Skip to content
New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

#

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Update Vision transformer chapter #369

Closed
wants to merge 1 commit into from
Closed

Update Vision transformer chapter #369

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions ...s/en/unit3/vision-transformers/vision-transformers-for-image-classification.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,10 @@

As the Transformers architecture scaled well in Natural Language Processing, the same architecture was applied to images by creating small patches of the image and treating them as tokens. The result was a Vision Transformer (ViT). Before we get started with transfer learning / fine-tuning concepts, let's compare Convolutional Neural Networks (CNNs) with Vision Transformers.

## Vision Transformer a Summary

To summarize, in Vision transformer, we rearrange every image as a 2D grid of patches. We train the model based on those patches!

### CNN vs Vision Transformers: Inductive Bias

Inductive bias is a term used in machine learning to describe the set of assumptions that a learning algorithm uses to make predictions. In simpler terms, inductive bias is like a shortcut that helps a machine learning model make educated guesses based on the information it has seen so far.
Expand Down
Loading