In paper, there is a CEL module at the start of every stage. Where are their implementation in the source code? It seems that the Patch Embedding Module is used only one time:
`def forward_features(self, x):
x = self.patch_embed(x)
if self.ape:
x = x + self.absolute_pos_embed
x = self.pos_drop(x)
for layer in self.layers:
x = layer(x)
x = self.norm(x) # B L C
x = self.avgpool(x.transpose(1, 2)) # B C 1
x = torch.flatten(x, 1)
return x`
In paper, there is a CEL module at the start of every stage. Where are their implementation in the source code? It seems that the Patch Embedding Module is used only one time:
`def forward_features(self, x):
x = self.patch_embed(x)
if self.ape:
x = x + self.absolute_pos_embed
x = self.pos_drop(x)