mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

Update Readme

Browse Source 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
2021-11-24 18:20:26 +01:00
parent be5864748a
commit 24cdb4c4a7
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -2
View File
@@ -17,10 +17,15 @@ If you use tkDNN in your research, please cite the [following paper](https://iee
} }
``` ```
### What's new (20 July 2021) ### What's new
#### 20 July 2021
- [x] Support to sematic segmentation [README](docs/README_seg.md) - [x] Support to sematic segmentation [README](docs/README_seg.md)
- [x] Support 2D/3D Object Detection and Tracking [README](docs/README_2d3dtracking.md) - [x] Support 2D/3D Object Detection and Tracking [README](docs/README_2d3dtracking.md)
- [ ] Support to TensorRT8 (WIP) #### 24 November 2021
- [x] Support to sematic segmentation on cuda 11
- [x] Support to TensorRT8 (thanks to [Harshvardhan Chandirasekar](https://github.com/perseusdg)).
TensorRT8 (and therefore Jetpack 4.6) is currently supported only on the branch tensorrt8 due to [performance issue with TensorRT8](https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-8.html)). We will merge it to the master as soon as those issues are fixed (probably in future minor releases).
## FPS Results ## FPS Results
Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimension as the input size, on Inference FPS of yolov4 with tkDNN, average of 1200 images with the same dimension as the input size, on