Giters

chenyilun95 / tf-cpn

Cascaded Pyramid Network for Multi-Person Pose Estimation (CVPR 2018)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About BN location

kaleidoscopical opened this issue · comments

commented

Hi! Thank you for making this project open to the world!
I run into some confuses because I am new to Tensorflow.
I wonder whether you add Batch Normalization(BN) to your added layers, e.g. 1*1 conv kernel and bottleneck in RefineNet.
Could you please give me a hint about where you add BN?

commented

That may be part due to historical problem. When we reproduce FPN for detection, we find BN can stablize the training process in case of NaN loss, thus we inherit from that. In fact that incurs redundant overhead of computation if now it trains well. BN is applied in original bottleneck blocks in resnet. As far as I know, it can improve the performance.

commented

Thanks for your quick response.