flâneur

DiffEqML/torchdyn: A PyTorch based library for all things neural differential equations

github.com · 653 words · saved by 1 readers

A PyTorch based library for all things neural differential equations

Quick Start Torchdyn provides utilities and layers to easily construct numerical deep learning models. For example, neural differential equations: from torchdyn.core import NeuralODE # your preferred torch.nn.Module here f = nn.Sequential(nn.Conv2d(1, 32, 3), nn.Softplus(), nn.Conv2d(32, 1, 3) ) nde = NeuralODE(f) And you have a trainable model. Feel free to combine Torchdyn classes with any PyTorch modules to build composite models. We offer additional tools to build custom neural differential equation and implicit models, including a functional API for numerical methods. There is much…

saved by

related reading