https://github.com/utility-code/sprintdl

pytorch wrapper for easier experimentation
https://github.com/utility-code/sprintdl

deep-learning deep-neural-networks pytorch

Last synced: 21 days ago
JSON representation

pytorch wrapper for easier experimentation

• Host: GitHub
• URL: https://github.com/utility-code/sprintdl
• Owner: utility-code
• Created: 2021-05-14T11:51:45.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-06-19T17:37:52.000Z (over 3 years ago)
• Last Synced: 2024-11-20T17:52:01.644Z (3 months ago)
• Topics: deep-learning, deep-neural-networks, pytorch
• Language: Jupyter Notebook
• Homepage: https://subhadityamukherjee.github.io/sprintdl/
• Size: 4.25 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# SprintDL

- A convenience wrapper over Pytorch

- Faster research and experimentation

- Based on [fastai](https://github.com/fastai)

- Not tooo high level and meant only for the "bit" advanced researcher

- Many many convenience functions that one would need

- (This library is not stable right now. Everything works of course, but they will be changed and rearranged eventually)

# Features

- Check features.md for a full list

## Documentation

- Okay so writing examples will take forever, so please check function documentation and the demos folder for most of what you need

- Check the syntax folder for documentation

- Check demos folder

- [Function documentation](https://subhadityamukherjee.github.io/sprintdl/)

- There will be blogs on the topics that were required and [more here](https://www.subhadityamukherjee.me/)

## Why

- I loved fastai, but in many things didnt agree with the way they went. I also needed some extra features that might have not ever been approved

- I wanted to learn DL even better. Thanks to the fastai course, I could do that. What better way to learn than make a whole library?

- On my way to be a better researcher, I have to take apart the things I take for granted. So, heres the cure for it.

## Reqs

- pip install -r requirements.txt

## Thank you

- A huge huge huge huge thank you to [Jeremy Howard](https://scholar.google.com/scholar?q=jeremy%20howard), [Rachel Thomas](https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=rachel+thomas&btnG=&oq=rachel+th), [Sylvian Gugger](https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=S+gugger&btnG=) and the whole fastai team for just being absolutely amazing and helpful

## Contributions

- Feel free to suggest requests or changes. Especially if I have made any mistakes

- Unlike the original fastai, this is just by me. Mainly for my research. In the spirit of open source, I wanted to share it here :)