e3nn/e3nn: 2021-06-21

Mario Geiger, Tess Smidt, M Alby, B. Miller, Wouter Boomsma, Bradley D. Dice, Kostiantyn Lapchevskyi, Maurice Weiler, Michał Tyszkiewicz, Simon Batzner, Jes Frellsen, Jung, Nuri, Sophia Sanborn, Joshua A. Rackers, Michael Bailey · Zenodo (CERN European Organization for Nuclear Research) · 2021

[0.3.3] - 2021-06-21 Changed FullyConnectedNet is now a torch.nn.Sequential Fixed BatchNorm was not equivariant for pseudo-scalars Added biases argument to o3.Linear nn.models.v2106: MessagePassing takes a sequence of irreps nn.models.v2106: Convolution inpired from Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks

Read the paper · More papers on PaperTik