Transformers

Shield:

These images were originally published in the book “Deep Learning with PyTorch Step-by-Step: A Beginner’s Guide”.

They are also available at the book’s official repository: https://github.com/dvgodoy/PyTorchStepByStep.

Index

• Back
• Stacked Encoders and Decoders
• Sub-Layer
• Transformer
  • Encoder
  • Decoder
  • Full
• Special Classifier Token
• Vision Transformer (ViT)

** CLICK ON THE IMAGES FOR FULL SIZE **

Papers

• Self-Attention / Transformer: Attention Is All You Need by Vaswani, A. et al. (2017)
• Vision Transformer: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale by Dosovitskiy, A. et al. (2020)

Stacked Encoders and Decoders

Source: Chapter 10

Source: Chapter 10

Sub-Layer

Source: Chapter 10

Source: Chapter 10

Source: Chapter 10

Source: Chapter 10

Transformer

Encoder

Source: Chapter 10

Source: Chapter 10

Decoder

Source: Chapter 10

Source: Chapter 10

Full

Source: Chapter 10

Source: Chapter 10

Source: Chapter 10

Special Classifier Token

Source: Chapter 10

Source: Chapter 10

Vision Transformer

Source: Chapter 10

This work is licensed under a Creative Commons Attribution 4.0 International License.