Haus

Hi, thanks for the great work on unifying SENet and CondConv. I just want to confirm if my understanding is correct: In SENet, attention is computed across the C input...

#2 #33 Regarding the issues above, I think the following lines are the proper way to replace the original implementation with the group normalization. The second function is the slightly...

Thank you for explaining this new concept! To confirm my understanding, is MPM implemented using the StripPooling class in customize.py, while SPM is implemented using the SPBlock class in resnet.py?...

In the **__init__** function of the PEG class, it seems that the **groups** parameter should be set to **in_chans** rather than **embed_dim**, since this is intended to be a depthwise...

Hi, thank you for the innovative work! However, I think I did not see a detailed explanation of how the $C$ in the equation $N_k=LC$ in section 3.2 is determined....

groups < out_channels is redundant

1

I think the if-else statement is redundant? Since if the groups parameter is greater than out_channels, an error(out_channels must divisible by groups) will be raised when we define the original...

### pycaret version checks - [x] I have checked that this issue has not already been reported [here](https://github.com/pycaret/pycaret/issues). - [x] I have confirmed this bug exists on the [latest version](https://github.com/pycaret/pycaret/releases)...