Commits · bf4914632176f868bde1553a6b58782eb5b75196 · OpenDAS / vision

"vscode:/vscode.git/clone" did not exist on "c07b91c89d0d02a3d0494d730fb5c67d54f05230"

30 May, 2025 1 commit
- add v0.19.1 release · bf491463
  limm authored May 30, 2025
  
  bf491463
19 May, 2021 1 commit

Added CUDA support for interpolation AA bilinear/bicubic (#3842) · 3c47bfdf

vfdev authored May 19, 2021

* Added CUDA support for interpolation AA bilinear/bicubic

* Fixed code formatting error

* Fixed cuda tests on cpu-only builds

* Fixed cuda internal torch check for bicubic mode

3c47bfdf

15 Feb, 2021 1 commit

Fix NMS and IoU overflows for fp16 (#3383) · f04e9cb9

Vasilis Vryniotis authored Feb 15, 2021

* Replace type T with accumulator.

* Upcast tensors of box ops to avoid overflow in multiplications.

f04e9cb9

29 Jan, 2021 1 commit
- Remove unneded ifdef in nms_kernel.cu (#3326) · 09ce6758
  Francisco Massa authored Jan 29, 2021
```
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
```
  09ce6758
14 Jan, 2021 1 commit
- Update to clang-format 11. (#3254) · ae87c1e4
  Vasilis Vryniotis authored Jan 14, 2021
  
  ae87c1e4
04 Jan, 2021 1 commit
- Add Torch Selective macros in all C++ Ops for better support on mobile (#3218) · 3711754a
  Vasilis Vryniotis authored Jan 04, 2021
```
* Adding TORCH_SELECTIVE_* macros on op registration.

* Adding torchvision namespace.
```
  3711754a
10 Dec, 2020 1 commit

Restructuring C++ project: (#3146) · 7d831a2f

Vasilis Vryniotis authored Dec 10, 2020

Summary:
* Reduce unnecessary header inclusions in models and io.

* Move autocast to separate folder and hide autograd implementation in an anonymous namespace.

* Moving files in subfolders.

Reviewed By: fmassa

Differential Revision: D25461523

fbshipit-source-id: 756eeb6848aacaa474de4825ed4c1045d17e2cea

7d831a2f