search

facebookresearch / video-nonlocal-net

Non-local Neural Networks for Video Classification
Other
1.97k stars 325 forks source link

Questions about the BN layer and affine layers #34

Open gooners1886 opened 6 years ago

gooners1886 commented 6 years ago

In the readme file: To train the i3d Non-local Networks with longer clips (32-frame input), we first need to obtain the model trained from "run_i3d_baseline_400k.sh" as a pre-trained model. Then we convert the Batch Normalization layers into Affine layers by running: python modify_caffe2_ftvideo.py xxxx

what is an affine layer? Is it a conv layer without batch normalizaion? Does the model with affine layer has more parameters than the one with BN layer arrording the gpu memory taking? Is there some other operation in affine layer?

yelantf commented 6 years ago

well, I wonder that too. So, is an affine layer an alternative of batch normalization layer? If so, how does it work and is there any research papers about that?

bryanyzhu commented 4 years ago

+1