Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"
359
stars
83
forks
source link
How can resume the train_search.py using weights in log_dir if the code stops due to accidents like power cut ... ? #19
Closed
JarveeLee closed 4 years ago
You can resue it with regular PyTorch functions such as
torch.load()
andmodel.load_state_dict()
.