{"id":20573342,"url":"https://github.com/m0saan/minima","last_synced_at":"2025-10-03T19:21:49.236Z","repository":{"id":172099631,"uuid":"647899744","full_name":"m0saan/minima","owner":"m0saan","description":"a lightweight deep learning framework, lean yet effective tailor-made for educational exploration.","archived":false,"fork":false,"pushed_at":"2023-07-04T06:23:48.000Z","size":31518,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-06T10:31:18.814Z","etag":null,"topics":["agi","deep-learning","deep-learning-framework","ndarray","neural-networks","tensors"],"latest_commit_sha":null,"homepage":"https://m0saan.github.io/minima/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/m0saan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-05-31T19:09:33.000Z","updated_at":"2023-07-08T04:26:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"f2edbb72-c215-4319-9acb-3674436ba118","html_url":"https://github.com/m0saan/minima","commit_stats":null,"previous_names":["m0saan/minima"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/m0saan/minima","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m0saan%2Fminima","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m0saan%2Fminima/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m0saan%2Fminima/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m0saan%2Fminima/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/m0saan","download_url":"https://codeload.github.com/m0saan/minima/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/m0saan%2Fminima/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278213932,"owners_count":25949381,"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","status":"online","status_checked_at":"2025-10-03T02:00:06.070Z","response_time":53,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["agi","deep-learning","deep-learning-framework","ndarray","neural-networks","tensors"],"created_at":"2024-11-16T05:27:20.308Z","updated_at":"2025-10-03T19:21:49.171Z","avatar_url":"https://github.com/m0saan.png","language":"Jupyter Notebook","readme":"Welcome to minima\n================\n\n\u003c!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! --\u003e\n\n![CI](https://github.com/m0saan/minima/workflows/CI/badge.svg)\n[![PyPI](https://img.shields.io/pypi/v/minima?color=blue\u0026label=pypi%20version.png)](https://pypi.org/project/minima/#description)\n[![Conda (channel\nonly)](https://img.shields.io/conda/vn/yourusername/minima?color=seagreen\u0026label=conda%20version.png)](https://anaconda.org/m0saan/minima)\n![docs](https://github.com/m0saan/minima/workflows/docs/badge.svg)\n\n# minima: A Mini Deep Learning Framework\n\n\u003e minima is a lightweight deep learning framewor, lean yet effective\n\u003e tailor-made for educational exploration.  \n\u003e Just like a delicate sapling inspired by the towering strength of an\n\u003e oak, Minima draws its inspiration from PyTorch.  \n\u003e Yet, it carves its own identity with a straightforward interface and a\n\u003e curated set of features.  \n\u003e This makes learning and using it a breeze, allowing you to\n\u003e effortlessly build and train neural networks.  \n\u003e Indeed, Minima is your friendly companion on the journey to\n\u003e understanding deep learning, where less is often more.\n\n## Installing\n\nYou can install minima on your own machines with conda\n\nIf you’re using\n[miniconda](https://docs.conda.io/en/latest/miniconda.html)\n(recommended) then run:\n\n``` bash\nconda install minima\n```\n\n…or if you’re using\n[Anaconda](https://www.anaconda.com/products/individual) then run:\n\n``` bash\nconda install minima anaconda\n```\n\nTo install with pip, use: `pip install minima`.\n\nIf you plan to develop Minima yourself, or want to be on the cutting\nedge, you can use an editable install.\n\n``` bash\ngit clone https://github.com/m0saan/minima\npip install .\n```\n\n## Features\n\n- Easy to install and use\n- Simple and intuitive API for defining and training neural networks\n- Built-in support for common layers and activation functions\n- Supports both CPU and GPU acceleration\n- Compatible with NumPy arrays for easy data manipulation\n\n## Usage\n\nHere’s a simple example of how to define and train a neural network\nusing Minima:\n\n``` python\nimport minima as mi\n\n# Define the neural network architecture\nmodel = mi.nn.Sequential(\n    mi.nn.Linear(784, 128),\n    mi.nn.ReLU(),\n    mi.nn.Linear(128, 10),\n    mi.nn.Softmax()\n)\n\n# Load the dataset\nx_train, y_train, x_test, y_test = load_data()\n\n# Train the model\nloss_fn = mi.nn.CrossEntropyLoss()\noptimizer = mi.optim.SGD(model.parameters(), lr=0.01)\nfor epoch in range(10):\n    for x_batch, y_batch in mi.nn.minibatch(x_train, y_train, batch_size=32):\n        y_pred = model(x_batch)\n        loss = loss_fn(y_pred, y_batch)\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n# Evaluate the model\ny_pred = model(x_test)\naccuracy = compute_accuracy(y_pred, y_test)\nprint(f\"Accuracy: {accuracy:.2f}\")\n```\n\nThis example defines a simple neural network with two linear layers and\ntwo activation functions, trains it on a dataset using stochastic\ngradient descent, and evaluates its accuracy on a test set.\n\n## Documentation\n\nFor more information on how to use minima, please refer to the\ndocumentation, which can be found in the website above.\n\n## Contributing\n\ncoming soon!\n\n## License\n\nminima is released under the Apache License 2.0. See `LICENSE` for more\ninformation.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm0saan%2Fminima","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fm0saan%2Fminima","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fm0saan%2Fminima/lists"}