MCPcopy
hub / github.com/shenweichen/DeepCTR-Torch / test_FiBiNET

Function test_FiBiNET

tests/models/FiBiNET_test.py:13–20  ·  view source on GitHub ↗
(bilinear_type)

Source from the content-addressed store, hash-verified

11 "interaction", "all"]
12)
13def test_FiBiNET(bilinear_type):
14 model_name = "FiBiNET"
15 sample_size = SAMPLE_SIZE
16 x, y, feature_columns = get_test_data(sample_size, sparse_feature_num=3, dense_feature_num=3)
17
18 model = FiBiNET(feature_columns, feature_columns,
19 bilinear_type=bilinear_type, dnn_hidden_units=[8, 8], dnn_dropout=0.5, device=get_device())
20 check_model(model, model_name, x, y)
21
22
23if __name__ == "__main__":

Callers

nothing calls this directly

Calls 4

FiBiNETClass · 0.90
get_test_dataFunction · 0.85
check_modelFunction · 0.85
get_deviceFunction · 0.50

Tested by

no test coverage detected