https://github.com/qengineering/tensorflow_lite_pose_rpi_32-bits
TensorFlow Lite Posenet on bare Raspberry Pi 4 at 5.0 FPS
https://github.com/qengineering/tensorflow_lite_pose_rpi_32-bits
armv7 bare-raspberry-pi cpp deep-learning frame-rate high-fps lite posenet raspberry-pi-4 tensorflow-examples tensorflow-lite testtensorflow-lite
Last synced: 6 months ago
JSON representation
TensorFlow Lite Posenet on bare Raspberry Pi 4 at 5.0 FPS
- Host: GitHub
- URL: https://github.com/qengineering/tensorflow_lite_pose_rpi_32-bits
- Owner: Qengineering
- License: bsd-3-clause
- Created: 2020-05-03T11:45:19.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2024-11-20T09:23:29.000Z (11 months ago)
- Last Synced: 2025-03-27T09:23:17.967Z (7 months ago)
- Topics: armv7, bare-raspberry-pi, cpp, deep-learning, frame-rate, high-fps, lite, posenet, raspberry-pi-4, tensorflow-examples, tensorflow-lite, testtensorflow-lite
- Language: C++
- Homepage: https://qengineering.eu/install-tensorflow-2-lite-on-raspberry-pi-4.html
- Size: 12.5 MB
- Stars: 12
- Watchers: 1
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TensorFlow_Lite_Pose_RPi_32-bits
## TensorFlow Lite Posenet running on a bare Raspberry Pi 4
[](https://opensource.org/licenses/BSD-3-Clause)
A fast C++ implementation of TensorFlow Lite on a bare Raspberry Pi 4.
Once overclocked to 2000 MHz, the app runs at 5.0 FPS without any hardware accelerator.
Special made for a bare Raspberry Pi see: https://qengineering.eu/install-tensorflow-2-lite-on-raspberry-pi-4.html
------------
Papers: https://medium.com/tensorflow/real-time-human-pose-estimation-in-the-browser-with-tensorflow-js-7dd0bc881cd5
------------
## Benchmark.
Frame rate Pose Lite : 5.0 FPS (RPi 4 @ 2000 MHz - 32 bits OS)
Frame rate Pose Lite : 9.4 FPS (RPi 4 @ 1825 MHz - 64 bits OS) see https://github.com/Qengineering/TensorFlow_Lite_Pose_RPi_64-bits
------------
## Dependencies.
To run the application, you have to:
- TensorFlow Lite framework installed. [Install TensorFlow Lite](https://qengineering.eu/install-tensorflow-2-lite-on-raspberry-pi-4.html)
- OpenCV installed. [Install OpenCV 4.5](https://qengineering.eu/install-opencv-4.5-on-raspberry-pi-4.html)
- Code::Blocks installed. (```$ sudo apt-get install codeblocks```)
------------
## Installing the app.
To extract and run the network in Code::Blocks
$ mkdir *MyDir*
$ cd *MyDir*
$ wget https://github.com/Qengineering/TensorFlow_Lite_Pose_RPi_32-bits/archive/refs/heads/master.zip
$ unzip -j master.zip
Remove master.zip 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
------------
## Running the app.
Run TestTensorFlow_Lite.cpb with Code::Blocks. More info or
if you want to connect a camera to the app, follow the instructions at [Hands-On](https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html#HandsOn).
See the Ubuntu 9.4 FPS movie at: https://www.youtube.com/watch?v=LxSR5JJRBoI
------------
[](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=CPZTM5BB3FCYL)