search

chenxin061 / pdarts

Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"
Other
359 stars 83 forks source link

which genotype is best？ #21

Open johsnows opened 4 years ago

johsnows commented 4 years ago

after search on the train_search.py, we get many genotype, no restrict skipconnetct genotype and genotypes with number of skip-connect:7,6,5,4,3,2,1,0, which one is best? which one is recommended to evaluate?

arash-vahdat commented 4 years ago

This can help us too. Will appreciate authors' feedback!

chenxin061 commented 4 years ago

Sorry for the late reply. According to our experiments, keeping 2 skip-connects is recommended. You can refer to our paper for more details.

arash-vahdat commented 4 years ago

Thanks for the clarification!

NdaAzr commented 4 years ago

@chenxin061 do you recommend keeping 2 skip-connects genotype for any kind of dataset (eg. medical image dataset)? And the genotype printed at the end is it genotype for the last epoch? As far as I understood, DARTS was giving the genotype after each epoch in the search stage, and we should select the genotype that gives the highest accuracy. I am wondering which genotype should I use for evaluation in PDARTS.

Thank you in advance,

chenxin061 commented 4 years ago

@chenxin061 do you recommend keeping 2 skip-connects genotype for any kind of dataset (eg. medical image dataset)? And the genotype printed at the end is it genotype for the last epoch? As far as I understood, DARTS was giving the genotype after each epoch in the search stage, and we should select the genotype that gives the highest accuracy. I am wondering which genotype should I use for evaluation in PDARTS.

Thank you in advance,

We found that for image classification (on CIFAR and ImageNet), keeping 2 skip-connects in the genotype forms a good balance between accuracy and model size. For other tasks and datasets, I believe that keeping 2 can also work well but I recommand you to do some ablation study on your own dataset.
The genotype printed at the end is from the last epoch. From my side, I recommand you to use the genotype with two skip-connects or the one fits your dataset best according to the additional ablation study.