{"id":15908314,"url":"https://github.com/jegp/multimodalrnnproject","last_synced_at":"2025-11-17T13:59:25.274Z","repository":{"id":142393241,"uuid":"92779488","full_name":"Jegp/multimodalrnnproject","owner":"Jegp","description":"A project on using RNN on multimodal data for person recognition","archived":false,"fork":false,"pushed_at":"2017-06-06T20:53:27.000Z","size":16563,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-03T00:25:26.460Z","etag":null,"topics":[],"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-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Jegp.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":"2017-05-29T22:21:12.000Z","updated_at":"2024-01-14T23:02:12.000Z","dependencies_parsed_at":null,"dependency_job_id":"49968c3b-1f87-4e24-9754-986c28a3630f","html_url":"https://github.com/Jegp/multimodalrnnproject","commit_stats":{"total_commits":8,"total_committers":1,"mean_commits":8.0,"dds":0.0,"last_synced_commit":"1e31ad7f093d6374285bb325430f9ff5910f4f34"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Jegp/multimodalrnnproject","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fmultimodalrnnproject","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fmultimodalrnnproject/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fmultimodalrnnproject/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fmultimodalrnnproject/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Jegp","download_url":"https://codeload.github.com/Jegp/multimodalrnnproject/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Jegp%2Fmultimodalrnnproject/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":284893575,"owners_count":27080531,"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","status":"online","status_checked_at":"2025-11-17T02:00:06.431Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2024-10-06T14:20:43.009Z","updated_at":"2025-11-17T13:59:25.259Z","avatar_url":"https://github.com/Jegp.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multimodal RNNs\nA project on using recurrent neural networks (LSTMs) on multimodal data for person recognition\n\n## Prerequisites\nTo run this project you need to install\n\n* Python 3\n* Keras - deep learning framework\n* Tensorflow or Theano - machine learning frameworks (required by Keras)\n* Matplotlib\n\nTo use the hyperparameter tuning, you are required to install Hyperas (Keras + Hyperopt),\nwhich can be found here: https://github.com/maxpumperla/hyperas\n\nAll of the above can be installed using pip. I strongly recommend doing this in a virtualenv.\n\n## File layout\nWe have tree models: one using only audio data, one using only video data and one using both\n(dualmodal).\n\nThe files containing ``hyper`` is concerned with hyper-parameter optimisation, while the files\n``unimodal_audio.py``, ``unimodal_video.py`` and ``dualmodal.py`` contains the optimised\nmodel parameters.\n\n## How to use\nTo run the already optimized files, simply pull this project and run\n\n    python3 dualmodal.py\n\nThis example runs the dualmodal model.\n\n### Pre-processing\nTo run the pre-processing step, you need to download the GRID dataset (http://spandh.dcs.shef.ac.uk/gridcorpus/)\ninto the same folder as this repository. To run the pre-processing, simply run the ``pre_chunks.py`` file:\n\n    python3 pre_chunks.py\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjegp%2Fmultimodalrnnproject","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjegp%2Fmultimodalrnnproject","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjegp%2Fmultimodalrnnproject/lists"}