def test_nested_multioutputs_train():
model = multioutputs.MultiOutputs(
multioutputs.MultiOutputs(LearnOutput(1.0), 2), 2)
model.train([None], numpy.array([[[1, 2], [3, 4]]]))
model.logging = False
assert model.activate([]) == [[1, 2], [3, 4]]
def test_get_error_unusual_targets_shape():
from learning import error
model = multioutputs.MultiOutputs([
helpers.SetOutputModel([1.0]),
helpers.SetOutputModel([1.0, 1.0, 1.0])
])
assert validation.get_error(model, [[]], [[[1.0], [1.0, 1.0, 1.0]]],
error_func=MeanSquaredError()) == 0.0
assert validation.get_error(model, [[]], [[[1.0], [0.0, 0.0, 0.0]]],
error_func=MeanSquaredError()) == 0.5
def test_serialize_unserialize():
dataset = (numpy.random.random((10, 10)), numpy.random.random((10, 2, 10)))
model = multioutputs.MultiOutputs(MLP((10, 2, 10)), 2)
unserialized_model = multioutputs.MultiOutputs.unserialize(
model.serialize())
assert isinstance(unserialized_model, multioutputs.MultiOutputs)
assert (helpers.fix_numpy_array_equality([
model.activate(inp_vec) for inp_vec in dataset[0]
]) == helpers.fix_numpy_array_equality(
[unserialized_model.activate(inp_vec) for inp_vec in dataset[0]]))
def test_multioutputs_train():
model = multioutputs.MultiOutputs(LearnOutput(1.0), 2)
model.train([None], numpy.array([[-1, 1]]))
assert model.activate([]) == [-1, 1]
def test_multioutputs_activate():
model = multioutputs.MultiOutputs(helpers.SetOutputModel(1), 2)
assert model.activate([None]) == [1, 1]
def test_multioutputs_list_of_models():
model = multioutputs.MultiOutputs([LearnOutput(1.0), LearnOutput(1.0)])
model.train([[None]], numpy.array([[-1, 1]]))
assert model.activate([]) == [-1, 1]
