mmuratarat
commited on
Commit
•
4125333
1
Parent(s):
f5b46d5
Update README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,7 @@ The Vision Transformer (ViT) model was proposed in "An Image is Worth 16x16 Word
|
|
27 |
|
28 |
The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.
|
29 |
|
30 |
-
![](https://github.com/mmuratarat/turkish/blob/master/_posts/images/
|
31 |
|
32 |
In this case, we'll be using [the google/vit-base-patch16-224-in21k model](https://huggingface.co/google/vit-base-patch16-224-in21k) from Hugging Face.
|
33 |
|
|
|
27 |
|
28 |
The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a supervised fashion, namely ImageNet-21k, at a resolution of 224x224 pixels. Next, the model was fine-tuned on ImageNet (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.
|
29 |
|
30 |
+
![](https://github.com/mmuratarat/turkish/blob/master/_posts/images/vit_architecture.jpg?raw=true)
|
31 |
|
32 |
In this case, we'll be using [the google/vit-base-patch16-224-in21k model](https://huggingface.co/google/vit-base-patch16-224-in21k) from Hugging Face.
|
33 |
|