--- a/mlp.py	Tue May 13 17:00:53 2008 -0400
+++ b/mlp.py	Tue May 13 18:30:08 2008 -0400
@@ -67,7 +67,7 @@
        - 'regularization_term'
 
     """
-    def __init__(self,n_hidden,n_classes,learning_rate,max_n_epochs,L2_regularizer=0,init_range=1.,n_inputs=None,minibatch_size=None):
+    def __init__(self,n_hidden,n_classes,learning_rate,max_n_epochs,L2_regularizer=0,init_range=1.,n_inputs=None,minibatch_size=None,linker='c|py'):
         self._n_inputs = n_inputs
         self._n_outputs = n_classes
         self._n_hidden = n_hidden
@@ -78,7 +78,7 @@
         self.L2_regularizer = L2_regularizer
         self._learning_rate = t.scalar('learning_rate') # this is the symbol
         self._input = t.matrix('input') # n_examples x n_inputs
-        self._target = t.imatrix('target') # n_examples x 1
+        self._target = t.lmatrix('target') # n_examples x 1
         self._target_vector = self._target[:,0]
         self._L2_regularizer = t.scalar('L2_regularizer')
         self._W1 = t.matrix('W1')
@@ -91,7 +91,7 @@
         self._output_class = t.argmax(self._output,1)
         self._class_error = t.neq(self._output_class,self._target_vector)
         self._minibatch_criterion = self._nll + self._regularization_term / t.shape(self._input)[0]
-        OnlineGradientTLearner.__init__(self)
+        OnlineGradientTLearner.__init__(self, linker = linker)
             
     def attributeNames(self):
         return ["parameters","b1","W2","b2","W2", "L2_regularizer","regularization_term"]
@@ -119,7 +119,7 @@
         
     def updateMinibatch(self,minibatch):
         MinibatchUpdatesTLearner.updateMinibatch(self,minibatch)
-        print self.nll
+        #print self.nll
 
     def allocate(self,minibatch):
         minibatch_n_inputs  = minibatch["input"].shape[1]

--- a/test_mlp.py	Tue May 13 17:00:53 2008 -0400
+++ b/test_mlp.py	Tue May 13 18:30:08 2008 -0400
@@ -2,8 +2,56 @@
 from mlp import *
 import dataset
 
+
+from functools import partial
+def separator(debugger, i, node, *ths):
+    print "==================="
+
+def what(debugger, i, node, *ths):
+    print "#%i" % i, node
+
+def parents(debugger, i, node, *ths):
+    print [input.step for input in node.inputs]
+
+def input_shapes(debugger, i, node, *ths):
+    print "input shapes: ",
+    for r in node.inputs:
+        if hasattr(r.value, 'shape'):
+            print r.value.shape,
+        else:
+            print "no_shape",
+    print
+
+def input_types(debugger, i, node, *ths):
+    print "input types: ",
+    for r in node.inputs:
+        print r.type,
+    print
+
+def output_shapes(debugger, i, node, *ths):
+    print "output shapes:",
+    for r in node.outputs:
+        if hasattr(r.value, 'shape'):
+            print r.value.shape,
+        else:
+            print "no_shape",
+    print
+
+def output_types(debugger, i, node, *ths):
+    print "output types:",
+    for r in node.outputs:
+        print r.type,
+    print
+
+
 def test0():
-    nnet = OneHiddenLayerNNetClassifier(10,2,.001,1000)
+    linker = 'c|py'
+    #linker = partial(theano.gof.DebugLinker, linkers = [theano.gof.OpWiseCLinker],
+    #                 debug_pre = [separator, what, parents, input_types, input_shapes],
+    #                 debug_post = [output_shapes, output_types],
+    #                 compare_fn = lambda x, y: numpy.all(x == y))
+    
+    nnet = OneHiddenLayerNNetClassifier(10,2,.001,1000, linker = linker)
     training_set = dataset.ArrayDataSet(numpy.array([[0, 0, 0],
                                                      [0, 1, 1],
                                                      [1, 0, 1],