Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"
Other
359
stars
83
forks
source link
In the original implementation of DARTS, it is input_search, target_search = next(iter(valid_queue), which slows down the training when using PyTorch 0.4 and above. #26
Regarding this issue, when I run the program using pytorch 1.1, I will still be prompted with a warning.
Is there a better solution?