DiffEqML/torchdyn
A PyTorch library for constructing and training neural differential equation models and numerical deep learning methods.
Not currently ranked — collecting fresh signals.
star history
Torchdyn provides utilities, layers, and functional APIs to build numerical deep learning models using neural differential equations (NeuralODE, NeuralSDE), implicit models, and GPU-compatible numerical methods. It integrates seamlessly with any PyTorch modules for composing composite models and includes tutorials and benchmarks for the deep learning research community.
Frequently asked
- What is DiffEqML/torchdyn?
- A PyTorch library for constructing and training neural differential equation models and numerical deep learning methods.
- Is torchdyn open source?
- Yes — DiffEqML/torchdyn is open source, released under the Apache-2.0 license.
- What language is torchdyn written in?
- DiffEqML/torchdyn is primarily written in Jupyter Notebook.
- How popular is torchdyn?
- DiffEqML/torchdyn has 1.6k stars on GitHub.
- Where can I find torchdyn?
- DiffEqML/torchdyn is on GitHub at https://github.com/DiffEqML/torchdyn.