Published April 13, 2022
| Version 0.5.0
Software
Open
e3nn/e3nn: 2022-04-13
Creators
- 1. @atomicarchitects
- 2. @mir-group @ Harvard University
- 3. University of Amsterdam
- 4. @NVIDIA
- 5. Harvard
- 6. Technical University of Denmark (DTU)
- 7. @seoklab
- 8. Redwood Center for Theoretical Neuroscience
- 9. University of California, Berkeley
Description
[0.5.0] - 2022-04-13 Added
- Sparse Voxel Convolution
- Clebsch-Gordan coefficients are computed via a change of basis from the complex to real basis.
o3
,nn
andio
are accessible throughe3nn
. For instancee3nn.o3.rand_axis_angle
.
- Since now the code is no more tested against
torch==1.8.0
, only tested againsttorch>=1.10.0
wigner_3j
now always returns a contiguous copy regardless of dtype or device
Files
e3nn/e3nn-0.5.0.zip
Files
(488.9 kB)
Name | Size | Download all |
---|---|---|
md5:8855c629c401354a72376087bbb2c71a
|
488.9 kB | Preview Download |
Additional details
Related works
- Is supplement to
- https://github.com/e3nn/e3nn/tree/0.5.0 (URL)