{"id":16775041,"url":"https://github.com/masasron/deepnet","last_synced_at":"2026-05-20T09:10:35.819Z","repository":{"id":80182817,"uuid":"120157152","full_name":"masasron/deepnet","owner":"masasron","description":"DeepNet is simple node based cli tool for creating machine learning classifiers you can use on the web.","archived":false,"fork":false,"pushed_at":"2018-02-11T14:16:20.000Z","size":44,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-16T17:46:09.791Z","etag":null,"topics":["classifier","classifier-training","deep-learning","deep-neural-networks","machine-learning","nodejs"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","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/masasron.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":"2018-02-04T05:16:02.000Z","updated_at":"2018-05-07T06:08:49.000Z","dependencies_parsed_at":null,"dependency_job_id":"e7db8c56-7a1c-4254-833f-f19ef9c2b4bd","html_url":"https://github.com/masasron/deepnet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/masasron/deepnet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masasron%2Fdeepnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masasron%2Fdeepnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masasron%2Fdeepnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masasron%2Fdeepnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/masasron","download_url":"https://codeload.github.com/masasron/deepnet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/masasron%2Fdeepnet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33253212,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-20T04:48:54.280Z","status":"ssl_error","status_checked_at":"2026-05-20T04:48:10.851Z","response_time":356,"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":["classifier","classifier-training","deep-learning","deep-neural-networks","machine-learning","nodejs"],"created_at":"2024-10-13T06:50:50.551Z","updated_at":"2026-05-20T09:10:35.802Z","avatar_url":"https://github.com/masasron.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DeepNet\nDeepNet is simple node based cli tool for creating machine learning classifiers you can use on the web.\n\n```bash\nroot$ node deepnet/src/cli.js -h\n\nUsage: cli [options] [command]\n\n\n  Options:\n\n    -V, --version  output the version number\n    -h, --help     output usage information\n\n\n  Commands:\n\n    train [options] \u003cfile\u003e\n    make-dataset [options] \u003cpositive_dataset_file\u003e \u003cnegative_dataset_file\u003e\n    predict [options] \u003cmodel\u003e \u003ctest-data\u003e\n```\n\n### Train\n\n```bash\nroot$ node deepnet/src/cli.js train -h\n\n  Usage: train [options] \u003cfile\u003e\n\n\n\n  Options:\n\n    -t, --test-dataset-percentage \u003cn\u003e  percentage of datasets to keep for testing (default: 25)\n    -n, --name \u003cvalue\u003e                 choose a name for your model (default: model-1518027472621)\n    -s, --save-period \u003cn\u003e              save model every \u003cn\u003e iterations (default: 20000)\n    -v, --vectorize \u003cf\u003e                automatically vectorize strings from training data (default: true)\n    -l, --learning-rate \u003cf\u003e            network learning rate (default: 0.1)\n    -e, --error-threshold \u003cf\u003e          minimum error threshold (default: 0.005)\n    -y, --hidden-layers \u003cn\u003e            number of hidden layers (default: 6)\n    -i, --iterations \u003cn\u003e               maximum number of iterations (default: 20000)\n    -p, --log-period \u003cn\u003e               log progress every \u003cn\u003e iterations (default: 25)\n    -g, --log \u003cb\u003e                      log traning progress (default: true)\n    -r, --randomize \u003cb\u003e                randomize dataset (default: true)\n    -a, --activation \u003cactivation\u003e      activation function (default: sigmoid)\n    -h, --help                         output usage information\n```\n\nThe train command require a JSON dataset file in the format below.   \nYou may use the `make-dataset` helper command to generate this file.\n\n```json\n[\n  {\n    \"input\": [0.1,0.2,0.3],\n    \"output\": [0.6]\n  },\n  {\n    \"input\": [0.1,0,0],\n    \"output\": [0.1]\n  }\n]\n```\n\n### Make Dataset\n\n```sh\nroot$ node deepnet/src/cli.js make-dataset -h\n\n  Usage: make-dataset [options] \u003cpositive_dataset_file\u003e \u003cnegative_dataset_file\u003e\n\n\n  Options:\n\n    -n, --name \u003cf\u003e       choose a dataset name (default: dataset-1518028193094)\n    -v, --vectorize \u003cf\u003e  automatically vectorize strings (default: true)\n    -h, --help           output usage information\n```\n\n### Predict\n\nYou can use the predict command to load an existing model.\n\n```sh\nroot$ node deepnetsrc/cli.js predict -h\n\n  Usage: predict [options] \u003cmodel\u003e \u003ctest-data\u003e\n\n\n  Options:\n\n    \u003cmodel\u003e      path to the model .bin file\n    \u003ctest-data\u003e  test data as string (if -, read from stdin)\n    -h, --help   output usage information\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmasasron%2Fdeepnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmasasron%2Fdeepnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmasasron%2Fdeepnet/lists"}