curtis.abcd
@BarretZoph Thanks for opensourcing. I really look forward to it! Also for SolarizeAdd, sorry for my misunderstanding. I will update this repo and start new experiments. Thanks.
I need to examine more since the performance doesn't match after I change augmentation search space as RandAugment's code. Best top1 error is 22.65 by training 180 epochs. cc @BarretZoph ...
@BarretZoph Thanks, I will look into your opensourced codes. By checking codes provided by you, I'm not sure what is different. Below items are few things that might ruin the...
@HobbitLong Thanks! They are surely things that can cause differences. As @BarretZoph mentioned, tensorflow's randaugment will be open this week or next, I will examine the code and share what...
@BarretZoph Thanks for the update. It will help a lot. I found that the preprocessing part for resnet/efficientnet implemented by google is a bit different than the one most people...
I fix the above problem and got **23.22** top1 error with resnet50 and the N=2, M=9. I guess there are more things to match but due to my current work,...
I will upload imagenet pretrained models(firstly, resnet50) after I reproduce paper's result.
You need to specify your dataset location : https://github.com/ildoonet/pytorch-randaugment/blob/master/RandAugment/train.py#L245
@iamhankai There is a bug with learning rate scheduler with recent version of pytorch. I fixed it so you can try again. Also I will look into this problem as...
@JoinWei-PKU @Shaw95 See our released codes. search.py