SLOW Semantic Segmentation on NVIDIA DRIVE Open Script
1 visualizzazione (ultimi 30 giorni)
Mostra commenti meno recenti
Paolo Rosettani
il 27 Set 2022
Commentato: Hariprasad Ravishankar
il 3 Ott 2022
Hello,
I'm using a NVIDIA Jetson AGX Xavier
I'm trying the Semantic Segmentation on NVIDIA DRIVE Open Script: https://it.mathworks.com/help/supportpkg/nvidia/ug/semantic-segmentation-on-nvidia-drive.html
I've only chaned the
opencv_link_flags = '`pkg-config --cflags --libs opencv`';
to
opencv_link_flags = '`pkg-config --cflags --libs opencv4`';
because without it it doesn't compile.
There is another problem: Why the FPS are so slow? Mine goes at 0.39 FPS (as shown in the screenshot below)
I've checked the screenshot in the example and it goes at 8.73 FPS.
![](https://www.mathworks.com/matlabcentral/answers/uploaded_files/1137880/image.png)
Thank you for your help.
Paolo R
0 Commenti
Risposta accettata
Hariprasad Ravishankar
il 30 Set 2022
Hi Paolo,
Can you try setting the deep learning target library to TensorRT?
cfg = coder.gpuConfig('exe');
cfg.DeepLearningConfig = coder.DeepLearningConfig(TargetLibrary = 'tensorrt');
Hari
1 Commento
Hariprasad Ravishankar
il 3 Ott 2022
In addition to this, you can also try the following to get a little bit more peformance.
1.TensorRT FP16 mode. Note that FP16 computation can result in lower accuracy from baseline FP32 computation.
cfg = coder.gpuConfig('exe');
dlcfg = coder.DeepLearningConfig(TargetLibrary = 'tensorrt');
dlcfg.DataType = 'FP16';
cfg.DeepLearningConfig = dlcfg;
2.You can use the nvpmodel tool to change the clock mode
For example:
sudo nvpmodel -m 0
Più risposte (0)
Vedere anche
Categorie
Scopri di più su Get Started with GPU Coder in Help Center e File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!