--- a/deep/stacked_dae/v_sylvain/stacked_dae.py	Sat Mar 13 15:45:43 2010 -0500
+++ b/deep/stacked_dae/v_sylvain/stacked_dae.py	Sun Mar 14 15:07:17 2010 -0400
@@ -193,14 +193,14 @@
         print "input_divider", input_divider
         print "----"
 
-        self.shared_divider = theano.shared(numpy.asarray(input_divider, dtype=theano.config.floatX))
+        #self.shared_divider = theano.shared(numpy.asarray(input_divider, dtype=theano.config.floatX))
 
         if len(hidden_layers_sizes) < 1 :
             raiseException (' You must have at least one hidden layer ')
 
 
         # allocate symbolic variables for the data
-        index   = T.lscalar()    # index to a [mini]batch 
+        ##index   = T.lscalar()    # index to a [mini]batch 
         self.x  = T.matrix('x')  # the data is presented as rasterized images
         self.y  = T.ivector('y') # the labels are presented as 1D vector of 
                                  # [int] labels
@@ -247,10 +247,10 @@
                 updates[param] = param - gparam * pretrain_lr
             
             # create a function that trains the dA
-            update_fn = theano.function([index], dA_layer.cost, \
+            update_fn = theano.function([ensemble], dA_layer.cost, \
                   updates = updates,
                   givens = { 
-                     self.x : train_set_x[index*batch_size:(index+1)*batch_size] / self.shared_divider})
+                     self.x : ensemble})
             # collect this function into a list
             self.pretrain_functions += [update_fn]
 
@@ -273,11 +273,13 @@
         for param,gparam in zip(self.params, gparams):
             updates[param] = param - gparam*finetune_lr
             
-        self.finetune = theano.function([index], cost, 
+        self.finetune = theano.function([ensemble_x,ensemble_y], cost, 
                 updates = updates,
                 givens = {
-                  self.x : train_set_x[index*batch_size:(index+1)*batch_size]/self.shared_divider,
-                  self.y : train_set_y[index*batch_size:(index+1)*batch_size]} )
+                  #self.x : train_set_x[index*batch_size:(index+1)*batch_size]/self.shared_divider,
+                  #self.y : train_set_y[index*batch_size:(index+1)*batch_size]} )
+                  self.x : ensemble_x,
+                  self.y : ensemble_y} )
 
         # symbolic variable that points to the number of errors made on the
         # minibatch given by self.x and self.y