# thuml/TimesNet

About Code release for "TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis" (ICLR 2023), https://openreview.net/pdf?id=ju_Uqw384Oq

Repository: https://github.com/thuml/TimesNet
Canonical: https://ross.abutalabs.com/products/timesnet
License: MIT
License Family: permissive
Last push: 2024-04-02T17:50:56+00:00

## Health v2 (maintenance only)
Score: 31/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 92
- inputs: {"age_days": 1295, "days_push": 883, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1111, forks 90 (observed 2026-08-28T04:03:37.624416+00:00)

## What it is
TimesNet is the official code release for the ICLR 2023 paper on temporal 2D-variation modeling for general time series analysis. It transforms 1D time series into 2D space to handle forecasting, imputation, anomaly detection, and classification, with complete code now merged into the Time-Series-Library repository.

## Use cases
- forecast long-term and short-term time series
- detect anomalies in time series data
- impute missing values in time series
- classify time series signals
- benchmark time series models against baselines
- reproduce TimesNet paper results

## When to choose
- you need a general-purpose deep learning model for multiple time series tasks
- you want state-of-the-art baselines for time series research
- you want to build on 2D-variation time series modeling via Time-Series-Library

## When to avoid
- you need actively developed standalone code - use the Time-Series-Library repo instead
- you need simple statistical forecasting rather than deep learning
- you work outside time series analysis

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, data-science
- domain: time-series, machine-learning, deep-learning, data-science
- platform: python
- tags: time-series-forecasting, anomaly-detection, imputation, classification, research-code, iclr-2023, pytorch, gpu

## Member repositories
- thuml/TimesNet (main) score 31

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:37.624416+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:43:24.953733+00:00, confidence not recorded.
  - readme: https://github.com/thuml/TimesNet (fetched 2026-08-28T04:03:37.624416+00:00, sha 62bc5b1f77f6)
- Data as of 2026-08-30T08:39:29.467469+00:00.