Convert a batch of sequences into a batch of images.
tf.contrib.layers.sequence_to_images( inputs, height, output_data_format='channels_last', outputs_collections=None, scope=None )
inputs: (num_steps, num_batches, depth) sequence tensor
height: the height of the images
output_data_format: Format of output tensor. Currently supports
outputs_collections: The collections to which the outputs are added.
scope: Optional scope for name_scope.
A tensor representing the output of the operation.