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
)
Args |
inputs
|
(num_steps, num_batches, depth) sequence tensor
|
height
|
the height of the images
|
output_data_format
|
Format of output tensor. Currently supports
'channels_first' and 'channels_last' .
|
outputs_collections
|
The collections to which the outputs are added.
|
scope
|
Optional scope for name_scope.
|
Returns |
A tensor representing the output of the operation.
|