Commits · 8ebfd2f5d5f1792ce2cf5a2329320f604530a68e · OpenDAS / vision

14 Jan, 2021 1 commit

Improve speed/accuracy of FasterRCNN by introducing a score threshold on RPN (#3205) · 8ebfd2f5

Vasilis Vryniotis authored Jan 14, 2021



* Introduce small score threshold on rpn

* Adding docs and fixing keypoint and mask.

* Making value 0.0 by default for BC.

* Fixing for onnx.

* Update threshold.

* Removing non-default threshold from reference scripts.
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

8ebfd2f5

27 Nov, 2020 1 commit

Support for image with no annotations in RetinaNet (#3032) · 4ab46e5f

Vasilis Vryniotis authored Nov 27, 2020

* Enable support for images without annotations

* Ensuring gradient propagates to RegressionHead.

* Rewriting losses to remove branching.

* Fix the seed on DeformConv autocast test.

4ab46e5f

07 Apr, 2020 1 commit
- Add tests for negative samples for Mask R-CNN and Keypoint R-CNN (#2069) · 51d694e1
  Francisco Massa authored Apr 07, 2020
```
* Add tests for negative samples for Mask R-CNN and Keypoint R-CNN

* Fix lint
```
  51d694e1
20 Mar, 2020 1 commit

Train Faster R-CNN with negative samples (#1911) · e75b4973

Monica Alfaro authored Mar 20, 2020



* modified FasterRCNN to accept negative samples

* remove debug lines

* Change torch.zeros_like to torch.zerros

* Add unit tests

* take the `device` into account
Co-authored-by: Francisco Massa <fvsmassa@gmail.com>

e75b4973