def test_dropout_mlp():
# Run for a couple of iterations
# assert that new error is less than original
model = mlp.DropoutMLP((2, 8, 2))
dataset = datasets.get_and()
error = validation.get_error(model, *dataset)
model.train(*dataset, iterations=20)
assert validation.get_error(model, *dataset) < error
def test_mlp_classifier_convergence():
# Run until convergence
# assert that network can converge
model = mlp.MLP((2, 3, 2),
transfers=mlp.SoftmaxTransfer(),
error_func=CrossEntropy())
dataset = datasets.get_and()
model.train(*dataset, retries=5, error_break=0.002)
assert validation.get_error(model, *dataset) <= 0.02
def test_dropout_mlp_classifier():
# Run for a couple of iterations
# assert that new error is less than original
model = mlp.DropoutMLP((2, 8, 2),
transfers=mlp.SoftmaxTransfer(),
error_func=CrossEntropy())
dataset = datasets.get_and()
error = validation.get_error(model, *dataset)
model.train(*dataset, iterations=20)
assert validation.get_error(model, *dataset) < error
def test_dropout_mlp_convergence():
# Run until convergence
# assert that network can converge
# Since XOR does not really need dropout, we use high probabilities
model = mlp.DropoutMLP((2, 8, 2),
input_active_probability=1.0,
hidden_active_probability=0.9)
dataset = datasets.get_and() # Easier and dataset for lienar output
# Error break lower than cutoff, since dropout may have different error
# after training
model.train(*dataset, retries=5, error_break=0.002, error_improve_iters=50)
# Dropout sacrifices training accuracy for better generalization
# so we don't worry as much about convergence
assert validation.get_error(model, *dataset) <= 0.1
def test_isdataset():
assert validation._isdataset(datasets.get_xor()) is True
assert validation._isdataset([datasets.get_and(),
datasets.get_xor()]) is False