Open zhaoxin111 opened 2 years ago
Thank you very much! Would you like to open a PR to fix this bug?
Thank you very much! Would you like to open a PR to fix this bug?
Maybe you misunderstood me, I haven't fixed the problem mentioned in the picture, do you have any suggestions?
I found that the group convolution in a certain module is not divided into the same group as the subsequent convolution
In method make_groups, delete the beak in the loop and merge the groups like
After the above modifications, the problem seems to be fixed
any updates ?
regarding getting error as
KeyError: Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
Firstly, thanks for your excellect job! I had tried to prune the mobilenet, it contains many DWConv. To support DWConv pruning, I make little changes Otherwise, the following error will be reported
When finetuning the pruned model, there was error about the DWConv.