CapProNet-Pytorch
CapProNet-Pytorch copied to clipboard
When the last layer of the fully connected layer becomes CapProNet,
When the last layer of the fully connected layer becomes CapProNet, how do you set up the initialization of the network? Or just change the CapProNet part, do not change the initialization of the network? thanks.
I have the same question, how to set the initialization of the weight? The training is unstable when we change the hyperparameter of initialization. thanks.