{"id":33121492,"url":"https://github.com/keytoyze/visionts","last_synced_at":"2026-04-20T08:09:59.629Z","repository":{"id":255380678,"uuid":"847868750","full_name":"Keytoyze/VisionTS","owner":"Keytoyze","description":"Code for our paper \"VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters\".","archived":false,"fork":false,"pushed_at":"2025-08-13T08:19:39.000Z","size":3351,"stargazers_count":255,"open_issues_count":0,"forks_count":24,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-10-27T10:29:54.439Z","etag":null,"topics":["computer-vision","deep-learning","time-series"],"latest_commit_sha":null,"homepage":"https://arxiv.org/pdf/2408.17253","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/Keytoyze.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,"zenodo":null}},"created_at":"2024-08-26T17:44:52.000Z","updated_at":"2025-10-24T08:31:32.000Z","dependencies_parsed_at":"2024-08-29T17:07:09.921Z","dependency_job_id":"24f7d7b6-ec47-4efd-889e-f9f55ec25a13","html_url":"https://github.com/Keytoyze/VisionTS","commit_stats":null,"previous_names":["keytoyze/visionts"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Keytoyze/VisionTS","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Keytoyze%2FVisionTS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Keytoyze%2FVisionTS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Keytoyze%2FVisionTS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Keytoyze%2FVisionTS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Keytoyze","download_url":"https://codeload.github.com/Keytoyze/VisionTS/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Keytoyze%2FVisionTS/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286079811,"owners_count":27282121,"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":"2025-11-24T02:00:07.096Z","response_time":68,"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":["computer-vision","deep-learning","time-series"],"created_at":"2025-11-15T05:00:23.871Z","updated_at":"2025-11-24T17:00:55.544Z","avatar_url":"https://github.com/Keytoyze.png","language":"Python","funding_links":[],"categories":["Time Series and Neuroscience Learning"],"sub_categories":["Physics"],"readme":"\u003cdiv align=\"center\"\u003e\n\n\n# VisionTS\n\n\n_Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters_\n\n[![VisionTS](https://img.shields.io/badge/VisionTS-2408.17253-red)](https://arxiv.org/abs/2408.17253)\n[![VisionTS++](https://img.shields.io/badge/VisionTS++-2508.04379-red)](https://arxiv.org/abs/2508.04379)\n[![PyPI - Version](https://img.shields.io/pypi/v/visionts)](#-quick-start)\n[![AI horizon forecast](https://img.shields.io/badge/AI_horizon_forecast-black?logo=data%3Aimage%2Fjpeg%3Bbase64%2C%2F9j%2F4AAQSkZJRgABAQAAAQABAAD%2F2wCEAAQEBAQEBAQEBAQGBgUGBggHBwcHCAwJCQkJCQwTDA4MDA4MExEUEA8QFBEeFxUVFx4iHRsdIiolJSo0MjRERFwBBAQEBAQEBAQEBAYGBQYGCAcHBwcIDAkJCQkJDBMMDgwMDgwTERQQDxAUER4XFRUXHiIdGx0iKiUlKjQyNEREXP%2FCABEIADAAMAMBIgACEQEDEQH%2FxAAcAAABBAMBAAAAAAAAAAAAAAAHAAQFBgECCAP%2F2gAIAQEAAAAA4by52aKaakJyNMdZgMxvee73dCJ5%2Bdhg%2BLJ6J2IY7r6SS%2F%2FEABkBAAIDAQAAAAAAAAAAAAAAAAMGAQIEBf%2FaAAgBAhAAAAB33c9jJRYk3%2F%2FEABcBAAMBAAAAAAAAAAAAAAAAAAQFBwD%2F2gAIAQMQAAAATKm88APoWH%2F%2FxAAxEAABAwIEBQEFCQAAAAAAAAABAgMEAAUGERITByExUWEiFEFCUqIjM0NTYnFykZL%2F2gAIAQEAAT8A2vIraqLBXJdS0jmo%2B6pluehull4aVDqDW15FbRp%2B3ux0JcW2dJ5Z0Up%2BWuH0RsS7nd1oBRbYa5Az%2BckIR9Sgax2wJsOyYi0ZKmNuMvkfnsEA%2FSQa0I7GtCOxq28MYF0w6i0XF4x7zdmi5b9ZCUNqTza3Aef2x9Iy6dan4RkWqS9BuKFsSWjkpCyP7HcHuORrDWC02jAL8ua6lp29zUbQcUEExogOfX