The class “Fusion”

[BASPIRIT]

The source code reads: self.down = nn.Sequential( nn.Conv2d(channels[level-1], channels[level], kernel_size=2, stride=2), LayerNorm(channels[level], eps=1e-6, data_format="channels_first"), ) if level in [1, 2, 3] else nn.Identity() So when level=0 and first_col=True, how do we implement downsampling?

[nightsnack]

level 0 does not need any downsample, if you do need one, just add one before level0