How to share weights during searching for training to save training time?

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

How to share weights during searching for training to save training time? #78

Open stanveer opened 5 years ago

stanveer commented 5 years ago

I want to use the weights computed during searching as initial weights for training but i cannot figure out a way to do that in this code,if someone can help me it out it would be great.