Merge pull request #401 from mchanchee/patch-2

Fix ViT image

Author: johko

chapters/en/unit3/vision-transformers/vision-transformers-for-image-classification.mdx

@@ -9,7 +9,7 @@ As the Transformers architecture scaled well in Natural Language Processing, the
 To summarize, in Vision transformer, images are reorganized as 2D grids of patches. The models are trained on those patches.
 
 The main idea can be found at the picture below: 
-![Vision Transformer](https://huggingface.co/datasets/hf-vision/course-assets/blob/main/Screenshot%20from%202024-12-27%2014-25-49.png)
+![Vision Transformer](https://huggingface.co/datasets/hf-vision/course-assets/resolve/main/Screenshot%20from%202024-12-27%2014-25-49.png)
 
 But there is a catch! The Convolutional Neural Networks (CNN)  are designed with an assumption missing in the VT. This assumption is based on how we perceive the objects in the images as humans. It is described in the following section.