使用Tensorflow Dataset API时如何使用设置输入标量

Question

I'm using TF Dataset API with a placeholder for file names which I feed when initializing the iterator (different files depending whether it's a training or validation set). I would also like to use additional placeholder indicating whether we're training or validating (to include in dropout layers). However, I'm unable to feed values to this placeholder using the dataset initializer (what makes sense since this is not a part of the dataset). How to feed additional variable while using Dataset API then?

Key code pieces:

filenames_placeholder = tf.placeholder(tf.string, shape = (None))
is_training = tf.placeholder(tf.bool, shape = ()) # Error: You must feed a value for placeholder tensor 'Placeholder_1' with dtype bool
dataset = tf.data.TFRecordDataset(filenames_placeholder)
# (...) Many other dataset operations
iterator = dataset.make_initializable_iterator()
next_element = iterator.get_next()

# Model code using "next_element"  as inputs including the dropout layer at some point 
# where I would like to let the model know if we're training or validating

tf.layers.dropout(x, training = is_training)

# Model execution
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
sess.run(iterator.initializer, feed_dict = {filenames_placeholder: training_files, is_training: True})
# (...) Performing training
sess.run(iterator.initializer, feed_dict = {filenames_placeholder: training_files, is_training: False})
# (...) Performing validadtion

Answer 1

What I do in this case is have an additional placeholder with a default value:

keep_prob = tf.placeholder_with_default(1.0, shape=())

And in the graph:

tf.layers.dropout(inputs, rate=1-keep_prob)

Then while training:

sess.run(...,feed_dict={keep_prob:0.5})

While evaluating:

sess.run(...) # No feed_dict here since the keep_prob placeholder has a default value of 1

Note that feeding a placeholder while training, that provides an additional float value doesn't slow your training at all.