https://github.com/qengineering/tensorflow_lite_ssd_jetson-nano

TensorFlow Lite SSD on a Jetson Nano 28.5 FPS
https://github.com/qengineering/tensorflow_lite_ssd_jetson-nano

aarch64 cpp gpu-acceleration gpu-delegate jetson-nano mobilenet-ssd ssd-mobilenet tensorflow-examples tensorflow-lite

Last synced: 3 months ago
JSON representation

TensorFlow Lite SSD on a Jetson Nano 28.5 FPS

• Host: GitHub
• URL: https://github.com/qengineering/tensorflow_lite_ssd_jetson-nano
• Owner: Qengineering
• License: bsd-3-clause
• Created: 2021-02-02T13:44:47.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2021-12-27T09:37:45.000Z (over 4 years ago)
• Last Synced: 2025-01-31T03:01:37.377Z (over 1 year ago)
• Topics: aarch64, cpp, gpu-acceleration, gpu-delegate, jetson-nano, mobilenet-ssd, ssd-mobilenet, tensorflow-examples, tensorflow-lite
• Language: C++
• Homepage: https://qengineering.eu/install-tensorflow-2-lite-on-raspberry-pi-4.html
• Size: 21.1 MB
• Stars: 12
• Watchers: 2
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# TensorFlow_Lite_SSD_Jetson-Nano

![output image]( https://qengineering.eu/images/SSD_Jetson.webp )


## TensorFlow Lite SSD running on a Jetson Nano 


[![License](https://img.shields.io/badge/License-BSD%203--Clause-blue.svg)](https://opensource.org/licenses/BSD-3-Clause)



A fast C++ implementation of TensorFlow Lite SSD on a Jetson Nano.


Once overclocked to 2015 MHz, the app runs at 28.5 FPS.


https://arxiv.org/abs/1611.10012 


Training set: COCO 


Size: 300x300 


## Benchmark.

| CPU 2015 MHz | GPU 2015 MHz | CPU 1479 MHz | GPU 1479 MHZ | RPi 4 64os 1950 MHz |

|  :------------: | :-------------: | :-------------:  | :-------------: | :-------------: |

|  28.5 FPS |  -- FPS  | 21.8 FPS | -- FPS  | 24 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) 





## 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```)

## Running the app.

To extract and run the network in Code::Blocks 


$ mkdir *MyDir* 


$ cd *MyDir* 


$ wget https://github.com/Qengineering/TensorFlow_Lite_SSD_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: 
 

James.mp4 


COCO_labels.txt 


detect.tflite 


TestTensorFlow_Lite.cpb 


MobileNetV1.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](https://qengineering.eu/install-tensorflow-2-lite-on-jetson-nano.html) 



See the RPi 4 movie at: https://vimeo.com/393889226

------------

[![paypal](https://qengineering.eu/images/TipJarSmall4.png)](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=CPZTM5BB3FCYL)