{"id":16776054,"url":"https://github.com/napsternxg/deepsequenceclassification","last_synced_at":"2025-03-22T00:30:54.089Z","repository":{"id":137717011,"uuid":"48568680","full_name":"napsternxg/DeepSequenceClassification","owner":"napsternxg","description":"Deep neural network based model for sequence to sequence classification","archived":false,"fork":false,"pushed_at":"2017-11-22T04:19:42.000Z","size":35,"stargazers_count":77,"open_issues_count":1,"forks_count":20,"subscribers_count":9,"default_branch":"master","last_synced_at":"2025-03-01T11:11:14.286Z","etag":null,"topics":["deep-neural-networks","named-entity-recognition","sequence-classification"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/napsternxg.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}},"created_at":"2015-12-25T06:03:22.000Z","updated_at":"2025-02-27T03:18:08.000Z","dependencies_parsed_at":null,"dependency_job_id":"172180f9-8858-48f7-b4f9-d7b0300a718f","html_url":"https://github.com/napsternxg/DeepSequenceClassification","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/napsternxg%2FDeepSequenceClassification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/napsternxg%2FDeepSequenceClassification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/napsternxg%2FDeepSequenceClassification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/napsternxg%2FDeepSequenceClassification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/napsternxg","download_url":"https://codeload.github.com/napsternxg/DeepSequenceClassification/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244166863,"owners_count":20409210,"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-neural-networks","named-entity-recognition","sequence-classification"],"created_at":"2024-10-13T07:08:53.082Z","updated_at":"2025-03-22T00:30:53.614Z","avatar_url":"https://github.com/napsternxg.png","language":"Python","readme":"[![Twitter Follow](https://img.shields.io/twitter/follow/TheShubhanshu.svg?style=social)](https://twitter.com/TheShubhanshu)\n[![GitHub license](https://img.shields.io/github/license/napsternxg/DeepSequenceClassification.svg)](https://github.com/napsternxg/DeepSequenceClassification/edit/master/LICENSE)\n\n# Deep Sequence Classification\n\nGeneric library for training models for deep neural networks for text sequence classification tasks. \n\n## Usage:\n\n* Create a json file `config.json` (default name) using the template in `config.json.sample` and specify the parameters for your training. \n* Best strategy is to save the training and test files in vector format in advance and then give their paths in `data_vectors` parameter in the file. \n\n* Train a model:\n```\npython model.py --config config_multitask.json --verbose 1\n```\n\n* Resume training from saved weights:\n```\npython model.py --config config_multitask.json --verbose 1 --weights output/models/model_multi_brnn_multitask_h2-45.h5 --base_epochs 45\n```\n\n## Preprocessing:\n\n* Currently, we support the preprocessing for the following file formats:\n```\n\u003cROOT\u003e\u003cDOC\u003e\n\u003cDOCNO\u003e DOCUMENT 1 \u003c/DOCNO\u003e\n     For \u003cTIME TYPE=\"DATE:DATE\"\u003esix years\u003c/TIME\u003e , \u003cENTITY TYPE=\"PERSON\"\u003eShubhanshu A. B. Mishra\u003c/ENTITY\u003e has made several programming projects after being inspired by \u003cENTITY TYPE=\"PERSON\"\u003eLinus Torvalds\u003c/ENTITY\u003e, a very renowned programmer.\n\u003c/DOC\u003e\u003c/ROOT\u003e\n```\n* Each file can contain multiple `DOCNO`. \n* The dir structure consists of many folders of data split for cross validation. It is as follows:\n```\ndata/\ndata/CV_files\ndata/CV_files/1/file1.xml\ndata/CV_files/1/file2.xml\ndata/CV_files/1/file3.xml\n...\n\ndata/CV_files/5/file1.xml\ndata/CV_files/5/file2.xml\n```\n\n## Supports:\n* Boundary and Category Detection\n* Simple RNN and Bidirectional RNN\n* Multi task sequence learning (Boundary + Category trained using same model)\n* CNN + BRNN\n\n## Coming Up:\n\n## Use Cases:\n* Named Entity Recognition\n* POS Tagging\n* Dependency Parsing\n\n## Author:\n* Shubhanshu Mishra\n\n## Dependencies:\n* Theano\n* Keras\n* BeautifulSoup (with lxml)\n* numpy\n* lxml (requires libxml2, libxslt and libxml2-dev)\n\n\nInstall theano and keras using the following commands:\n```\npip install --user --upgrade --no-deps git+git://github.com/Theano/Theano.git\npip install --user --upgrade --no-deps git+git://github.com/fchollet/keras.git\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnapsternxg%2Fdeepsequenceclassification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnapsternxg%2Fdeepsequenceclassification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnapsternxg%2Fdeepsequenceclassification/lists"}