The transpose of
value, filters, output_shape, rate, padding, name=None
This operation is sometimes called "deconvolution" after
(Zeiler et al., 2010), but is really the transpose (gradient) of
atrous_conv2d rather than an actual deconvolution.
Tensor of type
float. It needs to be in the default
format. Its shape is
[batch, in_height, in_width, in_channels].
Tensor with the same type as
value and shape
[filter_height, filter_width, out_channels, in_channels].
in_channels dimension must match that of
value. Atrous convolution is
equivalent to standard convolution with upsampled filters with effective
filter_height + (filter_height - 1) * (rate - 1) and effective
filter_width + (filter_width - 1) * (rate - 1), produced by
rate - 1 zeros along consecutive elements across the
filters' spatial dimensions.
Tensor of shape representing the output shape of the
A positive int32. The stride with which we sam|