Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/carefree0910/carefree-learn
Deep Learning ❤️ PyTorch
https://github.com/carefree0910/carefree-learn
algorithm automl computer-vision data-science deep-learning ensemble machine-learning numpy python pytorch tabular-data tabular-datasets
Last synced: about 2 hours ago
JSON representation
Deep Learning ❤️ PyTorch
- Host: GitHub
- URL: https://github.com/carefree0910/carefree-learn
- Owner: carefree0910
- License: mit
- Created: 2020-06-17T17:44:17.000Z (over 4 years ago)
- Default Branch: v0.5.x
- Last Pushed: 2024-03-18T12:01:04.000Z (8 months ago)
- Last Synced: 2024-04-18T06:19:53.852Z (7 months ago)
- Topics: algorithm, automl, computer-vision, data-science, deep-learning, ensemble, machine-learning, numpy, python, pytorch, tabular-data, tabular-datasets
- Language: Python
- Homepage: https://carefree0910.me/carefree-learn-doc/
- Size: 6.42 MB
- Stars: 401
- Watchers: 12
- Forks: 39
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
- StarryDivineSky - carefree0910/carefree-learn - learn是一个基于 PyTorch 的深度学习框架,旨在简化深度学习操作。它以模块为核心,提供简洁易用的模块化设计,并尽可能保持原生 PyTorch 风格,支持依赖注入和 torch.compile 优化。框架优先考虑模块化设计,并计划在未来根据现代 AI 发展添加训练功能,同时保证 API 的向后兼容性。 (其他_机器学习与深度学习)
README
![carefree-learn][socialify-image]
Deep Learning with [PyTorch](https://pytorch.org/) made easy 🚀 !
## v0.5.x WIP!
Here are the main design principles:
- The codes should be '`module` first', which means all previous `model`s should be a simple `module` now.
- And `model` should only be related to the training stuffs. If we only want to use the fancy AI models at inference stage, `module` should be all we need.
- The `module`s should be as 'native' as possible: no inheritance from base classes except `nn.Module` should be the best, and previous inheritance-based features should be achieved by **dependency injection**.
- This helps the `module`s to be more `torch.compile` friendly.
- Training stuffs are not considered at the first place, but they will definitely be added later on, based on the modern AI developments.
- APIs will be as BC as possible.## License
`carefree-learn` is MIT licensed, as found in the [`LICENSE`](https://carefree0910.me/carefree-learn-doc/docs/about/license) file.
[socialify-image]: https://socialify.git.ci/carefree0910/carefree-learn/image?description=1&descriptionEditable=Deep%20Learning%20%E2%9D%A4%EF%B8%8F%20PyTorch&forks=1&issues=1&logo=https%3A%2F%2Fraw.githubusercontent.com%2Fcarefree0910%2Fcarefree-learn-doc%2Fmaster%2Fstatic%2Fimg%2Flogo.min.svg&pattern=Floating%20Cogs&stargazers=1