Open vtddggg opened 4 years ago
We got the reported results by training the searched model for 200 epochs in the full training set. Note that we sample a validation set from the training set with "train_portion=0.9" during search. The detailed validation code for the searched model will be released soon.
Yeah, fine-tuning may be faster and improve the models. But we aim to search for better architecture and we think training from scratch is a more intuitive evaluation criterion. Thanks for your questions.
I run the experiment on CIFAR-100 using Single GPU:
But the result I got is
I found the result reported in paper is 71.57% after search. Is the 71.57% able to be achieved when setting larger
epoch
and largersearch iter
?Another question is after searching channels, model is trained from scratch in the code, can we finetune the model instead of training from scratch?
Thank for your helps