|
@@ -102,17 +102,17 @@ def test_decode_layer_03(): |
|
|
def test_decode_layer_04():
|
|
|
def test_decode_layer_04():
|
|
|
d = Data()
|
|
|
d = Data()
|
|
|
d.add_node_type('Dummy', 100)
|
|
|
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))
|
|
|
prep_d = prepare_training(d, TrainValTest(.8, .1, .1))
|
|
|
|
|
|
|
|
|
in_layer = OneHotInputLayer(d)
|
|
|
in_layer = OneHotInputLayer(d)
|
|
|
d_layer = DecagonLayer(in_layer.output_dim, 32, 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)
|
|
|
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
|