{"id":13528721,"url":"https://github.com/RobRomijnders/LSTM_tsc","last_synced_at":"2025-04-01T14:32:51.538Z","repository":{"id":106773749,"uuid":"55473163","full_name":"RobRomijnders/LSTM_tsc","owner":"RobRomijnders","description":"An LSTM for time-series classification","archived":false,"fork":false,"pushed_at":"2017-12-15T18:27:30.000Z","size":3442,"stargazers_count":408,"open_issues_count":13,"forks_count":146,"subscribers_count":35,"default_branch":"master","last_synced_at":"2024-11-02T15:36:11.265Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/RobRomijnders.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2016-04-05T06:24:27.000Z","updated_at":"2024-10-17T03:41:53.000Z","dependencies_parsed_at":"2023-05-05T21:12:44.811Z","dependency_job_id":null,"html_url":"https://github.com/RobRomijnders/LSTM_tsc","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/RobRomijnders%2FLSTM_tsc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RobRomijnders%2FLSTM_tsc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RobRomijnders%2FLSTM_tsc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/RobRomijnders%2FLSTM_tsc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/RobRomijnders","download_url":"https://codeload.github.com/RobRomijnders/LSTM_tsc/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246655221,"owners_count":20812601,"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":[],"created_at":"2024-08-01T07:00:23.290Z","updated_at":"2025-04-01T14:32:51.189Z","avatar_url":"https://github.com/RobRomijnders.png","language":"Python","funding_links":[],"categories":["Examples or singular models"],"sub_categories":[],"readme":"### Update 10-April-2017\nAnd now it works with Python3 and Tensorflow 1.1.0\n\n### Update 02-Jan-2017\nI updated this repo. Now it works with Tensorflow 0.12. In this readme I comment on some new benchmarks\n\n### LSTM for time-series classification\nThis post implements a Long Short-term memory for time series classification(LSTM). An LSTM is the extension of the classical Recurrent Neural Network. It has more flexibility and interpretable features such as a memory it can read, write and forget.\n\n## Aim\nThis repo aims to show the minimal Tensorflow code for proper time series classification. The main function loads the data and iterates over training steps. The *tsc_model.py* scripts contains the actual model.\nThis repo contrasts with [another project](http://robromijnders.github.io/CNN_tsc/) where I implement a similar script using convolutional neural networks as the model\n\n## Data and results\nThe code generalizes for any of the [UCR time series](http://www.cs.ucr.edu/~eamonn/time_series_data/). With the parameter *dataset* you can run the code on any of their datasets.\nFor your interests, you may compare performances with the nice overview in [this paper.](https://arxiv.org/pdf/1603.06995v4.pdf) They benchmark their CNN and other models on many of the UCR time series datasets\nThis code works amongst others for\n  * __Two_Patterns__ where it achieves state-of-the-art, bein 100% test accuracy\n  * __ChlorineConcentration__ where it achieves state-of-the-art, being 80% test accuracy\n\n# Credits\nCredits for this project go to [Tensorflow](https://www.tensorflow.org/versions/r0.7/tutorials/recurrent/index.html#recurrent-neural-networks) for providing a strong example, the [UCR archive](http://www.cs.ucr.edu/~eamonn/time_series_data/) for the dataset and my friend Ryan for strong feedback.\n\nLicense is in `LICENSE.txt`\n\nAs always, I am curious to any comments and questions. Reach me at romijndersrob@gmail.com\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRobRomijnders%2FLSTM_tsc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FRobRomijnders%2FLSTM_tsc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FRobRomijnders%2FLSTM_tsc/lists"}