running time when it compares with Resnet from other code

quark0 / darts

Differentiable architecture search for convolutional and recurrent networks

https://arxiv.org/abs/1806.09055

Apache License 2.0

3.92k stars 843 forks source link

running time when it compares with Resnet from other code #105

Open Margrate opened 5 years ago

Margrate commented 5 years ago

It takes a long time to search architecture and train from start. If I use other code with Resnet to train from start. It only takes 1/5 time of DARTS code. Maybe the DARTS code is not so efficient?

Catosine commented 5 years ago

I also compared the DARTS with ResNet. And I found the same. I think this could be fixed by switching the search space with more efficient ones.

GL, PF