Closed jrbtaylor closed 8 years ago
I'm working on an application where a CNN feeds into an RNN and am attempting to use an ImageNet pre-trained CNN. Is there a way to fix the weights in just that one module so they're not updated during training?
@jrbtaylor Yes. Just overload the accGradParameters call :
module = loadMyImageNetModel() module.accGradParameters = function(self) end
I'm working on an application where a CNN feeds into an RNN and am attempting to use an ImageNet pre-trained CNN. Is there a way to fix the weights in just that one module so they're not updated during training?