about the Resnet architecture

[Omnipresent-3201]

Hello there,
I am recently studying on your code, the outcome of the CNN oriented network is fansinating, but I am wondering if you could show me some clues about the ResNet architecture. Is there any reference? I am currently facing the problem of training loss non-convergence, and I don't know why. Could you please give me more details about your network architecture?

[wolverinn]

Hi, I didn't try the ResNet architecture. I stopped at the CNN network. So I'm afraid I can't provide much information.

[Omnipresent-3201]

Got it, thanks a lot for your reply~