def test_dropout_transfer_probability_zero():
length = random.randint(1, 20)
# Can't actually be zero, but can be close enough
dropout_transfer = mlp.DropoutTransfer(mlp.LinearTransfer(), 1e-16, length)
# Should not allow zero active, defaults to 1
assert list(dropout_transfer._active_neurons).count(1.0) == 1
assert list(dropout_transfer._active_neurons).count(0.0) == length - 1
def test_dropout_transfer_probability_one():
length = random.randint(1, 20)
dropout_transfer = mlp.DropoutTransfer(mlp.LinearTransfer(), 1.0, length)
assert (dropout_transfer._active_neurons == numpy.array(
[1.0] * length)).all(), 'All should be active'
# Random input
input_vec = numpy.random.random(length)
assert (dropout_transfer(input_vec) == input_vec).all()
def test_mlp_perceptron():
# Given known inputs and weights, test expected outputs
model = mlp.MLP((2, 1), transfers=mlp.LinearTransfer())
model._weight_matrices[0][0][0] = 0.0
model._weight_matrices[0][1][0] = 0.5
model._weight_matrices[0][2][0] = -0.5
assert (model.activate([1, 1]) == [0.0]).all()
model._weight_matrices[0][1][0] = 1.0
model._weight_matrices[0][2][0] = 2.0
assert (model.activate([1, 1]) == [3.0]).all()
def test_mlp_jacobian_lin_out_mse():
_check_jacobian(lambda s1, s2, s3: mlp.MLP(
(s1, s2, s3), transfers=mlp.LinearTransfer(), error_func=MSE()))
def test_mlp_obj_and_obj_jac_match_lin_out_mse():
_check_obj_and_obj_jac_match(lambda s1, s2, s3: mlp.MLP(
(s1, s2, s3), transfers=mlp.LinearTransfer(), error_func=MSE()))