Wei Peng
Wei Peng
Hello, Do you release the search part? If so, where can I find it? Thanks a lot.
RT, is this a complete implementation? Do you get the reported performance on CIFAR and Imagenet?
Hello, Thanks for your sharing. Could I ask a question about _compute_unrolled_model. What does unroll means here? Why did you code this function? It seem a backward-like function? thanks.
RT, I am trying to train it bymyself. But I change it for pytorch0.4. But in my model_search only loss.backward(retain_graph=True) can run. If it is loss.backward( ), is would raise...
Hello, I download your pretrained model resnext-101-kinetics-ucf101_split1.pt and want to test it directly on ucf101, But I get 0 accuracy. What should be the problem? Should I still finetuning it...
Hello, I really appreciate that you open source of your great work. However, without the processed dataset, we still can not run this code. I was wondering when do you...
I personally like this work. And will try something based on this one later. Wish all the best to this paper.
Hey, great work! Do you plan to release a PyTorch version? Best.