Some calculus with torch::autograd
Most neural networks learn by minimizing a scalar-valued error. There is ample information about the back-propagation calculus in neural networks, like this great video. …
tags
Deep-Learning
Training a PyTorch neural network on cell-centered OpenFOAM fields
This post covers the use of the PyTorch C++ API for approximating cell-centered fields (pressure, temperature, density, etc.) in OpenFOAM using a Neural Network (NN). The training …