A fast C++ implementation of TensorFlow Lite Posenet on a Jetson Nano.
Once overclocked to 2015 MHz, the app runs at 15.2 FPS.
Special made for a Jetson Nano see Q-engineering deep learning examples
| CPU 2015 MHz | GPU 2015 MHz | CPU 1479 MHz | GPU 1479 MHZ | RPi 4 64os 1950 MHz |
|---|---|---|---|---|
| 15.2 FPS | 11.8 FPS | 12 FPS | 11 FPS | 9.4 FPS |
To run the application, you have to:
- TensorFlow Lite framework installed. Install TensorFlow Lite
- Optional OpenCV installed. Install OpenCV 4.5
- Code::Blocks installed. (
$ sudo apt-get install codeblocks)
To extract and run the network in Code::Blocks
$ mkdir MyDir
$ cd MyDir
$ wget https://github.com/Qengineering/TensorFlow_Lite_Pose_Jetson-Nano/archive/refs/heads/main.zip
$ unzip -j master.zip
Remove master.zip, LICENSE and README.md as they are no longer needed.
$ rm master.zip
$ rm README.md
Your MyDir folder must now look like this:
Dance.mp4
posenet_mobilenet_v1_100_257x257_multi_kpt_stripped.tflite
TestTensorFlow_Lite_Pose.cpb
Pose_single.cpp
Run TestTensorFlow_Lite.cpb with Code::Blocks.
You may need to adapt the specified library locations in TestTensorFlow_Lite.cpb to match your directory structure.
With the #define GPU_DELEGATE uncommented, the TensorFlow Lite will deploy GPU delegates, if you have, of course, the appropriate libraries compiled by bazel. Install GPU delegates
See the RPi 4 movie at: https://www.youtube.com/watch?v=LxSR5JJRBoI
