Tensorflow-on-arm

Inspired by the tensorflow-on-raspberry-pi. Tool for compile tensorflow for arm.

Dependences

# NOTE: the libpng12-dev have in wheezy, jessie or sid distro.
apt-get install openjdk-8-jdk automake autoconf
apt-get install curl zip unzip libtool swig libpng12-dev zlib1g-dev pkg-config git g++ wget xz-utils

# For python2.7
apt-get install python-numpy python-dev python-pip python-mock

# For python3
apt-get install python3-numpy python3-dev python3-pip python3-mock

TensorFlow on Raspberry Pi

It's officially supported!

Python wheels for TensorFlow are being officially supported. As well, this repository maintain up-to-date tensorflow wheels for raspberry pi.

installation

Check out the official TensorFlow website for more information.

Cross-compilation

Make you sure added arm architecture, see how to adds in debian flavors:

dpkg --add-architecture armhf
echo "deb [arch=armhf] http://httpredir.debian.org/debian/ stretch main contrib non-free" >> /etc/apt/sources.list

if you want compile python support:

# For python2.7
apt-get install libpython-all-dev:armhf

# For python3
apt-get install libpython3-all-dev:armhf

Edit tweaks like bazel resources, board model, and others

see configuration file examples in: build_tensorflow/configs/

Finally, compile tensorflow.

cd build_tensorflow/
chmod +x build_tensorflow.sh
./build_tensorflow.sh <path-of-config>
# If no output errors, the pip package will be in the directory: /tmp/tensorflow_pkg/