Encountered an issue in Attention part of odconv.py about odconv HOT 3 CLOSED

Hi, I'd like to ask if the issue has been solved?

That one was actually solved by another attempt, in my case, yolov7 will try to check out the output size by feeding a batch=1
random tensor into the backbone to see whether everything is OK, causing BN error, I just located that line of code and set that random tensor batch=2, since that is meant to be executed once. You might want to follow the instruction or try poking around to do some checking

from odconv.

This issue is caused by the batch normalization used in our ODConv. When using batch normalization, the batch size should at least be 2 during training. You can try to increase the batch size, or replace the batch normalization with layer normalization if you train the model from scratch, or add code as below to freeze the batch normalization layers if you use the pre-trained model.

from odconv.

Hi, I'd like to ask if the issue has been solved?

from odconv.