3KUr6aewUi%2FwCBr5boD6HZVuebuLKW1BatsDbeAA%2FcE%2Fxo2EglBfGoHIjlnTXC2%2BRrMm9vNJ0LaD4aK07oZJ0h0oz1BBPRXSm%2BNl6dmh5y%2BXVAKwfvTo%2FyFVd8W4uvU%2B3XbDlykyoVyKNKGnFOIYkdHGyPgyPNPisW8ULi3PTAi4jc24TLcYuNyigOrQPWv0n4lVhHipcmb5CEu%2FuuR3FbTmuTuBKXBp15EnmnrVvxSbriSTAvFxnQJUJx1U9DKQthaGAVLWkkjbJA8jtVx4vXl%2B5vzI7iGmiopS0G0FIa6BBBHMZVun56t2J7nbY78eLOeabeTodS2spC09ld6cmuOKKtymZy21JUHOhFT%2BIcqVZ%2FYk7aZDjSGX5KU5POtN5FKFKozFq%2FENbvmt39Vb3mt3zW7W95r%2F%2FEACURAAEEAQMDBQEAAAAAAAAAAAECAxESAAQFIRQxUSJCQ3GBof%2FaAAgBAgEBPwBWjoaqEHBtjR0Re%2BSf4M6UYlC3nrOpZcBSfefSR%2BZTVdEtIaZsSVBNzMTNe3jEadRWlLWlbEJsoqWY57AEY3uRaMoXBwbkoG1%2BfvHd4cdiTEeOM%2F%2FEACQRAAIBBAEDBQEAAAAAAAAAAAECAwAEERIFEyEjFDFRYnGR%2F9oACAEDAQE%2FAFuA42U5FNyzjlEtNfGRjb7kZxXWNRXfIcYHWZZAHcsNgAP7k009016L7z9PcPnUdiBjNPz19Musaup2HbAJZSPepbGOZdZUDD4IBr0SFdNFxVtw9taKywx4DEk%2Fpr%2F%2F2Q%3D%3D)](https://aihorizonforecast.substack.com/p/visionts-building-high-performance)\n[![机器之心](https://img.shields.io/badge/%E6%9C%BA%E5%99%A8%E4%B9%8B%E5%BF%83-black?logo=wechat\u0026logoColor=white)](https://mp.weixin.qq.com/s/vTPkbu5ANYBGO4KYKZfAyg)\n\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n    🔍\u0026nbsp;\u003ca href=\"#-about\"\u003eAbout\u003c/a\u003e\n    | 🚀\u0026nbsp;\u003ca href=\"#-quick-start\"\u003eQuick Start\u003c/a\u003e\n    | 📊\u0026nbsp;\u003ca href=\"#-evaluation\"\u003eEvaluation\u003c/a\u003e\n    | 🔗\u0026nbsp;\u003ca href=\"#-citation\"\u003eCitation\u003c/a\u003e\n\u003c/p\u003e\n\n## 🎉 What's New\n\n- 🔥 Aug 2025: We released [VisionTS++](https://arxiv.org/abs/2508.04379), a SOTA time series foundation model by continual pretraining visual MAE on large-scale time series data, supporting multi-channel forecasting and probablistic forecasting!\n\n- May 2025: Our paper is accepted by ICML 2025!\n\n- Nov 2024: VisionTS achieved the **#1** rank 🏆 for zero-shot point forecasting (MASE) on [GIFT-EVAL](https://huggingface.co/spaces/Salesforce/GIFT-Eval) (as of Nov 2024, surpassing Moirai, TimesFM, chronos, etc) — **without any time series training**!\n\n## 🔍 About\n\n\n- We propose **VisionTS**, a time series forecasting (TSF) foundation model building from rich, high-quality *natural images* 🖼️. \n\n  - This is conceptually different from the existing TSF foundation models (*text-based* 📝 or *time series-based* 📈), but it shows a comparable or even better performance **without any adaptation on time series data**.\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"figure/ltsf_performance_overview.png\" style=\"width:70%;\" /\u003e\n\u003c/div\u003e\n\n- We reformulate the TSF task as an image reconstruction task, which is further processed by a visual masked autoencoder ([MAE](https://arxiv.org/abs/2111.06377)). \n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"figure/method.png\" style=\"width: 70%;\" /\u003e\n\u003c/div\u003e\n\n## 🚀 Quick Start\n\nWe have uploaded our package to PyPI. Please first install [pytorch](https://pytorch.org/get-started/locally/), then running the following command for installing **VisionTS**:\n\n```bash\npip install visionts\n```\n\nThen, you can refer to [demo.ipynb](demo.ipynb) about forecasting time series using **VisionTS**, with a clear visualization of the image reconstruction. \n\n\n## 📊 Evaluation\n\nOur repository is built on [Time-Series-Library](https://github.com/thuml/Time-Series-Library), [MAE](https://github.com/facebookresearch/mae), and [GluonTS](https://github.com/awslabs/gluonts). Please install the dependencies through `requirements.txt` before running the evaluation.