Detecto supports building and training computer vision models with the PyTorch machine learning framework.
PyTorch Geometric Temporal
PyTorch Geometric Temporal provides models and tools for spatiotemporal signal processing with neural learning.

About PyTorch Geometric Temporal
PyTorch Geometric Temporal is an open-source extension library for PyTorch Geometric. It provides dynamic and temporal geometric deep learning, embedding, and spatiotemporal regression methods drawn from published research papers. It also includes a dataset loader, a train-test splitter, and a temporal snapshot iterator for dynamic and temporal graphs.
The library ships with benchmark datasets from epidemiological forecasting, sharing economy, energy production, and web traffic management, and users can create their own datasets. The repository states that it supports GPUs and integrates with PyTorch Lightning for training on CPUs and single or multiple GPUs. Its homepage also describes index-batching and distributed data parallel training with Dask-DDP as memory-efficiency options, and points to case study tutorials and examples for its recurrent and attention-based models.
Key features
- Recurrent and attention-based dynamic and temporal graph neural network methods
- Dataset loader, train-test splitter, and temporal snapshot iterator for dynamic graphs
- Benchmark datasets from epidemiological, sharing economy, energy, and web traffic domains
- Support for creating custom datasets
- Index-batching to improve spatiotemporal memory efficiency
- Distributed data parallel training using Dask-DDP with index-batching
- Open source, with the code and examples hosted on GitHub
- Includes benchmark datasets from several named application domains
- Documented integration with PyTorch Lightning for CPU and GPU training
PyTorch Geometric Temporal at a glance
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
PyTorch Geometric Temporal alternatives
Tools and sites you could use instead, ranked by how closely they match.
PyTorch Lightning extension that accelerates and enhances foundation model experimentation with flexible fine-tuning schedules.
Katib automates machine learning on Kubernetes, including hyperparameter tuning and neural architecture search.
Learnergy is a Python library for energy-based machine learning models.
FEDOT automates machine learning model development through its modeling framework.
Enables single machine or distributed training and evaluation of deep learning models.
Popular in ML Training & Optimization
Well-known listings from the same topic.
PyTorch Geometric Temporal FAQ
Can I use my own data with the library?
Does the library support GPU training?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












