mit-han-lab / efficientvit

EfficientViT is a new family of vision models for efficient high-resolution vision.
Apache License 2.0
1.62k stars 143 forks source link

EfficientViT b0 pretrained in ImageNet #14

Closed seefun closed 11 months ago

seefun commented 11 months ago

Have you tested EfficientViT-b0 on ImageNet? And could you share the pretrained weights of EfficientViT-b0 in ImageNet 1k?

han-cai commented 11 months ago

Hi seefun,

You can download the pretrained weight of EfficientViT-B0 using the following link:

https://drive.google.com/file/d/1ganFBZmmvCTpgUwiLb8ePD6NBNxRyZDk/view?usp=drive_link

seefun commented 10 months ago

@han-cai Efficientvit series has been added into TIMM as EfficientViT (MIT) https://github.com/huggingface/pytorch-image-models