# locuslab/TCN

Sequence modeling benchmarks and temporal convolutional networks

Repository: https://github.com/locuslab/TCN
Canonical: https://ross.abutalabs.com/products/tcn
Homepage: https://github.com/locuslab/TCN
Language: Python
License: MIT
License Family: permissive
Last push: 2022-03-28T16:33:16+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": 3106, "days_push": 1619, "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 4549, forks 888 (observed 2026-08-28T04:08:53.278491+00:00)

## What it is
PyTorch implementation of Temporal Convolutional Networks (TCN) with benchmarks from the paper 'An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling'. It includes experiment code for tasks like the adding problem, sequential MNIST, polyphonic music, and language modeling.

## Use cases
- implement a temporal convolutional network in pytorch
- compare TCN against LSTM and GRU on sequence tasks
- run the adding problem benchmark
- train a model on sequential MNIST
- reproduce TCN language modeling results on PennTreebank
- learn how dilated causal convolutions work

## When to choose
- you need a reference TCN implementation in PyTorch
- you want to benchmark convolutions vs recurrent networks on sequence modeling
- you are reproducing the Bai et al. 2018 paper

## When to avoid
- you need a production-ready, actively maintained sequence modeling library
- you want a pip-installable package with an API rather than per-task scripts
- you need support for old PyTorch versions or modern features like mixed precision

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, benchmarking
- domain: deep-learning, machine-learning
- platform: python
- tags: temporal-convolutional-network, pytorch, sequence-modeling, research-code, benchmarks, natural-language-processing

## Member repositories
- locuslab/TCN (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.278491+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 2026-08-29T18:20:05.495989+00:00, confidence not recorded.
  - readme: https://github.com/locuslab/TCN (fetched 2026-08-28T04:08:53.278491+00:00, sha 346b345ff451)
  - homepage: https://github.com/locuslab/TCN (fetched 2026-08-29T09:05:46.277528+00:00, sha 17c295beaa39)
- Data as of 2026-08-30T08:39:29.467469+00:00.