Linux Mint 17.3 Rosa: TensorFlow setup (Ubuntu/Linux 64-bit, CPU only)

Ubuntu TensorFlow

Python のバージョン確認

[]$ python -V
Python 2.7.6

Install pip

$ dpkg -l | grep python-dev
ii  libpython-dev:amd64                         2.7.5-5ubuntu3                                      amd64        header files and a static library for Python (default)
ii  python-dev                                  2.7.5-5ubuntu3                                      amd64        header files and a static library for Python (default)
[]$ dpkg -l | grep python-pip
ii  python-pip                                  1.5.4-1ubuntu3                                      all          alternative Python package installer
ii  python-pip-whl                              1.5.4-1ubuntu3                                      all          alternative Python package installer
[]$

Install TensorFlow (Ubuntu/Linux 64-bit, CPU only)

[]$ sudo pip install --upgrade https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.8.0-cp27-none-linux_x86_64.whl
  :
  :
Successfully installed tensorflow protobuf wheel numpy setuptools
Cleaning up...
[]$

Run TensorFlow from the Command Line

[]$ python
Python 2.7.6 (default, Jun 22 2015, 17:58:13) 
[GCC 4.8.2] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorflow as tf
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
>>> print(sess.run(hello))
Hello, TensorFlow!
>>> a = tf.constant(11)
>>> b = tf.constant(43)
>>> print(sess.run(a + b))
54
>>> exit()
[]$

参考