Debugging.

williampeer · Mar 30, 2016 · 9e8066c · 9e8066c
1 parent 77853a3
commit 9e8066c
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/DNMM.py b/DNMM.py
@@ -57,8 +57,8 @@ def hpc_learn_patterns_wrapper(hpc, patterns, max_training_iterations):
                 if out_values_row[el_index] != cur_p_row[el_index]:
                     learned_all = False
                     print "Patterns are not yet successfully learned. Learning more..."
-                    # print "Displaying intermediary results... (output, target)"
-                    # show_image_from(np.asarray([out_values_row], dtype=np.float32))
+                    print "Displaying intermediary results... (output, target)"
+                    show_image_from(np.asarray([out_values_row], dtype=np.float32))
                     # show_image_from(np.asarray([cur_p_row], dtype=np.float32))
                     print "iter:", iter_ctr
                     break

diff --git a/HPC.py b/HPC.py
@@ -74,31 +74,31 @@ def __init__(self, dims, connection_rate_input_ec, perforant_path, mossy_fibers,
 
         # randomly assign about 25 % of the weights to a random connection weight
         # ec_dg_weights = binomial_f(dims[1], dims[2], self.PP) * uniform_f(dims[1], dims[2])
-        ec_dg_weights = binomial_f(dims[1], dims[2], self.PP) * np.random.normal(0.5, 0.25, (dims[1], dims[2]))
+        ec_dg_weights = binomial_f(dims[1], dims[2], self.PP) * np.random.normal(0.5, 0.25 ** 2, (dims[1], dims[2]))
         self.ec_dg_weights = theano.shared(name='ec_dg_weights', value=ec_dg_weights.astype(theano.config.floatX),
                                            borrow=True)
 
         # randomly assign all weights between the EC and CA3
         # ec_ca3_weights = uniform_f(dims[1], dims[3])
-        ec_ca3_weights = binomial_f(dims[1], dims[3], self.PP) * np.random.normal(0.5, 0.25, (dims[1], dims[3]))
+        ec_ca3_weights = binomial_f(dims[1], dims[3], self.PP) * np.random.normal(0.5, 0.25 ** 2, (dims[1], dims[3]))
         self.ec_ca3_weights = theano.shared(name='ec_ca3_weights', value=ec_ca3_weights.astype(theano.config.floatX),
                                             borrow=True)
 
         # randomly assign about 4 % of the weights to random connection weights
         # dg_ca3_weights = binomial_f(dims[2], dims[3], self.MF) * uniform_f(dims[2], dims[3])  # elemwise
-        dg_ca3_weights = binomial_f(dims[2], dims[3], self.MF) * np.random.normal(0.9, 0.01, (dims[2], dims[3]))  # elemwise
+        dg_ca3_weights = binomial_f(dims[2], dims[3], self.MF) * np.random.normal(0.9, 0.01 ** 2, (dims[2], dims[3]))  # elemwise
         self.dg_ca3_weights = theano.shared(name='dg_ca3_weights', value=dg_ca3_weights.astype(theano.config.floatX),
                                             borrow=True)
 
         # randomly assign 100 % of the weights between CA3 and CA3
         # ca3_ca3_weights = uniform_f(dims[3], dims[3])
-        ca3_ca3_weights = np.random.normal(0.5, 0.25, (dims[3], dims[3]))
+        ca3_ca3_weights = np.random.normal(0.5, 0.25 ** 2, (dims[3], dims[3]))
         self.ca3_ca3_weights = theano.shared(name='ca3_ca3_weights', value=ca3_ca3_weights.astype(theano.config.floatX),
                                              borrow=True)
 
         # random weight assignment, full connection rate CA3-out
         # ca3_output_weights = uniform_f(dims[3], dims[4])
-        ca3_output_weights = np.random.normal(0.5, 0.25, (dims[3], dims[4]))
+        ca3_output_weights = np.random.normal(0.5, 0.25 ** 2, (dims[3], dims[4]))
         self.ca3_out_weights = theano.shared(name='ca3_out_weights',
                                              value=ca3_output_weights.astype(theano.config.floatX), borrow=True)