ndrplz/ConvLSTM_pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2267 stars · 444 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning computer-vision python convlstm pytorch spatiotemporal neural-networks sequence-modeling

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ndrplz/ConvLSTM_pytorch")