配置tensorflow+theano+keras

一、配置tensorflow(pip 安装，最简单)

1.首先升级

pip install –upgrade

2.安装tensorflow

pip install python-pip

3.验证是否安装成功

进入python

Import tesorflow as tf
#输入#
Hello=tf.constant(‘Hello，TensorFlow!’)
Sess=tf.Session()
Print(sess.run(hello))
#如果输出#
Hello，TensorFlow

成功！

二、安装theano和keras

1.升级相关

apt update
apt upgrade

2.安装

apt install -y python-dev python-pip python-nose gcc g++ git gfortran vim
apt install -y libopenblas-dev liblapack-dev libatlas-base-dev
pip install -U --pre pip setuptools wheel
pip install -U --pre numpy scipy matplotlib scikit-learn scikit-image

3.安装theano

pip install -U --pre theano

4.安装keras

pip install -U --pre keras

成功！

注释：如果导入keras模块出错，改backend

#输入#
gedit ~/.keras/keras.json
#将tensorflow改为theano#
#输入#
gedit ~/.theanorc
[global]
openmp=True 
device = cpu 
floatX = float32  
allow_input_downcast=True  
[blas]
ldflags= -lopenblas