{"id":44316390,"url":"https://github.com/w86763777/numpynet","last_synced_at":"2026-02-11T05:11:59.483Z","repository":{"id":33665560,"uuid":"160465602","full_name":"w86763777/numpynet","owner":"w86763777","description":"A simple Deep Learning framework powered by numpy.","archived":false,"fork":false,"pushed_at":"2024-05-03T19:54:19.000Z","size":23,"stargazers_count":1,"open_issues_count":2,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-05T05:02:10.005Z","etag":null,"topics":["backpropagation","cnn","deeplearning","fundamental","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/w86763777.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":"2018-12-05T05:26:38.000Z","updated_at":"2022-09-09T23:16:07.000Z","dependencies_parsed_at":"2022-09-02T07:40:25.071Z","dependency_job_id":null,"html_url":"https://github.com/w86763777/numpynet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/w86763777/numpynet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/w86763777%2Fnumpynet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/w86763777%2Fnumpynet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/w86763777%2Fnumpynet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/w86763777%2Fnumpynet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/w86763777","download_url":"https://codeload.github.com/w86763777/numpynet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/w86763777%2Fnumpynet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29327137,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-11T03:52:29.695Z","status":"ssl_error","status_checked_at":"2026-02-11T03:52:23.094Z","response_time":97,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["backpropagation","cnn","deeplearning","fundamental","numpy","python"],"created_at":"2026-02-11T05:11:58.803Z","updated_at":"2026-02-11T05:11:59.478Z","avatar_url":"https://github.com/w86763777.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NumpyNet\n\nHigh level neural network API implementated using numpy.\n\nThe project is my homework in deeplearning course at NCTU. Anyone can trace the code to learn how to do the backpropagation on sequential model and how to build a basic deeplearning API with python.\n\n## Requirements\n- python3\n\n## Install\n```\n$ git clone https://github.com/w86763777/numpynet\n$ cd numpynet\n$ python setup.py install\n```\n\n## Example\n\n```python\nfrom numpynet.dataset import iris, split_dataset\nfrom numpynet.models import SequentialModel\nfrom numpynet.optimizers import Adam\nfrom numpynet.loss import CrossEntropy\nfrom numpynet.metrics import categorical_accuracy\nfrom numpynet.layers import Input, Dense, ReLU, Softmax, Dropout\n\n\nif __name__ == \"__main__\":\n    # load iris dataset\n    iris = iris.read_data_sets()\n    # split dataset\n    train, test = split_dataset(iris, test_size=0.33)\n\n    # build model\n    model = SequentialModel()\n    model.add(Input((4,)))\n    model.add(Dense(10))\n    model.add(ReLU())\n    model.add(Dropout(0.3))\n    model.add(Dense(10))\n    model.add(ReLU())\n    model.add(Dropout(0.3))\n    model.add(Dense(3))\n    model.add(Softmax())\n\n    # assign objective, optimizer and metrics which is going to be shown on\n    # progress bar\n    model.compile(\n        objective=CrossEntropy(),\n        optimizer=Adam(learning_rate=0.001),\n        metric=[categorical_accuracy])\n    \n    # fit on data\n    model.fit(\n        x=train.X, y=train.y, val_x=test.X, val_y=test.y,\n        epochs=500, batch_size=8)\n\n```\n\noutput\n\n```\nEpoch 1/500\n100%|█████████████| 13/13 [00:00\u003c00:00, 1441.88it/s, categorical_accuracy=0.2900, cross_entropy=1.0986, val_categorical_accuracy=0.3600, val_cross_entropy=1.0982]\nEpoch 2/500\n100%|█████████████| 13/13 [00:00\u003c00:00, 1288.82it/s, categorical_accuracy=0.4200, cross_entropy=1.0968, val_categorical_accuracy=0.3600, val_cross_entropy=1.0982]\n...\nEpoch 500/500\n100%|█████████████| 13/13 [00:00\u003c00:00, 1296.02it/s, categorical_accuracy=0.6900, cross_entropy=0.8285, val_categorical_accuracy=0.9600, val_cross_entropy=0.2492]\n```\n\n[more examples](https://github.com/w86763777/numpynet/tree/master/examples)\n\n## How it work\n\n- TODO\n\n\n## Issues\n- regularization deos not work","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fw86763777%2Fnumpynet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fw86763777%2Fnumpynet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fw86763777%2Fnumpynet/lists"}