about the Resnet architecture

wolverinn / HEVC-CU-depths-prediction-CNN

Using convolutional neural networks to predict the Coding Units (CUs) depths in HEVC intra-prediction mode, in order to reduce the time of the encoding process in HEVC.

MIT License

75 stars 25 forks source link

about the Resnet architecture #5

Open Omnipresent-3201 opened 3 years ago

Omnipresent-3201 commented 3 years ago

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 commented 3 years ago

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 commented 3 years ago

Got it, thanks a lot for your reply~