{"id":29608321,"url":"https://github.com/boobshash/numpy-neural-net","last_synced_at":"2025-07-20T19:34:31.609Z","repository":{"id":87183834,"uuid":"471377012","full_name":"boobshash/Numpy-Neural-Net","owner":"boobshash","description":"Simple and extendable library for deep learning in numpy","archived":false,"fork":false,"pushed_at":"2022-03-20T09:32:50.000Z","size":4450,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-11T03:39:33.566Z","etag":null,"topics":["deep-learning","mlp-classifier","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/boobshash.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-03-18T13:23:19.000Z","updated_at":"2022-03-23T12:19:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"f55bf41d-8f74-4c9e-8be4-084bb320cb63","html_url":"https://github.com/boobshash/Numpy-Neural-Net","commit_stats":null,"previous_names":["boobshash/numpy-neural-net"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/boobshash/Numpy-Neural-Net","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/boobshash%2FNumpy-Neural-Net","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/boobshash%2FNumpy-Neural-Net/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/boobshash%2FNumpy-Neural-Net/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/boobshash%2FNumpy-Neural-Net/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/boobshash","download_url":"https://codeload.github.com/boobshash/Numpy-Neural-Net/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/boobshash%2FNumpy-Neural-Net/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266187643,"owners_count":23890010,"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","mlp-classifier","numpy"],"created_at":"2025-07-20T19:34:25.886Z","updated_at":"2025-07-20T19:34:31.585Z","avatar_url":"https://github.com/boobshash.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Numpy-Neural-Net\n\n\nDear comrade! You can see a simple and extendable library for deep learning which is written entirely in numpy.\n\n## Core\nThe choosen architecture a little similar to PyTorch (`Module`, `Criterion`, and etc entities), see `core` folder for precise information.\n\n##  Data\nIn `data/data.py` you can find 3 useful abstractions:\n1. `DatasetImageFolder`\n2. `DataLoader`\n3. `DataManager`\n\nDatasetImageFolder and DataLoader are similar to Torch, DataManager similar to Torch Lightning.\n\nP.S. To run `run.py` to test efficiency of nn, download [CIFAR-10 dataset](https://drive.google.com/drive/folders/1M0M8jFpfWyi2G45kVovvVeoPgzGo6vaD?usp=sharing)\n\n## Trainer\nI have implement `Trainer` in  `trainer.py`, you can use it to fit your model.\n\n```python\ndm = DataManager(\n    train_data_path='data/Dataset/train',\n    test_data_path='data/Dataset/test',\n    val_data_path='data/Dataset/test',\n    class_names=[str(i) for i in range(10)],\n    batch_size=512\n)\n\ntrainer = Trainer(\n    model=model,\n    train_dataloader=dm.get_train_dataloader(),\n    test_dataloader=dm.get_test_dataloader(),\n    val_dataloader=dm.get_val_dataloader(),\n    criterion=criterion,\n    metrics_fn=metrics,\n    optimizer=optimizer,\n    optimizer_config=optimizer_config,\n    optimizer_state={}\n)\n\nmodel, hist = trainer.fit(n_epochs=100)\n```\n\n\n## Examples\nsee `example.ipynb`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fboobshash%2Fnumpy-neural-net","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fboobshash%2Fnumpy-neural-net","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fboobshash%2Fnumpy-neural-net/lists"}