Skip layer connections from the second layer

[zhou-rui1]

Hi, when I try to edit the unet to unet++, it seems that the horizontal connections are only added from the second layer, and the last output layer is up-sampled by one layer to restore the dimensions, which is not the same as the original model.

is this for the design to use the pretrained model?

With great appreciation!

[zhou-rui1]

Hi, and plus...how did you get the channel calculation function for unet to adapt to different backbones...I have trouble when I change the structure to unet++

[IanTaehoonYoo]

Hi, Zhou
It's different between your snapshot and my code. The 'get_last_out_channels' function gets the last channel of features. So you don't need 'cfi_idx' in 'get_last_out_channels' and reconsider to use 'self.features[cfi_idx] as features'.
Also, I checked my code and the unet is working as the original model.

Thanks,

[zhou-rui1]

Thanks for your reply！
Yes, I found out that this is because the first layer of vgg is divided into two layers in resnet....

I change 'get_last_out_channels' to plus the number of channels added by the unet++ dense connection, and it seems I am unable to get a channel calculation function like you designed for unet, thus I can not change the backbones directly

but if use 'self.features[cfi_idx] as features', the features are backbone