Giters

SHI-Labs / Neighborhood-Attention-Transformer

Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Do you try larger resolution when evaluation or pretrained on ImageNet-22k to get higher performance?

laisimiao opened this issue · comments

commented
Do you try larger resolution when evaluation or pretrained on ImageNet-22k to get higher performance?
commented

I think it would be more convinced about your model capacity if you provide the mentioned results.

commented

As mentioned in the paper, we are currently looking into 22K pretraining. We were facing several issues as Swin did not release their 22k training settings in full until 2 weeks ago, and even now it is still incomplete for reproduction, and training on 22K is time consuming. We plan to release our 22k checkpoints and results when ready, so stay tuned.

commented

Look forward. Best regards.

commented

Regarding this issue, we now have new models which we do train on ImageNet-22K and fine-tune on ImageNet-1K at both 224x224 and 384x384 resolutions.
I'm closing this issue now, but feel free to reopen it if you have further questions.