search

facebookresearch / AttentiveNAS

code for "AttentiveNAS Improving Neural Architecture Search via Attentive Sampling"
Other
103 stars 21 forks source link

The actual way to get best/worst pareto models #7

Closed RachelXu7 closed 2 years ago

RachelXu7 commented 2 years ago

It seems that the accuracy predictor is not fed into the sampler. Instead of using accuracy predictor, the code shows the way to get the pareto models is to rank the computed losses of k models after running forward. I am confused that the way to get the best/worst pareto model during training is different from the details in the paper. Am I misunderstanding the paper or missing the details of the code?

RachelXu7 commented 2 years ago

duplicate with https://github.com/facebookresearch/AttentiveNAS/issues/8