MacOS上安装TensorFlow和Keras并用与深度学习

[zibuyu1995]

在本教程中你将学习如何在macos上搭建深度学习平台

Mac 环境配置

• Homebrew安装

/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"

• homebrew 加速(可选)

自备小火箭

export ALL_PROXY=socks5://127.0.0.1:1080

• Python 3.6 安装

官网下载3.6.5包

基本依赖安装

brew install cmake pkg-config wget
brew install jpeg libpng libtiff openexr
brew install eigen tbb hdf5

Python虚拟环境安装

可以选择pipenv(虽然我很讨厌这个包)，也可以采用virtualenvwrapper 这里选用virtualenvwrapper

• 安装 virtualenv virtualenvwrapper

pip3 install virtualenv virtualenvwrapper

• 用virtualenvwrapper管理虚拟环境

$ vi ~/.profile 或者 vi ~/.zshrc

# virtualenv and virtualenvwrapper
export WORKON_HOME=$HOME/.virtualenvs
source /usr/local/bin/virtualenvwrapper.sh

$ source ~/.zshrc

• 创建虚拟环境

 mkvirtualenv DeepLearning

激活虚拟环境

workon DeepLearning 

安装OpenCv IPython

• OpenCv 安装

pip install opencv-contrib-python -i https://pypi.douban.com/simple/

• 安装ipython

pip install ipython -i https://pypi.douban.com/simple/

安装TensorFlow和Keras

• 基本视觉库安装

pip install scipy pillow -i https://pypi.douban.com/simple/
pip install imutils h5py requests progressbar2 -i https://pypi.douban.com/simple/
pip install scikit-learn scikit-image  -i https://pypi.douban.com/simple/

• 安装matplotlib

pip install matplotlib -i https://pypi.douban.com/simple/
mkdir ~/.matplotlib
touch ~/.matplotlib/matplotlibrc
echo "backend: TkAgg" >> ~/.matplotlib/matplotlibrc

• 安装TensorFlow和Keras

pip install tensorflow -i https://pypi.douban.com/simple/
pip install keras -i https://pypi.douban.com/simple/

• 验证

Demo运行

计算张量积(在tensorflow程序中所有的数据都通过张量的形式来表示)

import tensorflow as tf


x1 = tf.constant([1,2,3,4])
x2 = tf.constant([5,6,7,8])
result = tf.multiply(x1, x2)

with tf.Session() as s:
    print(s.run(result))

# out: [ 5 12 21 32]