fix

Author: n-shevko

bindsnet/network/topology.py

@@ -441,8 +441,6 @@ def compute(self, s: torch.Tensor) -> torch.Tensor:
 
         # Run through pipeline
         for f in self.pipeline:
-            if type(f).__name__ == 'Weight' and self.mask is not None:
-                f.value.masked_fill_(self.mask, 0)
             conn_spikes = f.compute(conn_spikes)
 
         # Sum signals for each of the output/terminal neurons
@@ -492,6 +490,8 @@ def update(self, **kwargs) -> None:
             # Pipeline learning
             for f in self.pipeline:
                 f.update(**kwargs)
+                if type(f).__name__ == 'Weight' and self.mask is not None:
+                    f.value.masked_fill_(self.mask, 0)
 
     def normalize(self) -> None:
         # language=rst

examples/dosidicus/network.py

@@ -6,33 +6,32 @@
 from bindsnet.network.topology_features import Weight, Bias
 from bindsnet.learning.MCC_learning import PostPre
 
-network = Network(dt=1.0)
-source_layer = LIFNodes(n=5, traces=True)
-target_layer = LIFNodes(n=5, traces=True)
-
-
-network.add_layer(source_layer, name="input")
-network.add_layer(target_layer, name="output")
 
+network = Network(dt=1.0)
+neurons_number = 7
+layer = LIFNodes(n=neurons_number, traces=True)
+network.add_layer(layer, name="input")
+network.add_layer(layer, name="output")
+mask = ~torch.tril(torch.ones((neurons_number, neurons_number)), diagonal=-1).bool()
 weight = Weight(
     name='weight_feature',
-    value=torch.rand(5, 5),
+    value=torch.rand(neurons_number, neurons_number) * mask,
     learning_rule=PostPre,
     nu=(1e-4, 1e-2)
 )
-bias = Bias(name='bias_feature', value=torch.rand(5, 5))
-
+bias = Bias(
+    name='bias_feature',
+    value=torch.rand(neurons_number, neurons_number)
+)
 connection = MulticompartmentConnection(
-    source=source_layer,
-    target=target_layer,
+    source=layer,
+    target=layer,
     pipeline=[weight, bias],
-    mask=~torch.tril(torch.ones((5, 5)), diagonal=-1).bool(),
+    mask=mask,
     device='cpu'
 )
 network.add_connection(connection, source="input", target="output")
-print(connection.pipeline[0].value)
 network.run(
-    inputs={"input": torch.bernoulli(torch.rand(250, 5)).byte()},
+    inputs={"input": torch.bernoulli(torch.rand(250, neurons_number)).byte()},
     time=250
-)
-print(connection.pipeline[0].value)
+)