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

Update README and add print in demo

Browse Source 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
2021-11-24 18:08:41 +01:00
parent 0707c26bbd
commit bbae618118
2 changed files with 18 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+10 -4
View File
@@ -17,9 +17,15 @@ If you use tkDNN in your research, please cite the [following paper](https://iee
} }
``` ```
### What's new (November 2021) ### What's new
- [x] Support to sematic segmentation on cuda 11+ [README](docs/README_seg.md) #### 20 July 2021
- [x] Support to TensorRT8 - [x] Support to sematic segmentation [README](docs/README_seg.md)
- [x] Support 2D/3D Object Detection and Tracking [README](docs/README_2d3dtracking.md)
#### 24 November 2021
- [x] Support to sematic segmentation on cuda 11
- [x] Support to TensorRT8.
TensorRT8 (and therefore Jetpack 4.6) is currently supported only on the branch tensort8 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
@@ -81,7 +87,7 @@ Results for COCO val 2017 (5k images), on RTX 2080Ti, with conf threshold=0.001
## Dependencies ## Dependencies
This branch works on every NVIDIA GPU that supports the following (latest tested) dependencies: This branch works on every NVIDIA GPU that supports the following (latest tested) dependencies:
* CUDA 11.3 (or >= 10.2) [the segmentation only works with CUDA 10 for now] * CUDA 11.3 (or >= 10.2)
* cuDNN 8.2.1 (or >= 8.0.4) * cuDNN 8.2.1 (or >= 8.0.4)
* TensorRT 8.0.3 (or >=7.2) * TensorRT 8.0.3 (or >=7.2)
* OpenCV 4.5.4 (or >=4) * OpenCV 4.5.4 (or >=4)
demo/demo/demo.cpp
+8 -6
View File
@@ -62,12 +62,14 @@ int main(int argc, char *argv[]) {
bool show = YAMLgetConf<bool>(conf, "show", true); bool show = YAMLgetConf<bool>(conf, "show", true);
bool save = YAMLgetConf<bool>(conf, "save", false); bool save = YAMLgetConf<bool>(conf, "save", false);
std::cout <<"Net settings - net: "<< net
<<", ntype: "<< ntype
<<", n_classes: "<< n_classes
<<", n_batch: "<< n_batch
<<", conf_thresh: "<< conf_thresh<<"\n";
std::cout <<"Demo settings - input: "<< input
<<", show: "<< show
<<", save: "<< save<<"\n\n";
tk::dnn::Yolo3Detection yolo; tk::dnn::Yolo3Detection yolo;
tk::dnn::CenternetDetection cnet; tk::dnn::CenternetDetection cnet;