# ndrplz/ConvLSTM_pytorch

Implementation of Convolutional LSTM in PyTorch.

Repository: https://github.com/ndrplz/ConvLSTM_pytorch
Canonical: https://ross.abutalabs.com/products/convlstm_pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2020-07-26T03:06:51+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": 3316, "days_push": 2229, "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 2267, forks 444 (observed 2026-08-28T04:06:32.790844+00:00)

## What it is
A PyTorch implementation of the Convolutional LSTM (ConvLSTM) neural network module, provided as a reusable nn.Module supporting arbitrary layer counts and configurable hidden dimensions and kernel sizes. It is a small, single-file research library for spatiotemporal sequence modeling.

## Use cases
- implement convlstm in pytorch
- spatiotemporal sequence prediction model
- video frame prediction neural network
- precipitation nowcasting with deep learning
- use lstm with convolutional layers for image sequences

## When to choose
- you need a ready-made ConvLSTM layer in a PyTorch project
- you want a lightweight, MIT-licensed module you can drop into existing models
- you need multi-layer ConvLSTM with per-layer hidden dimensions and kernel sizes

## When to avoid
- you need stateful inference or extensive documentation - it is a work in progress
- you need a maintained library with recent releases (last release 2020)
- you work outside PyTorch, e.g. TensorFlow or JAX

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, computer-vision
- platform: python
- tags: convlstm, pytorch, spatiotemporal, neural-networks, sequence-modeling

## Member repositories
- ndrplz/ConvLSTM_pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:32.790844+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 2026-08-30T02:42:12.084577+00:00, confidence not recorded.
  - readme: https://github.com/ndrplz/ConvLSTM_pytorch (fetched 2026-08-28T04:06:32.790844+00:00, sha b0c83b70379e)
- Data as of 2026-08-30T08:39:29.467469+00:00.