# hfawaz/dl-4-tsc

Deep Learning for Time Series Classification

Repository: https://github.com/hfawaz/dl-4-tsc
Canonical: https://ross.abutalabs.com/products/dl-4-tsc
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: deep-learning, deep-neural-networks, time-series-classification, review, empirical-research, research-paper, convolutional-neural-networks
Last push: 2023-03-18T00:30:12+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2914, "days_push": 1265, "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 1659, forks 594 (observed 2026-08-28T04:05:18.256928+00:00)

## What it is
Companion repository for the paper 'Deep learning for time series classification: a review', providing TensorFlow 2 implementations of nine deep neural network architectures for time series classification. It includes scripts to run experiments on the UCR/UEA and MTS archives, with a Docker image for reproducibility.

## Use cases
- classify time series with deep learning
- reproduce benchmark results from the TSC review paper
- compare FCN and ResNet architectures on UCR datasets
- run time series classification experiments on multivariate datasets
- get reference TensorFlow implementations of TSC models

## When to choose
- you need reference implementations of the nine deep learning models benchmarked for time series classification
- you want to reproduce or extend the empirical results of the review paper
- you need a reproducible Docker-based setup for TSC experiments on UCR/UEA data

## When to avoid
- you need a production-ready or actively maintained time series classification library
- you want scikit-learn-style APIs or easy integration into application pipelines
- you need models beyond the nine architectures covered in the paper

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, benchmarking
- domain: deep-learning, machine-learning, time-series, data-science
- platform: python
- tags: time-series-classification, tensorflow, research-code, ucr-archive, resnet, fcn, paper-companion, research, docker, gpu, linux

## Member repositories
- hfawaz/dl-4-tsc (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:18.256928+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 2026-08-30T03:44:42.140628+00:00, confidence not recorded.
  - readme: https://github.com/hfawaz/dl-4-tsc (fetched 2026-08-28T04:05:18.256928+00:00, sha de9016f5c129)
- Data as of 2026-08-30T08:39:29.467469+00:00.