) so now you will have 3x 30-sample-batches and 1x 10-sample-batch before the input queue will restart.
让我也用一个代码示例来详细说明:
Let me also elaborate with a code sample:
queue = tf.train.string_input_producer(filenames,
num_epochs=1) # only iterate through all samples in dataset once
reader = tf.TFRecordReader() # or any reader you need
_, example = reader.read(queue)
image, label = your_conversion_fn(example)
# batch will now load up to 100 image-label-pairs on sess.run(...)
# most tf ops are tuned to work on batches
# this is faster and also gives better result on e.g. gradient calculation
batch = tf.train.batch([image, label], batch_size=100)
with tf.Session() as sess:
# "boilerplate" code
sess.run([
tf.local_variables_initializer(),
tf.global_variables_initializer(),
])
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
# in most cases coord.should_stop() will return True
# when there are no more samples to read
# if num_epochs=0 then it will run for ever
while not coord.should_stop():
# will start reading, working data from input queue
# and "fetch" the results of the computation graph
# into raw_images and raw_labels
raw_images, raw_labels = sess.run([images, labels])
finally:
coord.request_stop()
coord.join(threads)
这篇关于TensorFlow:当批次完成训练时，tf.train.batch 是否会自动加载下一批?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
