Dr Lusine Abrahamyan

Hi! We haven't tested, but if the overall number of parameters of the segmentation model is lower than ~10M, it might give a boost

If you are using the implementation from the torch vision you need to remove the last conv from the `self.features` and define a new member. For example: Original: `layers.append( Conv2dNormActivation(...

as the error is saying you are trying to multiply tensors with different sizes and you need to debug your code.

Hi, the configs are the following: SkipblockNet-XS - mode='small', width=0.5 SkipblockNet-S - mode='small', width=0.75 SkipblockNet-M - mode='large', width=1.0 SkipblockNet-L - mode='large', width=1.15

AS mentioned in the paper (before Eq. 1) v_i is the variance of the feature maps of the i-th data point in the batch, where t_i stands for i-th data...

thanks for your work!