added requirements for lasagne, datasetloaders and simple ITK

Author: StephanieLarocque

doc/cnn_1D_segm.txt

@@ -150,6 +150,13 @@ The FCN implementation can be found in the following file:
 * `fcn1D.py <../code/cnn_1D_segm/fcn1D.py>`_ : Main script. Defines the model.
 * `train_fcn1D.py <../code/cnn_1D_segm/train_fcn1D.py>`_ : Training loop
 
+Change the *dataset_loaders/config.ini* file and add the right path for the dataset:
+
+[cortical_layers]
+
+shared_path = /data/lisa/exp/vazquezd/datasets/cortical_layers/
+
+
 First define a *bn+relu+conv* block that returns the name of the last layer of
 the block. Since the implementation uses a dictionary variable *net* that keeps
 the layer's name as key and the actual layer object as variable, the name of the

doc/fcn_2D_segm.txt

@@ -174,8 +174,14 @@ The FCN-8 implementation can be found in the following file:
 * `[GitHub Repo] <https://github.com/fvisin/dataset_loaders>`_ Francesco Visin, Adriana Romero - Dataset loaders: a python library to load and preprocess datasets. 2017
 
 
-TODO : import model_helpers, dataset_loader, metrics
-TODO : remove /Tmp/romerosa path and make them relative path
+The user must install `Lasagne <http://lasagne.readthedocs.io/en/latest/user/installation.html>`_ ,
+and clone the GitHub repo `Dataset Loaders <https://github.com/fvisin/dataset_loaders>`_.
+
+Change the *dataset_loaders/config.ini* file and add the right path for the dataset:
+
+[polyps912]
+
+shared_path = /data/lisa/exp/vazquezd/datasets/polyps_split7/
 
 We used Lasagne layers, as you can see in the code below.
 

doc/unet.txt

@@ -106,8 +106,20 @@ The U-Net implementation can be found in the following GitHub repo:
 
 * `train_unet.py <../code/unet/train_unet.py>`_ : Training loop.
 
-The user can now build a U-Net with a specified number of input channels and number of classes.
 
+The user must install `Lasagne <http://lasagne.readthedocs.io/en/latest/user/installation.html>`_ ,
+`SimpleITK <http://www.simpleitk.org/SimpleITK/resources/software.html>`_ and 
+clone the GitHub repo `Dataset Loaders <https://github.com/fvisin/dataset_loaders>`_.
+
+Change the *dataset_loaders/config.ini* file to set the right path for the dataset:
+
+[isbi_em_stacks]  
+
+
+shared_path = /path/to/DeepLearningTutorials/data/isbi_challenge_em_stacks
+
+
+The user can now build a U-Net with a specified number of input channels and number of classes.
 First include the Lasagne layers needed to define the U-Net architecture :
 
 .. literalinclude:: ../code/unet/Unet_lasagne_recipes.py