tensorflow_lite_segmentation_jetson-nano's Introduction

TensorFlow_Lite_Segmentation_Jetson-Nano

TensorFlow Lite Unet running on a Jetson Nano

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

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
Optional OpenCV installed. Install OpenCV 4.5
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

See the RPi 4 movie at: https://www.youtube.com/watch?v=Kh9DLMgCIIE

tensorflow_lite_segmentation_jetson-nano's People

Stargazers

Watchers

tensorflow_lite_segmentation_jetson-nano's Issues

regarding semantic segmentation

GPU DELEGATE

Hi,
If I want to use the version without GPU, where or which code should I uncommented #define GPU_DELEGATE ?

How to use this package with Jetson-Nano-Ubuntu-20-image

Hello,

First of all, thank you very much for all your support in Jetson Nano and AI algorithms.

I have installed your Jetson-Nano-Ubuntu-20-image (9Gb image) on my Jetson Nano. I tried to run this algorithm (Tensorflow_lite_segmentation_Jetson-Nano) on this image, but I have a few problems.

First of all, considering the Ubuntu image has already installed tensorflow, opencv, etc. I am a little bit confused about what should I install in this image. Should I install all TensorFlow Lite frameworks (https://qengineering.eu/install-tensorflow-2-lite-on-jetson-nano.html) ?

I have tried the step above, but I get an invalid ld reference to -ltensorflow.

If I do not install the tensorflow lite framework, and use the one install with Ubuntu image, I have errors related to missing files and references, such as builtin_op_data.h. This file is really not found on tensorflow installed with the Ubuntu image. What should I do?

Please, if you can help me on that, I really appreciate your support.

Thanks.

Recommend Projects