question about the behavior of bn layers in inference about acnet HOT 4 CLOSED

Thank you for your interest in this paper. We must fuse the BN layers then merge the three branches. You can do some maths for verification.

from acnet.

That would result in a model without bn layers, how could I merge the branches so that I can have conv-bn structures which is exactly the off-shelf model?

from acnet.

We never need conv-bn structure in deployed models, as an inference-time BN layer is just a linear transformation. Actually, for the deployment of a regular CNN, you should #always# fuse the BN layer into the conv kernel manually or automatically (if your platform could do so) for efficiency.

from acnet.

Thanks for replying!!! I am closing this:)

from acnet.