ubuntu系統theano和keras的安裝

說明:系統是unbuntu14.04LTS,32位的操做系統,之前安裝了python3.4,如今想要安裝theano和keras。步驟以下:python

1,安裝pipjson

sudo apt-get install python3-setuptools
sudo easy_install3 pip

 2,安裝g++vim

 sudo apt-get install g++

採用上述命令安裝g++,安裝完成後可用g++ -version查看是否安裝完成。注意,若是沒有安裝g++,在import theano時會出現如下錯誤:dom

WARNING (theano.configdefaults): g++ not detected ! Theano will be unable to execute optimized C-implementations (for both CPU and GPU) and will default to Python implementations. Performance will be severely degraded. To remove this warning, set Theano flags cxx to an empty string.

搜了一下是由於theano採用g++編譯的話速度比較快,在網上找到的大部分解決方案都是基於Anaconda安裝的,解決方法是:測試

conda install mingw libpython

3,安裝theanothis

sudo pip3 install theano

 該命令會自動下載theano所須要的依賴,包括numpy,scipy等等。spa

4,安裝keras操作系統

sudo pip3 install keras

 最後須要注意的是,keras默認的backend是tensorflow,咱們須要的是theano,因此須要修改下設置。(並且tensorflow用pip3安裝,在32位系統上沒有對應的版本!用源文件安裝又很複雜)code

vim ~/.keras/keras.json

{

    "image_dim_ordering":"tf",

    "epsilon":1e-07,

    "floatx":"float32",

    "backend":"theano"

}

 5,測試theanoorm

import numpy as np  
import time  
import theano  
A = np.random.rand(1000,10000).astype(theano.config.floatX)  
B = np.random.rand(10000,1000).astype(theano.config.floatX)  
np_start = time.time()  
AB = A.dot(B)  
np_end = time.time()  
X,Y = theano.tensor.matrices('XY')  
mf = theano.function([X,Y],X.dot(Y))  
t_start = time.time()  
tAB = mf(A,B)  
t_end = time.time()  
print("NP time: %f[s], theano time: %f[s] (times should be close when run on CPU!)" %(  
                                           np_end-np_start, t_end-t_start))  
print("Result difference: %f" % (np.abs(AB-tAB).max(), ))
相關文章
相關標籤/搜索