win10-64位安装机器学习Theano包

最近开始学习深度学习相关知识，发现很多地方需要用到theano包。由于自己之前没有接触过theano等机器学习的安装，所以从开始尝试到最后成功安装花了好几天时间。

我自己电脑的环境是win10-64位；安装了vs2013，也可以是其他版本，不过如果想要安装CUDA，就选用非2015版的（亲测不支持，都是泪啊！）。

开始安装：

一、安装Anaconda

anaconda是一款自带python环境的免费软件，而且嵌入了很多必须的库，省去不少安装时间，非常方便。下面，到anaconda官网下载最新版软件，注意要与自己的系统相匹配，下载时选择python2.x版本（建议python2.7），因为在Deep Learning Tutorials中使用的代码都是python2的，使用python3会有语法错误，改起来很麻烦。下载完，安装，过程中建议选择all users，然后路径默认，我的是C:\Anaconda2。安装完，打开CMD，输入python，如果不出错，就表示安装成功。

二、安装MinGW

以管理员身份运行CMD，输入conda install mingw libpython，回车，下面会出现Fetching package...字样，等一会，就会自己安装，最后看到successfully就表示成功了。这样就能把MinGW安装到Anaconda目录下面了。

三、新建环境变量

1、右键此电脑——属性——高级系统设置——环境变量，在用户变量中点击“新建”，变量名为path（如果存在，直接双击，然后点击添加），变量值按照自己anaconda安装的位置来定，我的是C:\Anaconda2;C:\Anaconda2\Scripts;（注意这两个分号是英文模式下的，在新建的时候将上面红色部分复制过去，如果是添加，只能将上面两句分开加，即添加两次，不用分号)。

2、在用户变量中新建，变量名为pythonpath，变量值为C:\Anaconda\Lib\site-packages\theano;。

3、在Users中自己的目录下（不知道的时候就打开CMD，右上角显示的路径就是），新建一个名叫.theano.txt的文本文件（把查看中文件后缀名显示出来，否则容易建成.theano.txt.txt），用写字板打开，输入一下内容：

[global]
openmp=False
[blas]
ldflags=
[gcc]
cxxflags=-IC:\Anaconda2\MinGW

上面红色路径为自己安装的anaconda路径。

4、保存并重启电脑

四、下载并安装theano

1、打开CMD，输入pip install theano，回车，稍微等一会，就会显示安装成功。

2、在CMD中输入python，进去python编译环境，输入import theano，回车，首次输入，要等一会才好。下面可以输入theano.test()来测试是否安装成功，也可以打开anaconda2里面的spyder，直接测试一下下面这段代码能不能正确运行。

<span style="font-size:14px;">import theano
from theano import tensor as T
from theano.tensor.nnet import conv2d
import numpy
import pylab
from PIL import Image
rng = numpy.random.RandomState(23455)

# instantiate 4D tensor for input
input = T.tensor4(name='input')

# initialize shared variable for weights.
w_shp = (2, 3, 9, 9)
w_bound = numpy.sqrt(3 * 9 * 9)
W = theano.shared( numpy.asarray(
            rng.uniform(
                low=-1.0 / w_bound,
                high=1.0 / w_bound,
                size=w_shp),
            dtype=input.dtype), name ='W')

# initialize shared variable for bias (1D tensor) with random values
# IMPORTANT: biases are usually initialized to zero. However in this
# particular application, we simply apply the convolutional layer to
# an image without learning the parameters. We therefore initialize
# them to random values to "simulate" learning.
b_shp = (2,)
b = theano.shared(numpy.asarray(
            rng.uniform(low=-.5, high=.5, size=b_shp),
            dtype=input.dtype), name ='b')

# build symbolic expression that computes the convolution of input with filters in w
conv_out = conv2d(input, W)

# build symbolic expression to add bias and apply activation function, i.e. produce neural net layer output
# A few words on ``dimshuffle`` :
#   ``dimshuffle`` is a powerful tool in reshaping a tensor;
#   what it allows you to do is to shuffle dimension around
#   but also to insert new ones along which the tensor will be
#   broadcastable;
#   dimshuffle('x', 2, 'x', 0, 1)
#   This will work on 3d tensors with no broadcastable
#   dimensions. The first dimension will be broadcastable,
#   then we will have the third dimension of the input tensor as
#   the second of the resulting tensor, etc. If the tensor has
#   shape (20, 30, 40), the resulting tensor will have dimensions
#   (1, 40, 1, 20, 30). (AxBxC tensor is mapped to 1xCx1xAxB tensor)
#   More examples:
#    dimshuffle('x') -> make a 0d (scalar) into a 1d vector
#    dimshuffle(0, 1) -> identity
#    dimshuffle(1, 0) -> inverts the first and second dimensions
#    dimshuffle('x', 0) -> make a row out of a 1d vector (N to 1xN)
#    dimshuffle(0, 'x') -> make a column out of a 1d vector (N to Nx1)
#    dimshuffle(2, 0, 1) -> AxBxC to CxAxB
#    dimshuffle(0, 'x', 1) -> AxB to Ax1xB
#    dimshuffle(1, 'x', 0) -> AxB to Bx1xA
output = T.nnet.sigmoid(conv_out + b.dimshuffle('x', 0, 'x', 'x'))

# create theano function to compute filtered images
f = theano.function([input], output)

# open random image of dimensions 639x516

img = Image.open(r'C:\\Users\USER\Desktop\3wolfmoon.jpg','r')

# dimensions are (height, width, channel)
img = numpy.asarray(img, dtype='float64') / 256.

# put image in 4D tensor of shape (1, 3, height, width)
img_ = img.transpose(2, 0, 1).reshape(1, 3, 639, 516)
filtered_img = f(img_)

# plot original image and first and second components of output
pylab.subplot(1, 3, 1); pylab.axis('off'); pylab.imshow(img)
pylab.gray();
# recall that the convOp output (filtered image) is actually a "minibatch",
# of size 1 here, so we take index 0 in the first dimension:
pylab.subplot(1, 3, 2); pylab.axis('off'); pylab.imshow(filtered_img[0, 0, :, :])
pylab.subplot(1, 3, 3); pylab.axis('off'); pylab.imshow(filtered_img[0, 1, :, :])
pylab.show()
</span>

将下面的图片保存到桌面，名称是：3wolfmoon.jpg

如果能成功运行，并出现三张图片，即表示theano安装成功！

参考资料：

http://deeplearning.net/software/theano/install.html#

http://blog.csdn.net/m624197265/article/details/45700619