Closed johsnows closed 5 years ago
Hi @johsnows !
Sorry I can't catch you. To evaluate a searched model generated by PDARTS, you would always need to retrain it by provided codes such as train_cifar.py, or implement your own version of retrain code.
GL,
就是先用train_search.py 再train_cifar.py这样是嘛
Use train_search.py
to do architecture search and train_cifar.py
/train_imagenet.py
to do architecture evaluation.
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?
or evalutate code train_cifar include the search process?