There is a newer version of the record available.

Published April 21, 2021 | Version 0.2.8
Software Open

e3nn/e3nn: 2021-04-21

Authors/Creators

  • 1. @atomicarchitects
  • 2. MIR group @ Harvard University
  • 3. University of Amsterdam
  • 4. University of Michigan
  • 5. Harvard
  • 6. Technical University of Denmark (DTU)
  • 7. Redwood Center for Theoretical Neuroscience

Description

[0.2.8] - 2021-04-21 Added
  • squared option to o3.Norm
  • e3nn.nn.models.v2104.voxel_convolution.Convolution made to be resolution agnostic
  • TensorProduct.visualize keyword argument aspect_ratio
Changed
  • ReducedTensorProducts is a (scriptable) torch.nn.Module
  • e3nn now requires the latest stable PyTorch, >=1.8.1
  • TensorProduct.visualize: color of paths based on w.pow(2).mean() instead of w.sum().sign() * w.abs().sum()
Fixed
  • No more NaN gradients of o3.Norm/nn.NormActivation at zero when using epsilon
  • Modules with @compile_mode('trace') can now be compiled when their dtype and the current default dtype are different
  • Fix errors in ReducedTensorProducts and add new tests

Files

e3nn/e3nn-0.2.8.zip

Files (719.3 kB)

Name Size Download all
md5:dfbaa803c5fe20fe2d587871bdc06957
719.3 kB Preview Download

Additional details

Related works

Is supplement to
https://github.com/e3nn/e3nn/tree/0.2.8 (URL)