search

ziplab / LITv2

[NeurIPS 2022 Spotlight] This is the official PyTorch implementation of "Fast Vision Transformers with HiLo Attention"
Apache License 2.0
229 stars 11 forks source link

large release for the model #5

Closed mathshangw closed 1 year ago

mathshangw commented 1 year ago

Thanks for sharing the code. I'm interested in your paper but is there any large release for the model?

HubHop commented 1 year ago

Hi @mathshangw, thanks for your interest! I assume you refer to a larger model or training on a larger dataset, like Swin-Large and ImageNet-22K. Unfortunately, to train such a large model on ImageNet-22K is far beyond our existing hardware resources. We will explore this setting in the future.

mathshangw commented 1 year ago

appreciate your reply , thanks