search

yuhuixu1993 / PC-DARTS

PC-DARTS:Partial Channel Connections for Memory-Efficient Differentiable Architecture Search
436 stars 108 forks source link

Is a channel sampling mask fixed? #42

Open nabk89 opened 4 years ago

nabk89 commented 4 years ago

Hello, thank you for your code sharing. When looking into your code, I have a question about implementation for your partial channel connection idea.

In your code (model_search.py), it seems that "channel_shuffle" function only choose the first quartile of channels (including "forward" function of MixedOp class). Does it mean that a channel sampling mask S_i,j defined in your paper is a fixed mask?

Please answer my question. Thank you!

yuhuixu1993 commented 4 years ago

Hi, we offer two kinds of implementations in this repo. One is the mentioned channel_shuffle (it induces fixed mask each layer while different within layers.) which is an approximation; The other is a totally random mask, you can check model_search_random.py, if you are interested.

nabk89 commented 4 years ago

Thank you, but I don't understand that working of channel_shuffle is different within layers. Would you explain this part in a detail?

sjjdd commented 3 years ago

请问固定和随机哪种效果更好一些啊?