serereuk

In 'augmentation_transforms_hp.py' line 164 ``` HP_TRANSFORM_NAMES = NAME_TO_TRANSFORM.keys() ``` As I understand about your codes, It saves the list of (prob, mag), not saving the ops in search parts and...

Thanks for your help! I'm so happy to help you. :) :+1: I had hard time to reproduce the results and I think this may cause the problem. I'll try...

Hi again @arcelien I tried to reproduce with your code as paper. But I failed to make a result as you presented At first I did search with dataset 'rcifar10'...

Thanks for reply! I used Google Colab for Baseline. Because of colab policy, I had to turn off at checkpoint 150 , restore with ckpt and retrain until 200 epochs....

Thanks for replying! My original issue was that I couldn't reproduce the high accuracy results that your paper showed. To be precise, I tried measuring the paper's baseline performance using...

Thanks for fast reply!! I agree with your idea that Resnet is tricky haha.. I'll try to make another experiments with VGG nets first 👍 I'm using Resnet18 (little bit...

Actually, when I test with the pruned model which was from ```prune_model```, there were no issues with channels when I tried to get prediction. So I think there were no...