{"id":28311321,"url":"https://github.com/alonmell/modulnet","last_synced_at":"2026-04-29T00:07:40.369Z","repository":{"id":292014898,"uuid":"979533952","full_name":"AlonMell/ModulNet","owner":"AlonMell","description":"Lightweight NumPy-based neural network framework with core layers, loss functions, optimizers, and data utilities","archived":false,"fork":false,"pushed_at":"2025-05-07T17:16:51.000Z","size":4186,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-31T23:22:16.152Z","etag":null,"topics":["deep-learning","from-scratch","machine-learning","neural-network","numpy"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AlonMell.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,"zenodo":null}},"created_at":"2025-05-07T16:58:27.000Z","updated_at":"2025-05-07T17:13:02.000Z","dependencies_parsed_at":"2025-05-07T18:34:15.945Z","dependency_job_id":null,"html_url":"https://github.com/AlonMell/ModulNet","commit_stats":null,"previous_names":["alonmell/modulnet"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/AlonMell/ModulNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlonMell%2FModulNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlonMell%2FModulNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlonMell%2FModulNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlonMell%2FModulNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AlonMell","download_url":"https://codeload.github.com/AlonMell/ModulNet/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AlonMell%2FModulNet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261248195,"owners_count":23130348,"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","from-scratch","machine-learning","neural-network","numpy"],"created_at":"2025-05-24T12:11:06.359Z","updated_at":"2026-04-29T00:07:40.357Z","avatar_url":"https://github.com/AlonMell.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ModulNet\n\nA lightweight neural network framework written from scratch in NumPy.\nIncludes core building blocks for fully-connected and convolutional networks, custom optimizers, loss functions, and data loading utilities.\n\n## Explanation\n![Architecture](MLP.svg)\n\n## Features\n\n- Module API with `forward`/`backward` methods\n- Layers: `Linear`, `Conv2D`, `MaxPool2D`, `Flatten`, `ReLU`, `Sigmoid`, `DropOut`\n- Loss: `CrossEntropy` with softmax\n- Optimizers: `SGD`, `Adagrad`, `RMSProp`, `Adam`\n- Regularization utilities: `L1`, `L2`, `ElasticNet`\n- Simple `DataLoader` for batching\n- Example ConvNet training on MNIST in `main.py`\n- Jupyter notebooks for experimentation\n- Ruff, pytest integration for linting, formatting, and testing\n\n## Installation\n\n```bash\ngit clone https://github.com/AlonMell/ModulNet.git module_net\ncd module_net\npip install -r requirements.txt\n```\n\n## Usage\n\nTrain the example convolutional network on MNIST:\n\n```bash\npython main.py\n```\n\nOr explore the ModuleNet implementation in `notebooks/module.ipynb`.\n\n## Development\n\n- Lint: `make lint`\n- Format: `make fmt`\n- Run tests: `make test` or `pytest`\n\n## License\n\nThis project is licensed under the MIT License. See [LICENSE](LICENSE).","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falonmell%2Fmodulnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falonmell%2Fmodulnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falonmell%2Fmodulnet/lists"}