[英]Tensorflow Lite on Nvidia Jetson
Has anyone used Tensorflow Lite on any Nvidia Jetson product?有没有人在任何 Nvidia Jetson 产品上使用过 Tensorflow Lite? I want to use my Jetson Nano for inference and would like to so with tf-lite utilizing the GPU.
我想使用我的 Jetson Nano 进行推理,并希望使用 GPU 的 tf-lite 进行推理。
Confusingly, there does not seem to be a Python API for creating a GPU Delegate in tf-lite .令人困惑的是,似乎没有用于在 tf-lite 中创建 GPU 委托的 Python API 。
Is there are clear reason for this?这有明确的原因吗?
Is the alternative to use the full Tensorflow library (I would prefer not use the Nvidia TensorRT engine)?是否可以使用完整的 Tensorflow 库(我不想使用 Nvidia TensorRT 引擎)?
Yes, I have tried to use tf lite on Jetson Nano before.是的,我之前曾尝试在 Jetson Nano 上使用 tf lite。
You can refer to my previous article on Medium (PS: I am sorry that the article was written in Chinese.)你可以参考我之前在Medium上的文章(PS:很抱歉这篇文章是用中文写的。)
This article is about how to set up the TF Lite Environment on Jetson Nano这篇文章是关于如何在Jetson Nano上设置TF Lite环境
Notice:注意:
You should change the following command according to your own environment.您应该根据自己的环境更改以下命令。
pip3 install https://dl.google.com/coral/python/tflite_runtime-2.1.0.post1-cp36-cp36m-linux_aarch64.whl
in case it is of interest to you to use inference with C++ you can compile TFlite 2.4.1 on your Jetson device like I did on the Xavier NX:如果您对使用 C++ 进行推理感兴趣,您可以像在 Xavier NX 上一样在 Jetson 设备上编译 TFlite 2.4.1:
$ sudo apt-get install cmake curl
$ wget -O tensorflow.zip https://github.com/tensorflow/tensorflow/archive/v2.4.1.zip
$ unzip tensorflow.zip
$ mv tensorflow-2.4.1 tensorflow
$ cd tensorflow
$ ./tensorflow/lite/tools/make/download_dependencies.sh
$ ./tensorflow/lite/tools/make/build_aarch64_lib.sh
After that you will also have to install the TF lite flat buffers like this:之后,您还必须像这样安装 TF lite 平面缓冲区:
$ cd ./tensorflow/tensorflow/lite/tools/make/downloads/flatbuffers
$ mkdir build && cd build
$ cmake ..
$ make -j
$ sudo make install
$ sudo ldconfig
After that you find the library here tensorflow/tensorflow/lite/tools/make/gen/linux_aarch64/libtensorflow-lite.a
之后,您可以在此处找到库
tensorflow/tensorflow/lite/tools/make/gen/linux_aarch64/libtensorflow-lite.a
You can build your inference application against that like this您可以像这样构建推理应用程序
gcc -llibtensorflow-lite.a -ledgetpu main.cpp
You will also need to install libedgetpu.so like shown on Coral.ai您还需要安装 libedgetpu.so,如 Coral.ai 所示
Best Alexander最好的亚历山大
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.