How do you consider about Layer normalization and Batch normalization?

MenghaoGuo / PCT

Jittor implementation of PCT:Point Cloud Transformer

661 stars 80 forks source link

Open Alobal opened 2 years ago

Alobal commented 2 years ago

Hi,

PCT used the Batch normalization, instead of the Layer normalization, used by original Transformer.

I wonder how do you consider about Layer normalization and Batch normalization in PCT?