Merge pull request lisa-lab#35 from nouiz/url

Url

Author: nouiz

doc/lenet.txt

@@ -42,10 +42,12 @@ Convolutional Neural Networks (LeNet)
 .. _dimshuffle: http://deeplearning.net/software/theano/library/tensor/basic.html#tensor._tensor_py_operators.dimshuffle
 
 .. note::
-    The code for this section is available for download `here`_.
+    The code for this section is available for download `here`_ and the `3wolfmoon image`_
 
 .. _here: http://deeplearning.net/tutorial/code/convolutional_mlp.py
 
+.. _3wolfmoon image: https://raw.githubusercontent.com/lisa-lab/DeepLearningTutorials/master/doc/images/3wolfmoon.jpg
+
 
 Motivation
 ++++++++++
@@ -258,7 +260,7 @@ Let's have a little bit of fun with this...
         from PIL import Image
 
         # open random image of dimensions 639x516
-        img = Image.open(open('images/3wolfmoon.jpg'))
+        img = Image.open(open('doc/images/3wolfmoon.jpg'))
         img = numpy.asarray(img, dtype='float64') / 256.
 
         # put image in 4D tensor of shape (1, 3, height, width)

doc/rnnrbm.txt

@@ -20,8 +20,7 @@ Modeling and generating sequences of polyphonic music with the RNN-RBM
   Note that both dependencies above can be setup automatically by running the ``download.sh`` script in the ``../data`` directory.
 
 .. caution::
-  Depending on your locally installed Theano version, you may have problems running this script.
-  If this is the case, please use the `'bleeding-edge' developer version <http://deeplearning.net/software/theano/#download>`_ from github.
+  Need Theano 0.6 or more recent.
 
 
 The RNN-RBM