Conv Details

[hhqweasd]

The conv in original is
==>Basic()
==>torch.nn.Conv2d(in_channels=intInput, out_channels=intOutput, ...)
Yours is
==>_conv_module()
==>torch.nn.Conv2d(in_channels, in_channels, kernel, stride, padding)
The channel is different.

[xiaozhi2015]

After fixing this bug, have you obtained the result same as the original author's https://github.com/sniklaus/sepconv-slomo ?
I just got the blur result in this project.