507
edits
R2Inference/Supported backends/TensorFlow-Lite: Difference between revisions
R2Inference/Supported backends/TensorFlow-Lite (view source)
Revision as of 17:44, 18 February 2020
, 18 February 2020→Installation
| Line 38: | Line 38: | ||
</pre> | </pre> | ||
===Nvidia Jetson (TX1, TX2, Xavier, Nano)=== | ===Nvidia Jetson (TX1, TX2, Xavier, Nano)=== | ||
You can install the C/C++ Tensorflow API for Jetson devices following the next steps: | |||
* Build and install Tensorflow Lite | |||
Download Tensorflow source code: | |||
<pre> | |||
git clone https://github.com/tensorflow/tensorflow | |||
cd tensorflow/tensorflow/lite/tools/make | |||
</pre> | |||
Download dependencies: | |||
<pre> | |||
./download_dependencies.sh | |||
</pre> | |||
Build: | |||
<pre> | |||
./build_aarch64_lib.sh | |||
</pre> | |||
Copy the static library to the libraries path: | |||
<pre> | |||
cp gen/aarch64_armv8-a/lib/libtensorflow-lite.a /usr/lib/aarch64-linux-gnu/ | |||
</pre> | |||
<!-- | |||
===i.MX 8=== | ===i.MX 8=== | ||
For i.MX8 boards download the prebuilt binary for free from [https://shop.ridgerun.com/search?q=TensorFlow-CPU+Binaries+for+i.MX8 our shop]. Then run the following: | For i.MX8 boards download the prebuilt binary for free from [https://shop.ridgerun.com/search?q=TensorFlow-CPU+Binaries+for+i.MX8 our shop]. Then run the following: | ||