https://github.com/qengineering/tensorflow_lite_segmentation_jetson-nano
TensorFlow Lite segmentation on a Jetson Nano at 11 FPS
https://github.com/qengineering/tensorflow_lite_segmentation_jetson-nano
aarch64 cpp gpu-acceleration gpu-delegate jetson-nano tensorflow-examples tensorflow-lite unet unet-segmentation unet-tensorflow
Last synced: 3 months ago
JSON representation
TensorFlow Lite segmentation on a Jetson Nano at 11 FPS
- Host: GitHub
- URL: https://github.com/qengineering/tensorflow_lite_segmentation_jetson-nano
- Owner: Qengineering
- License: bsd-3-clause
- Created: 2021-02-02T14:05:40.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2023-01-25T09:42:45.000Z (over 2 years ago)
- Last Synced: 2025-04-07T02:21:55.142Z (6 months ago)
- Topics: aarch64, cpp, gpu-acceleration, gpu-delegate, jetson-nano, tensorflow-examples, tensorflow-lite, unet, unet-segmentation, unet-tensorflow
- Language: C++
- Homepage: https://qengineering.eu/install-tensorflow-2-lite-on-raspberry-pi-4.html
- Size: 11.5 MB
- Stars: 14
- Watchers: 1
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TensorFlow_Lite_Segmentation_Jetson-Nano
## TensorFlow Lite Unet running on a Jetson Nano
[](https://opensource.org/licenses/BSD-3-Clause)
A fast C++ implementation of TensorFlow Lite Unet on a Jetson Nano.
Once overclocked to 2015 MHz, the app runs at 11 FPS.
Special made for a Jetson Nano see [Q-engineering deep learning examples](https://qengineering.eu/deep-learning-examples-on-raspberry-32-64-os.html)
------------
Papers: https://arxiv.org/abs/1606.00915
Training set: VOC2017
Size: 257x257
------------
## Benchmark.
| CPU 2015 MHz | GPU 2015 MHz | CPU 1479 MHz | GPU 1479 MHZ | RPi 4 64os 1950 MHz |
| :------------: | :-------------: | :-------------: | :-------------: | :-------------: |
| 11 FPS | 9.1 FPS | 9 FPS | 8.3 FPS | 7.2 FPS |
------------
## Dependencies.
To run the application, you have to:
- TensorFlow Lite framework installed. [Install TensorFlow Lite](https://qengineering.eu/install-tensorflow-2-lite-on-jetson-nano.html)
- Optional OpenCV installed. [Install OpenCV 4.5](https://qengineering.eu/install-opencv-4.5-on-jetson-nano.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_Segmentation_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:
cat.jpg.mp4
deeplabv3_257_mv_gpu.tflite
TestUnet.cpb
Unet.cpp
------------
## Running the app.
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](https://qengineering.eu/install-tensorflow-2-lite-on-jetson-nano.html)
See the RPi 4 movie at: https://www.youtube.com/watch?v=Kh9DLMgCIIE
------------
[](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=CPZTM5BB3FCYL)