tfc.ops.same_padding_for_kernel

Determine correct amount of padding for same convolution.

tfc.ops.same_padding_for_kernel(
    shape, corr, strides_up=None
)

To implement 'same' convolutions, we first pad the image, and then perform a 'valid' convolution or correlation. Given the kernel shape, this function determines the correct amount of padding so that the output of the convolution or correlation is the same size as the pre-padded input.

shape Shape of the convolution kernel (without the channel dimensions).
corr Boolean. If True, assume cross correlation, if False, convolution.
strides_up If this is used for an upsampled convolution, specify the strides here. (For downsampled convolutions, specify (1, 1): in that case, the strides don't matter.)

The amount of padding at the beginning and end for each dimension.