RuoyiDu
RuoyiDu
I notice that the time variable "t" is also inputted into the sigma_net, which is not consistent with the operation in the original paper.
Can the demo run on a remote server? I added server_name="xxxxxx", server_port=xxxxx to the launch() and the interface opens but I can't run the results.
Can we use the pre-trained ResNet152 in torchvision as the teacher model?
Excellent work! How much memory is needed to run this code (train and inference)?