| 
				
				
					
				
				
				 | 
			
			 | 
			@@ -102,17 +102,17 @@ def test_decode_layer_03(): | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			def test_decode_layer_04():
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    d = Data()
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    d.add_node_type('Dummy', 100)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    assert len(d.relation_types[0, 0]) == 0
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    assert len(d.relation_families) == 0
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    prep_d = prepare_training(d, TrainValTest(.8, .1, .1))
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    in_layer = OneHotInputLayer(d)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    d_layer = DecagonLayer(in_layer.output_dim, 32, d)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    dec_layer = DecodeLayer(input_dim=d_layer.output_dim, data=prep_d, keep_prob=1.,
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			        decoder_class=DEDICOMDecoder, activation=lambda x: x)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    dec_layer = DecodeLayer(input_dim=d_layer.output_dim, data=prep_d,
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			        keep_prob=1., activation=lambda x: x)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    seq = torch.nn.Sequential(in_layer, d_layer, dec_layer)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    pred_adj_matrices = seq(None)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    pred = seq(None)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    assert isinstance(pred_adj_matrices, dict)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    assert len(pred_adj_matrices) == 0
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    assert isinstance(pred, Predictions)
 | 
		
		
	
		
			
			 | 
			 | 
			
			 | 
			    assert len(pred.relation_families) == 0
 |