tf.contrib.nn.conv1d_transpose( value, filter, output_shape, stride, padding='SAME', data_format='NWC', name=None )
The transpose of
This operation is sometimes called "deconvolution" after Deconvolutional Networks, but is actually the transpose (gradient) of
conv1d rather than an actual deconvolution.
value: A 3-D
[batch, in_width, in_channels]for
NWCdata format or
[batch, in_channels, in_width]for
filter: A 3-D
Tensorwith the same type as
[filter_width, output_channels, in_channels].
in_channelsdimension must match that of
output_shape: A 1-D
Tensorrepresenting the output shape of the deconvolution op.
integer. The number of entries by which the filter is moved right at each step.
padding: A string, either
'SAME'. The padding algorithm. See the comment here
data_format: A string. 'NHWC' and 'NCHW' are supported.
name: Optional name for the returned tensor.
Tensor with the same type as
ValueError: If input/output depth does not match
filter's shape, or if padding is other than
© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.