guyuchao / dots Goto Github PK

Thanks for your work!
One question I hope can be answered: for the same data set and parameter settings, I run train.py with the best cell obtained by train_search.py. Why can't I get the same high accuracy as in train_search.py?
Look forward to your reply.

Thank you for your work, can you provide the code of Figure 3 in the paper?

Distinguished Researcher
Does your PyTorch version of DOTS also need to call jittor to search for it? Is there a pure Torch version? I often make errors debugging the Jittor.

Is there a Network parameter in PyTorch that can replace the Jittor?

Hello, I want to reproduce the result on cifar10 dataset. Could you provide more experiment information? I am interested in the valid accuracy curve/logs or final valid accuracy and random seed in search stage and the random seed of train stage. Thanks a lot.