Update README.md
Browse files
README.md
CHANGED
@@ -5,7 +5,8 @@ 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 |
|
10 |
Weights converted to PyTorch for Kornia ViT implementation (by [@gau-nernst](https://github.com/gau-nernst) in [kornia/kornia#2786](https://github.com/kornia/kornia/pull/2786#discussion_r1482339811))
|
11 |
<details>
|
|
|
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/16 pretrained on imagenet21k](https://storage.googleapis.com/vit_models/augreg/S_16-i21k-300ep-lr_0.001-aug_light1-wd_0.03-do_0.0-sd_0.0.npz)
|
10 |
|
11 |
Weights converted to PyTorch for Kornia ViT implementation (by [@gau-nernst](https://github.com/gau-nernst) in [kornia/kornia#2786](https://github.com/kornia/kornia/pull/2786#discussion_r1482339811))
|
12 |
<details>
|