D-X-Y / AutoDL-Projects

Automated deep learning algorithms implemented in PyTorch.
MIT License
1.57k stars 282 forks source link

how to train model found by DARTS1V-search-NASNet-space.sh #67

Closed abduallahmohamed closed 4 years ago

abduallahmohamed commented 4 years ago

Hi,

I read most of the issues with how to train and so, I reached out that I might need to use:
./scripts/nas-infer-train.sh cifar10 to train the model, but apparently there's no such thing as ./configs/archs/NAS-CIFAR-DARTS_V1.config

Am I missing something?

Thanks

D-X-Y commented 4 years ago

Please see README here: https://github.com/D-X-Y/AutoDL-Projects/blob/master/docs/CVPR-2019-GDAS.md#searching-on-the-nasnet-search-space

It is suggested to use ./scripts/retrain-searched-net.sh to re-train the searched architecture.