mirror of
https://github.com/facebookresearch/pytorch3d.git
synced 2025-08-03 20:32:51 +08:00
bce396df93
Summary: C++/CUDA implementation of forward and backward passes for the sigmoid alpha blending function. This is slightly faster than the vectorized implementation in Python, but more importantly uses less memory due to fewer tensors being created. Reviewed By: gkioxari Differential Revision: D19980671 fbshipit-source-id: 0779055d2c68b1f20fb0870e60046077ef4613ff