johnnv commited on
Commit
3ebdd26
1 Parent(s): bb6a761

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -5,6 +5,13 @@ pipeline_tag: image-classification
5
 
6
  Pytorch weights for Kornia ViT converted from the original google JAX vision-transformer repo.
7
 
 
 
 
 
 
 
 
8
  Original weights from https://github.com/google-research/vision_transformer: This weight is based on the
9
  [Original ViT_S/32 pretrained on imagenet21k](https://storage.googleapis.com/vit_models/augreg/S_32-i21k-300ep-lr_0.001-aug_none-wd_0.1-do_0.0-sd_0.0.npz)
10
 
 
5
 
6
  Pytorch weights for Kornia ViT converted from the original google JAX vision-transformer repo.
7
 
8
+ ```python
9
+ from kornia.contrib import VisionTransformer
10
+
11
+ vit_model = VisionTransformer.from_config('vit_s/32', pretrained=True)
12
+ ...
13
+ ```
14
+
15
  Original weights from https://github.com/google-research/vision_transformer: This weight is based on the
16
  [Original ViT_S/32 pretrained on imagenet21k](https://storage.googleapis.com/vit_models/augreg/S_32-i21k-300ep-lr_0.001-aug_none-wd_0.1-do_0.0-sd_0.0.npz)
17