You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello,
We used this version of CIFAR10 database to train models in timm (https://github.com/rwightman/pytorch-image-models), and it lead systematically to a drop of 2-3% accuracy. Upon inspection, it looks like this version of the dataset has substantial JPEG artifacts -- the images actually look noticeably less sharp and colorful. This is the topic of this issue that you can read here: (locuslab/convmixer#11 (comment)).
The text was updated successfully, but these errors were encountered:
I ran into the same issue as well while creating my own dataset, saving the images in PNG format is a much better solution that won't generate compression artifacts. If you are looking for the CIFAR-10 dataset with the raw images you can find it here https://www.kaggle.com/competitions/cifar-10/data
Hello,
We used this version of CIFAR10 database to train models in timm (https://github.com/rwightman/pytorch-image-models), and it lead systematically to a drop of 2-3% accuracy. Upon inspection, it looks like this version of the dataset has substantial JPEG artifacts -- the images actually look noticeably less sharp and colorful. This is the topic of this issue that you can read here: (locuslab/convmixer#11 (comment)).
The text was updated successfully, but these errors were encountered: