423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2026-01-16 19:30:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

Adding utility methods to TensorProperties

Browse Source 
Summary:
Context: in the code we are releasing with CO3D dataset, we use  `cuda()` on TensorProperties like Pointclouds and Cameras where we recursively move batch to a GPU. It would be good to push it to a release so we don’t need to depend on the nightly build.

Additionally, I aligned the logic of `.to("cuda")` without device index to the one of `torch.Tensor` where the current device is populated to index. It should not affect any actual use cases but some tests had to be changed.

Reviewed By: bottler

Differential Revision: D29659529

fbshipit-source-id: abe58aeaca14bacc68da3e6cf5ae07df3353e3ce
This commit is contained in:
Roman Shapovalov
2021-07-13 10:28:41 -07:00
committed by Facebook GitHub Bot
parent fa44a05567
commit 0c02ae907e
6 changed files with 31 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tests/test_transforms.py
View File

@@ -50,9 +50,9 @@ class TestTransform(TestCaseMixin, unittest.TestCase):
self.assertEqual(torch.float32, t.dtype)
self.assertIsNot(t, cpu_t)
cuda_device = torch.device("cuda")
cuda_device = torch.device("cuda:0")
cuda_t = t.to("cuda")
cuda_t = t.to("cuda:0")
self.assertEqual(cuda_device, cuda_t.device)
self.assertEqual(cpu_device, t.device)
self.assertEqual(torch.float32, cuda_t.dtype)