v0.7.4
版本发布时间: 2023-05-10 23:14:23
facebookresearch/pytorch3d最新发布版本:v0.7.7(2024-06-27 19:32:25)
A small release. It also has builds for PyTorch 2.0.1
Minor new features
- Saving normals to OBJ https://github.com/facebookresearch/pytorch3d/commit/092400f1e79826cbb503b5f309c2d55cd5ca43ef
- Saving TexturesVertex to GLB https://github.com/facebookresearch/pytorch3d/commit/178a7774d4424ca2f0047a8d48aa40c39b67e1d2
- Implicitron can now read from a new dataset format which stores metadata in sqlite files. This requires the sqlalchemy library. https://github.com/facebookresearch/pytorch3d/commit/32e1992924929a9b79e880ed6f5bdc74089e8c73
Fixes
- Error in example in cameras.md https://github.com/facebookresearch/pytorch3d/commit/f5a117c74b3c34f1e2b4fb5dfa2e68dec2f42975
- Build fix with newer CUB https://github.com/facebookresearch/pytorch3d/commit/b921efae3e52dcd93e553db3d02378951e894769
- Warnings when we don’t obey user’s request of torch.use_deterministic_algorithms. Some cuda implementations in pytorch3d are non-deterministic. https://github.com/facebookresearch/pytorch3d/commit/ef5f620263562657a022dee419abd63534d123e7
- Implicitron evaluation still works when ground truth depth map is not supplied https://github.com/facebookresearch/pytorch3d/commit/0e3138eca89336d222d9338687741da824a39443
- Loading bounding boxes in Co3D-type datasets in implicitron was failing when masks were not requested https://github.com/facebookresearch/pytorch3d/commit/7aeedd17a4140eef139987e946a7017df7a97433