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

Training And Fine Tuning Configuration #8

Closed MarkWijkhuizen closed 11 months ago

MarkWijkhuizen commented 1 year ago

Could you provide the training and fine tuning configuration, I would be especially interested in:

han-cai commented 11 months ago

The training guide for ImageNet classification is available at https://github.com/mit-han-lab/efficientvit/blob/master/TRAINING.md.

The training guide for segmentation will be released soon.

Thanks for your interest in our work.