tf.contrib.nn.conv1d_transpose(
value,
filter,
output_shape,
stride,
padding='SAME',
data_format='NWC',
name=None
)
Defined in tensorflow/python/ops/nn_ops.py
.
The transpose of conv1d
.
This operation is sometimes called "deconvolution" after Deconvolutional
Networks, but is
actually the transpose (gradient) of conv1d
rather than an actual
deconvolution.
Args:
value
: A 3-DTensor
of typefloat
and shape[batch, in_width, in_channels]
forNWC
data format or[batch, in_channels, in_width]
forNCW
data format.filter
: A 3-DTensor
with the same type asvalue
and shape[filter_width, output_channels, in_channels]
.filter
'sin_channels
dimension must match that ofvalue
.output_shape
: A 1-DTensor
representing the output shape of the deconvolution op.stride
: Aninteger
. The number of entries by which the filter is moved right at each step.padding
: A string, either'VALID'
or'SAME'
. The padding algorithm. See the "returns" section oftf.nn.convolution
for details.data_format
: A string. 'NHWC' and 'NCHW' are supported.name
: Optional name for the returned tensor.
Returns:
A Tensor
with the same type as value
.
Raises:
ValueError
: If input/output depth does not matchfilter
's shape, or if padding is other than'VALID'
or'SAME'
.