wavefrontshaping / complexPyTorch

A high-level toolbox for using complex valued neural networks in PyTorch
MIT License
610 stars 148 forks source link

Another batch norm suggestion #34

Open MordehayM opened 6 months ago

MordehayM commented 6 months ago

Hi, About the naive batch norm, I believe it's more effective to normalize the tensor with the absolute value rather than normalizing each part individually: https://github.com/wavefrontshaping/complexPyTorch/blob/2044cb077b3f139d59dff56abc378b1457de40d6/complexPyTorch/complexLayers.py#L213

What do you think?