How to install theano and keras on ubuntu system

Note: The system is unbuntu14.04LTS, a 32-bit operating system. Python3.4 was previously installed. Now I want to install theano and keras. Proceed as follows:

1 , Install pip

sudo apt-get install python3-setuptools
sudo easy_install3 pip

2 , Install g++

sudo apt-get install g++

Use the above command to install g++. After the installation is complete, you can use g++ -version to check whether the installation is complete. Note that if g++ is not installed, the following error will occur when importing theano:

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.
I searched it because theano uses g++ to compile the speed faster. Most of the solutions found on the Internet are installed based on Anaconda. The solution is:

conda install mingw libpython

3 , Install theano

sudo pip3 install theano

This command will automatically download the dependencies required by theano, including numpy, scipy and so on.

4 , Install keras

sudo pip3 install keras

The last thing to note is that the default backend of keras is tensorflow, what we need is theano, so we need to modify the settings. (And tensorflow is installed with pip3, there is no corresponding version on 32-bit systems! It is very complicated to install with source files)

vim ~/.keras/keras.json
{" image_dim_ordering":"tf","epsilon":1e-07,"floatx":"float32","backend":"theano"}

5 , Test theano

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(),))

to sum up

The above is the installation method of ubuntu system theano and keras introduced by the editor, I hope it will be helpful to you!