Установка Theano на Ubuntu

Оглавление

Устанавливать Theano будем на Ubuntu 14.04, но инструкция действительна для любой версии.

Для установки нужно ввести следующие команды:

sudo apt-get update
sudo apt-get upgrade
sudo apt-get install build-essential
# BLAS → LAPACK → ATLAS → numpy → scipy → Theano
# remove numpy and scipy
sudo apt-get remove python-numpy
sudo apt-get remove python-scipy
# Instalation commands
sudo apt-get install gfortran
sudo apt-get install libopenblas-dev
sudo apt-get install liblapack-dev
sudo apt-get install libatlas-base-dev
# Theano dep
sudo apt-get install python-dev
sudo apt-get install python-pip
sudo apt-get install python-nose
sudo apt-get install g++
sudo apt-get install git 
# Numpy
sudo pip install numpy
# Scipy
sudo pip install scipy
# Theano
sudo pip install Theano

Вот и все, установка завершена. В заключении небольшой пример на python, для проверки работоспособности.

Пример: Логистическая регрессия.

import numpy
import theano
import theano.tensor as T
rng = numpy.random

N = 400                                   # training sample size
feats = 784                               # number of input variables

# generate a dataset: D = (input_values, target_class)
D = (rng.randn(N, feats), rng.randint(size=N, low=0, high=2))
training_steps = 10000

# Declare Theano symbolic variables
x = T.matrix("x")
y = T.vector("y")

# initialize the weight vector w randomly
#
# this and the following bias variable b
# are shared so they keep their values
# between training iterations (updates)
w = theano.shared(rng.randn(feats), name="w")

# initialize the bias term
b = theano.shared(0., name="b")

print("Initial model:")
print(w.get_value())
print(b.get_value())

# Construct Theano expression graph
p_1 = 1 / (1 + T.exp(-T.dot(x, w) - b))   # Probability that target = 1
prediction = p_1 > 0.5                    # The prediction thresholded
xent = -y * T.log(p_1) - (1-y) * T.log(1-p_1) # Cross-entropy loss function
cost = xent.mean() + 0.01 * (w ** 2).sum()# The cost to minimize
gw, gb = T.grad(cost, [w, b])             # Compute the gradient of the cost
                                          # w.r.t weight vector w and
                                          # bias term b
                                          # (we shall return to this in a
                                          # following section of this tutorial)

# Compile
train = theano.function(
          inputs=[x,y],
          outputs=[prediction, xent],
          updates=((w, w - 0.1 * gw), (b, b - 0.1 * gb)))
predict = theano.function(inputs=[x], outputs=prediction)

# Train
for i in range(training_steps):
    pred, err = train(D[0], D[1])

print("Final model:")
print(w.get_value())
print(b.get_value())
print("target values for D:")
print(D[1])
print("prediction on D:")
print(predict(D[0]))

Оглавление