snail-pytorch icon indicating copy to clipboard operation
snail-pytorch copied to clipboard
verified publisher icon eambutu

Some discrepancies from the paper

Open ericjang opened this issue 6 years ago • 2 comments

For the Mini-ImageNet ResNet-based encoder, I believe the authors use mean pooling instead of max pooling, as done by this implementation. I am currently unable to reproduce the mini-imagenet results with your codebase (even train accuracy does not go up), and am hunting for discrepancies :)

ericjang avatar Aug 27 '19 18:08 ericjang

Awesome thanks so much! I hadn't achieved parity with MiniImagenet yet when I'd stopped working on this, so I appreciate the help! I finally have access to compute resources again, so I might try again this weekend.

One thing that might be worth a shot is trying loading/processing MiniImagenet in a different way: in other meta-learning repos using Miniimagenet, they download the images from the link in (https://github.com/dragen1860/LearningToCompare-Pytorch/issues/4) and do some other normalization (see: https://github.com/dragen1860/MAML-Pytorch/blob/master/MiniImagenet.py#L55).

eambutu avatar Aug 28 '19 06:08 eambutu

Hey guys, thanks for sharing the suggestions! I added image transformation based on your dataloader. But the train accuracy still cannot go up. Are you guys able to reproduce the results on miniImagenet so far?

suoql avatar May 20 '21 15:05 suoql