Escnn, built on PyTorch, is a library that, in the spirit of Geometric Deep Learning, provides a high-level interface to designing and training group-equivariant neural networks. This post introduces important mathematical concepts, the library’s key actors,…
We code up a simple group-equivariant convolutional neural network (GCNN) that is equivariant to rotation. The world may be upside down, but the network will know. Convolutional neural networks (CNNs) are great – they’re able to…
This post introduces deep learning on graphs by mapping its central concept - message passing - to minimal usage patterns of PyTorch Geometric’s foundation-laying MessagePassing class. Exploring those patterns, we gain some basic, very concrete insights…