{"id":13665696,"url":"https://github.com/okrasolar/pytorch-timeseries","last_synced_at":"2025-04-26T08:32:58.263Z","repository":{"id":44736663,"uuid":"211461433","full_name":"okrasolar/pytorch-timeseries","owner":"okrasolar","description":"PyTorch implementations of neural networks for timeseries classification","archived":false,"fork":false,"pushed_at":"2022-01-27T19:08:46.000Z","size":55,"stargazers_count":109,"open_issues_count":4,"forks_count":23,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-11T00:37:05.302Z","etag":null,"topics":["classification","deep-learning","machine-learning","pytorch","time-series"],"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/okrasolar.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":"2019-09-28T07:24:23.000Z","updated_at":"2024-11-03T22:54:42.000Z","dependencies_parsed_at":"2022-08-26T04:40:40.818Z","dependency_job_id":null,"html_url":"https://github.com/okrasolar/pytorch-timeseries","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/okrasolar%2Fpytorch-timeseries","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/okrasolar%2Fpytorch-timeseries/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/okrasolar%2Fpytorch-timeseries/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/okrasolar%2Fpytorch-timeseries/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/okrasolar","download_url":"https://codeload.github.com/okrasolar/pytorch-timeseries/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250960611,"owners_count":21514487,"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":["classification","deep-learning","machine-learning","pytorch","time-series"],"created_at":"2024-08-02T06:00:47.721Z","updated_at":"2025-04-26T08:32:53.239Z","avatar_url":"https://github.com/okrasolar.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"# pytorch-timeseries\n\nPyTorch implementations of deep neural neural nets for time series classification.\n\nCurrently, the following papers are implemented:\n* [InceptionTime: Finding AlexNet for Time Series Classification](https://arxiv.org/abs/1909.04939)\n* [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://arxiv.org/abs/1611.06455)\n\n### Beyond the UCR/UEA archive\nThere are two ways use the Inception Time model on your own data:\n\n1. Copy the [models](src/models), and write new training loops\n2. Extend the [base trainer](src/trainer.py) by implementing an initializer, `get_loaders` and `save`. \nThis allows the training code (which handles both single and multi-class outputs) to be used - an example of this is\nthe [`UCRTrainer`](src/ucr.py).\n\n### Setup\n\n[Anaconda](https://www.anaconda.com/download/#macos) running python 3.7 is used as the package manager. To get set up\nwith an environment, install Anaconda from the link above, and (from this directory) run\n\n```bash\nconda env create -f environment.yml\n```\nThis will create an environment named `inception` with all the necessary packages to run the code. To \nactivate this environment, run\n\n```bash\nconda activate inception\n```\n\nIn addition, [UCR/UEA archive](https://www.cs.ucr.edu/~eamonn/time_series_data/) must be downloaded and stored in the \n[data folder](data).\n\n### Scripts\n\nExample scripts showing how to train and evaluate the model can be found in the [scripts folder](scripts).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fokrasolar%2Fpytorch-timeseries","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fokrasolar%2Fpytorch-timeseries","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fokrasolar%2Fpytorch-timeseries/lists"}