https://github.com/dvgodoy/dl-visuals

Over 200 figures and diagrams of the most popular deep learning architectures and layers FREE TO USE in your blog posts, slides, presentations, or papers.
https://github.com/dvgodoy/dl-visuals

cc-by deep-learning design diagrams neural-networks

Last synced: 4 months ago
JSON representation

Over 200 figures and diagrams of the most popular deep learning architectures and layers FREE TO USE in your blog posts, slides, presentations, or papers.

• Host: GitHub
• URL: https://github.com/dvgodoy/dl-visuals
• Owner: dvgodoy
• License: cc-by-4.0
• Created: 2021-05-20T11:20:16.000Z (about 5 years ago)
• Default Branch: main
• Last Pushed: 2021-07-11T18:43:02.000Z (almost 5 years ago)
• Last Synced: 2025-01-28T15:49:30.270Z (over 1 year ago)
• Topics: cc-by, deep-learning, design, diagrams, neural-networks
• Homepage:
• Size: 8.83 MB
• Stars: 1,407
• Watchers: 32
• Forks: 122
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Deep Learning Visuals

Shield: [![CC BY 4.0][cc-by-shield]][cc-by]

This repository was inspired by the [ML Visuals](https://github.com/dair-ai/ml-visuals) repository maintained by [dair.ai](https://dair.ai/).

**Deep Learning Visuals** contains **215 unique images** divided in **23 categories** (some images may appear in more than one category). All the images were originally published in my book ["Deep Learning with PyTorch Step-by-Step: A Beginner's Guide"](https://leanpub.com/pytorch).

## Can I Freely Use These Images?

Sure, these images can be FREELY USED in your own blog posts, slides, presentations, or papers under the CC-BY license.

## Awesome, where are they?

You can easily navigate through the pages and indices, and click on the desired image to visualize it in full size:

- [Activation Functions](https://dvgodoy.github.io/dl-visuals/Activation%20Functions)

- [Architectures](https://dvgodoy.github.io/dl-visuals/Architectures)

- [Assorted](https://dvgodoy.github.io/dl-visuals/Assorted)

- [Attention](https://dvgodoy.github.io/dl-visuals/Attention)

- [Batch Norm](https://dvgodoy.github.io/dl-visuals/BatchNorm)

- [BERT](https://dvgodoy.github.io/dl-visuals/BERT)

- [Classification](https://dvgodoy.github.io/dl-visuals/Classification)

- [Convolutions](https://dvgodoy.github.io/dl-visuals/Convolutions)

- [Decoder](https://dvgodoy.github.io/dl-visuals/Decoder)

- [Dropout](https://dvgodoy.github.io/dl-visuals/Dropout)

- [ELMo](https://dvgodoy.github.io/dl-visuals/ELMo)

- [Encoder](https://dvgodoy.github.io/dl-visuals/Encoder)

- [Feed-Forward Networks](https://dvgodoy.github.io/dl-visuals/Feed-Forward%20Networks)

- [Gradient Descent](https://dvgodoy.github.io/dl-visuals/Gradient%20Descent)

- [Initializations and Gradient Clipping](https://dvgodoy.github.io/dl-visuals/Initializations%20and%20Clipping)

- [LayerNorm](https://dvgodoy.github.io/dl-visuals/LayerNorm)

- [Optimizers and Schedulers](https://dvgodoy.github.io/dl-visuals/Optimizers%20and%20Schedulers)

- [Patch Embeddings](https://dvgodoy.github.io/dl-visuals/Patch%20Embeddings)

- [Positional Encoding](https://dvgodoy.github.io/dl-visuals/Positional%20Encoding)

- [RNNs](https://dvgodoy.github.io/dl-visuals/RNNs)

- [Seq2Seq](https://dvgodoy.github.io/dl-visuals/Seq2Seq)

- [Transformers](https://dvgodoy.github.io/dl-visuals/Transformers)

## How Can I Use Them?

**DISCLAIMER: this is NOT legal advice, you should always read the license yourself!**

In a nutshell, you're allowed to use (or adapt) these images in your own materials, even for commercial purposes, as long as you attribute it.

Here is a quick guide on [Best Practices for Attribution](https://wiki.creativecommons.org/wiki/best_practices_for_attribution).

Here are some examples of both images and attributions:

### Logistic Regression

![](https://raw.githubusercontent.com/dvgodoy/dl-visuals/main/Classification/logistic_model.png)

Image by [dvgodoy](https://github.com/dvgodoy/dl-visuals) / [CC BY](https://creativecommons.org/licenses/by/4.0/)

### RNN

![](https://raw.githubusercontent.com/dvgodoy/dl-visuals/main/RNNs/rnn2.png)

Image by [dvgodoy](https://github.com/dvgodoy/dl-visuals) / [CC BY](https://creativecommons.org/licenses/by/4.0/)

### Transformer

![](https://raw.githubusercontent.com/dvgodoy/dl-visuals/main/Transformers/full_transformer.png)

Image by [dvgodoy](https://github.com/dvgodoy/dl-visuals) / [CC BY](https://creativecommons.org/licenses/by/4.0/)

This work is licensed under a

[Creative Commons Attribution 4.0 International License][cc-by].

[![CC BY 4.0][cc-by-image]][cc-by]

[cc-by]: http://creativecommons.org/licenses/by/4.0/

[cc-by-image]: https://i.creativecommons.org/l/by/4.0/88x31.png

[cc-by-shield]: https://img.shields.io/badge/License-CC%20BY%204.0-lightgrey.svg