ASFF
ASFF copied to clipboard
Why do you use Convolutional layers without Batch-normalization in RFBblock?
@ruinmessi Hi,
Why do you use Convolutional layers without Batch-normalization in RFBblock? https://github.com/ruinmessi/ASFF/blob/55b6637b21d69509ae73100f9db19dc98acb419d/models/network_blocks.py#L138-L159
@AlexeyAB Hi, I just do this for simplicity. I think the essential part of rfb is the distribution of RFs, not BN. But I haven't done any experiments to verify that.