{"id":18011126,"url":"https://github.com/birdx0810/timegan-pytorch","last_synced_at":"2025-03-26T14:32:25.321Z","repository":{"id":59983686,"uuid":"324125626","full_name":"birdx0810/timegan-pytorch","owner":"birdx0810","description":"This repository is a non-official implementation of TimeGAN (Yoon et al., NIPS2019) using PyTorch.","archived":false,"fork":false,"pushed_at":"2022-07-26T05:40:09.000Z","size":2239,"stargazers_count":84,"open_issues_count":2,"forks_count":36,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-21T23:43:02.846Z","etag":null,"topics":["deep-learning","generative-adversarial-network","hacktoberfest","pytorch","time-series"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/birdx0810.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}},"created_at":"2020-12-24T10:07:07.000Z","updated_at":"2025-03-10T06:55:32.000Z","dependencies_parsed_at":"2022-09-25T14:51:17.230Z","dependency_job_id":null,"html_url":"https://github.com/birdx0810/timegan-pytorch","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/birdx0810%2Ftimegan-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/birdx0810%2Ftimegan-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/birdx0810%2Ftimegan-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/birdx0810%2Ftimegan-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/birdx0810","download_url":"https://codeload.github.com/birdx0810/timegan-pytorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245670967,"owners_count":20653459,"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-learning","generative-adversarial-network","hacktoberfest","pytorch","time-series"],"created_at":"2024-10-30T02:22:31.855Z","updated_at":"2025-03-26T14:32:24.762Z","avatar_url":"https://github.com/birdx0810.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# timegan-pytorch\nThis repository holds the code for the reimplementation of TimeGAN ([Yoon et al., NIPS2019](https://papers.nips.cc/paper/8789-time-series-generative-adversarial-networks)) using PyTorch. Some of the code was derived from the original implementation [here](https://github.com/jsyoon0823/TimeGAN).\n\n\u003e :warning: WARNING!!!\n\u003e - This implementation is written for other purposes, not for experiments in the original paper.\n\u003e - There are some known issues that I've haven't got time to resolve (see issue [#1](https://github.com/d9n13lt4n/timegan-pytorch/issues/1#issuecomment-895126605)).\n\n## Getting Started\n### Installing Requirements\nThis implementation assumes Python3.8 and a Linux environment with a GPU is used.\n```bash\ncat requirements.txt | xargs -n 1 pip install --upgrade\n```\n\n### Directory Hierarchy\n```bash\ndata/                         # the folder holding the datasets and preprocessing files\n  ├ data_preprocessing.py     # the data preprocessing functions\n  └ stock.csv                 # the example stock data derived from the original repo\nmetrics/                      # the folder holding the metric functions for evaluating the model\n  ├ dataset.py                # the dataset class for feature predicting and one-step ahead predicting\n  ├ general_rnn.py            # the model for fitting the dataset during TSTR evaluation\n  ├ metric_utils.py           # the main function for evaluating TSTR\n  └ visualization.py          # PCA and t-SNE implementation for time series taken from the original repo\nmodels/                       # the code for the model\noutput/                       # the output of the model\nmain.py                       # the main code for training and evaluating TSTR of the model\nrequirements.txt              # requirements for running code\nrun.sh                        # the bash script for running model\nvisualization.ipynb           # jupyter notebook for running visualization of original and synthetic data\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbirdx0810%2Ftimegan-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbirdx0810%2Ftimegan-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbirdx0810%2Ftimegan-pytorch/lists"}