github-featured/nvidia--tensorrt
2
0
Fork 0
Code Issues Pull Requests Deployments Models Agent Notes Packages Projects Releases Wiki Activity
224 Commits 42 Branches 72 Tags
master
Commit Graph

4 Commits

Author SHA1 Message Date
William Raveane 532557026e EfficientNMS: Dynamic Input Shape 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-09-22 12:55:39 -07:00
Stephan Seitz 5a44e7b7c9 Fix assertion in EfficientNMSPlugin 
Documentation states:
```cpp
    // Shape of boxes input should be
    // [batch_size, num_boxes, 4] or [batch_size, num_boxes, 1, 4] or [batch_size, num_boxes, num_classes, 4]
```
however, the second possibility `[batch_size, num_boxes, 1, 4]` triggers a false positive in an
assertion. The third dimension must be either equal to 1 or the number
of classes.

Signed-off-by: Stephan Seitz <sseitz@nvidia.com>
 2021-09-22 10:24:46 -07:00
William Raveane 3235cc2ffc EfficientNMS Updates: Empty Input Tensor + TX1/TX2 Resources 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-07-08 14:50:27 -07:00
Rajeev Rao aff45dd565 TensorRT OSS 8.0 release 
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
 2021-07-02 16:35:44 -07:00