TensorFlow Lite Posenet on a Jetson Nano at 15.2 FPS
BSD-3-CLAUSE License
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:
$ 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