The transpose of
value=None, filter=None, output_shape=None, strides=None,
padding='SAME', data_format='NHWC', name=None, input=None,
This operation is sometimes called "deconvolution" after
(Zeiler et al., 2010), but is really the transpose (gradient) of
rather than an actual deconvolution.
Tensor of type
float and shape
[batch, height, width, in_channels] for
NHWC data format or
[batch, in_channels, height, width] for
NCHW data format.
Tensor with the same type as
value and shape
[height, width, output_channels, in_channels].
in_channels dimension must match that of
Tensor representing the output shape of the
An int or list of
ints that has length
stride of the sliding window for each dimension of
input. If a single
value is given it is replicated in the
W dimension. By default
C dimensions are set to 0. The dimension order is determined
by the value of
data_format, see below for details.
A string, either |
'SAME'. The padding algorithm.
See the "returns" section o