\n\n#### Long-Term TSF Benchmarks (Zero-Shot)\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"figure/ltsf_performance.png\" style=\"width: 70%;\" /\u003e\n\u003c/div\u003e\n\n\nWe evaluate our methods on 6 long-term TSF benchmarks for zero-shot forecasting. The scripts are under `long_term_tsf/scripts/vision_ts_zeroshot`. Before running, you should first follow the instructions of [Time-Series-Library](https://github.com/thuml/Time-Series-Library) to download datasets into `long_term_tsf/dataset`. Using the following command for reproduction:\n\n\n```bash\ncd long_term_tsf/\nbash scripts/vision_ts_zeroshot/$SOME_DATASET.sh\n```\n\n#### Monash (Zero-Shot)\n\n\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"figure/monash_performance.png\" style=\"width: 50%;\" /\u003e\n\u003c/div\u003e\n\n\nWe evaluate our methods on 29 Monash TSF benchmarks. You can use the following command for reproduction, where the benchmarks will be automatically downloaded.\n\n\n```bash\ncd eval_gluonts/\nbash run_monash.sh\n```\n\n\u003e [!IMPORTANT]\n\u003e The results in the paper are evaluated based on `python==3.8.18`, `torch==1.7.1`, `torchvision==0.8.2`, and `timm==0.3.2`. Different versions may lead to slightly different performance.\n\n#### PF (Zero-Shot)\n\nWe evaluate our methods on 6 long-term TSF benchmarks for zero-shot forecasting. Before running, you should first follow the instructions of [Time-Series-Library](https://github.com/thuml/Time-Series-Library) to download datasets into `long_term_tsf/dataset`, in addition to the following three datasets:\n\n- Walmart: https://www.kaggle.com/competitions/walmart-recruiting-store-sales-forecasting/overview (download to `long_term_tsf/dataset/walmart-recruiting-store-sales-forecasting/train.csv`)\n- Istanbul Traffic: https://www.kaggle.com/datasets/leonardo00/istanbul-traffic-index (download to `long_term_tsf/dataset/istanbul-traffic-index/istanbul_traffic.csv`)\n- Turkey Power: https://www.kaggle.com/datasets/dharanikra/electrical-power-demand-in-turkey  (download to `long_term_tsf/dataset/electrical-power-demand-in-turkey/power Generation and consumption.csv`)\n\nYou can use the following command for reproduction.\n\n```bash\ncd eval_gluonts/\nbash run_pf.sh\n```\n\n#### Long-Term TSF Benchmarks (Full-Shot)\n\n\nWe evaluate our methods on 8 long-term TSF benchmarks for full-shot forecasting. The scripts are under `long_term_tsf/scripts/vision_ts_fullshot`. Using the following command for reproduction:\n\n\n```bash\ncd long_term_tsf/\nbash scripts/vision_ts_fullshot/$SOME_DATASET.sh\n```\n\n\n## 🔗 Citation\n\n```bibtex\n@misc{chen2024visionts,\n      title={VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters}, \n      author={Mouxiang Chen and Lefei Shen and Zhuo Li and Xiaoyun Joy Wang and Jianling Sun and Chenghao Liu},\n      year={2024},\n      eprint={2408.17253},\n      archivePrefix={arXiv},\n      url={https://arxiv.org/abs/2408.17253}, \n}\n```\n\n## ⭐ Star History\n\n\n\u003cdiv align=\"center\"\u003e\n    \u003ca href=\"https://star-history.com/#Keytoyze/VisionTS\u0026Timeline\"\u003e\n        \u003cimg src=\"https://api.star-history.com/svg?repos=Keytoyze/VisionTS\u0026type=Timeline\" style=\"width: 70%;\" /\u003e\n    \u003c/a\u003e\n\u003c/div\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeytoyze%2Fvisionts","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkeytoyze%2Fvisionts","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkeytoyze%2Fvisionts/lists"}