Installing Latest Tensor flow and Keras on RASPBERRY PI

From: www.raspberrypi.org

— — — — — — — — — — — — — — — — — — — — — — — — — — — — — — —

Now TensorFlow 1.9 Officially Supports the Raspberry Pi

Please check this link

— — — — — — — — — — — — — — — — — — — — — — — — — — — — — — — -

Intro

If you want to run a Neural network model on Embedded system, RPi is one of the best option available.

Installing latest version….. then you have to surf the internet, follow different posts

This post just simplifies the steps to install Tensorflow and Keras,

Hardware specs : https://www.raspberrypi.org/products/raspberry-pi-3-model-b/

Raspbian OS

Start by installing latest version of Raspbian os form here :

RASPBIAN STRETCH . just use Etcher for writing ISO to tf card

Python

Stretch comes pre-installed with python version 3.5 and 2.7

for “2018–04–18-raspbian-stretch” the version are 3.5.2 and 2.7.13, (which i used)

Tensorflow (1.8.0)

i used .whl provided by lhelontra in tensorflow-on-arm

Raspberry pi 2/3

python version 3.5
wget https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.8.0/tensorflow-1.8.0-cp35-none-linux_armv7l.whl
sudo pip3 install tensorflow-1.8.0-cp35-none-linux_armv7l.whl
sudo pip3 uninstall mock
sudo pip3 install mock
python version 2.7
wget https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.8.0/tensorflow-1.8.0-cp27-none-linux_armv7l.whl
sudo pip install tensorflow-1.8.0-cp27-none-linux_armv7l.whl
sudo pip uninstall mock
sudo pip install mock

Raspberry pi one/zero with openblas

python version 3.5
wget https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.8.0/tensorflow-1.8.0-cp35-none-linux_armv6l.whl
sudo pip3 install tensorflow-1.8.0-cp35-none-linux_armv6l.whl
sudo pip3 uninstall mock
sudo pip3 install mock
python version 2.7
wget https://github.com/lhelontra/tensorflow-on-arm/releases/download/v1.8.0/tensorflow-1.8.0-cp27-none-linux_armv6l.whl
sudo pip install tensorflow-1.8.0-cp27-none-linux_armv6l.whl
sudo pip uninstall mock
sudo pip install mock

check tensorflow-on-arm if you want older versions

Keras

sudo apt-get install python3-numpy
sudo apt-get install libblas-dev
sudo apt-get install liblapack-dev
sudo apt-get install python3-dev 
sudo apt-get install libatlas-base-dev
sudo apt-get install gfortran
sudo apt-get install python3-setuptools
sudo apt-get install python3-scipy
sudo apt-get update
sudo apt-get install python3-h5py
sudo pip3 install keras 

Note: remember to change pip3 with just pip and python3 with python for 2.7 version

Conclusion

Test your installation by

Tensorflow

python -c 'import tensorflow as tf; print(tf.__version__)'  # for Python 2
python3 -c 'import tensorflow as tf; print(tf.__version__)'  # for Python 3

Keras

python -c 'import keras; print(keras.__version__)'# python 2
python3 -c 'import keras; print(keras.__version__)'  # for Python 3

That’s it, enjoy

Reference

Layman installation guide for Keras and Tensorflow on RPi 3

Raspberry Pi - Teach, Learn, and Make with Raspberry Pi

lhelontra/tensorflow-on-arm