{"id":21181609,"url":"https://github.com/utility-code/tinydl","last_synced_at":"2025-07-10T00:31:18.007Z","repository":{"id":53451506,"uuid":"347930940","full_name":"utility-code/tinyDL","owner":"utility-code","description":"Tiny, easy to understand deep learning library in Python. With GPU support and only in numpy :)","archived":false,"fork":false,"pushed_at":"2021-04-27T12:26:46.000Z","size":443,"stargazers_count":16,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2023-03-05T03:09:30.502Z","etag":null,"topics":["deep-learning","easy-to-understand","gpu","library","numpy","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/utility-code.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-03-15T10:46:44.000Z","updated_at":"2022-05-14T12:31:23.000Z","dependencies_parsed_at":"2022-08-28T13:30:30.675Z","dependency_job_id":null,"html_url":"https://github.com/utility-code/tinyDL","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/utility-code%2FtinyDL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/utility-code%2FtinyDL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/utility-code%2FtinyDL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/utility-code%2FtinyDL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/utility-code","download_url":"https://codeload.github.com/utility-code/tinyDL/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225606685,"owners_count":17495551,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","easy-to-understand","gpu","library","numpy","python"],"created_at":"2024-11-20T17:51:40.699Z","updated_at":"2024-11-20T17:51:41.515Z","avatar_url":"https://github.com/utility-code.png","language":"Python","readme":"# TinyDL\n\n- Tiny Deep learning library \n- [DOCUMENTATION](https://subhadityamukherjee.github.io/tinyDL/)\n- Check the demo.py or the demo notebook!!! (same content)\n- Have a look at what works so far :)\n- Only needs numpy and pycuda for the library\n\n## Contributions\n- Do check the todo.md for stuff you can work on :)\n- Welcome! Add an issue if you have something you want to look at\n- PRs welcome\n\n## Requirements\n- numpy\n- matplotlib\n- pycuda  (for GPU)\n- pandas (if you are using the helpers and need to read a table)\n\n## How to run\n- Install the requirements\n- Configure parameters in config.py\n- python demo.py\n\n## Why?\n- Pytorch is too complicated to learn from. (Please. I tried. There are a million folders. My brain \u003e.\u003c)\n- This does not intend to be Pytorch. Just to understand what goes into it\n- An attempt at recreating most of the essential components from scratch\n- Eventual blogs on it as well\n\n## Inspired by\n- Karpathy and his awesomeness xD\n- [micrograd](https://github.com/karpathy/micrograd)\n- [teddykokker](https://github.com/teddykoker/tinyloader)\n- ft. Every attempt of me trying this in other languages and failing miserably ):\n\n## What are the .sh files\n- I am lazy. So I write code when I have to do the same things again and again.\n### pusher.sh\n- Formats all the code using \"Black\" formatter\n- Creates documentation from docstrings in the code using pandoc\n- Fixes the documentation paths for working with Github Pages\n- Takes the demo.py and pops it into a nice notebook for anyone to run and use\n- If an argument is given, it git commits with the message and pushes it to the repository\n\n## References\n- [training and tensor operations](https://github.com/kartik4949/deepops)\n- [autograd](https://github.com/karpathy/micrograd)\n- [pbar](https://stackoverflow.com/questions/3173320/text-progress-bar-in-the-console)\n- [skalski](https://github.com/SkalskiP/ILearnDeepLearning.py/blob/master/01_mysteries_of_neural_networks/03_numpy_neural_net/Numpy%20deep%20neural%20network.ipynb)\n- [softmax](https://stackoverflow.com/questions/34968722/how-to-implement-the-softmax-function-in-python)\n- [activations1](https://machinelearningmastery.com/weight-initialization-for-deep-learning-neural-networks/)\n- [albumentations](https://albumentations.ai/docs/api_reference/)\n- [conv](https://medium.com/analytics-vidhya/2d-convolution-using-python-numpy-43442ff5f381)\n- [optim](https://github.com/ilguyi/optimizers.numpy/blob/master/02.stochastic.gradient.descent.ipynb)\n- [loss](https://github.com/Nico-Curti/NumPyNet/blob/master/NumPyNet/metrics.py)\n- [loss2](https://github.com/ddbourgin/numpy-ml/blob/master/numpy_ml/neural_nets/losses/losses.py#L514-L924)\n- Countless stackoverflow searches (hehe)\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Futility-code%2Ftinydl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Futility-code%2Ftinydl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Futility-code%2Ftinydl/lists"}