Vision Transformer (ViT)模型使用DINOv2方法进行训练。

Go to file

YYJ-aaaa 8a695b7180 first commit		2024-11-01 16:24:08 +08:00
.gitattributes	Add .gitattributes	2024-11-01 16:20:25 +08:00
README.md	Initial commit	2024-11-01 16:20:24 +08:00
config.json	first commit	2024-11-01 16:24:08 +08:00
model.safetensors	first commit	2024-11-01 16:24:08 +08:00
preprocessor_config.json	first commit	2024-11-01 16:24:08 +08:00
pytorch_model.bin	first commit	2024-11-01 16:24:08 +08:00

README.md

dinov2-small-imagenet1k-1-layer_a13446260285501440368918

Vision Transformer (ViT)模型使用DINOv2方法进行训练。