def test_concat_generator():
size1, size2 = 10, 20
t_min, t_max = 0.5, 1.5
generator1 = Generator1D(size1, t_min=t_min, t_max=t_max)
generator2 = Generator1D(size2, t_min=t_min, t_max=t_max)
concat_generator = ConcatGenerator(generator1, generator2)
x = concat_generator.get_examples()
assert _check_shape_and_grad(concat_generator, size1 + size2, x)
grid1 = (4, 4, 4)
size1, size2, size3 = grid1[0] * grid1[1] * grid1[2], 100, 200
generator1 = Generator3D(grid=grid1)
generator2 = GeneratorSpherical(size2)
generator3 = GeneratorSpherical(size3)
concat_generator = ConcatGenerator(generator1, generator2, generator3)
r, theta, phi = concat_generator.get_examples()
assert _check_shape_and_grad(concat_generator, size1 + size2 + size3, r,
theta, phi)
added_generator = generator1 + generator2 + generator3
r, theta, phi = added_generator.get_examples()
assert _check_shape_and_grad(added_generator, size1 + size2 + size3, r,
theta, phi)
str(concat_generator)
repr(concat_generator)
def x():
g = EnsembleGenerator(
Generator1D(GRID[0], R_MIN, R_MAX, method='uniform'),
Generator1D(GRID[1], 0, np.pi * 2, method='uniform'),
Generator1D(GRID[2], Z_MIN, Z_MAX, method='uniform'),
)
return SamplerGenerator(g).get_examples()
def generators():
return dict(
train=Generator1D(64, t_min=T_MIN, t_max=T_MAX, method='uniform'),
valid=Generator1D(64,
t_min=T_MIN,
t_max=T_MAX,
method='equally-spaced'),
)
def __init__(
self,
ode_system,
conditions,
t_min,
t_max,
nets=None,
train_generator=None,
valid_generator=None,
analytic_solutions=None,
optimizer=None,
criterion=None,
n_batches_train=1,
n_batches_valid=4,
metrics=None,
n_output_units=1,
# deprecated arguments are listed below
batch_size=None,
shuffle=None):
if train_generator is None or valid_generator is None:
if t_min is None or t_max is None:
raise ValueError(
f"Either generator is not provided, t_min and t_max should be both provided: \n"
f"got t_min={t_min}, t_max={t_max}, "
f"train_generator={train_generator}, valid_generator={valid_generator}"
)
if train_generator is None:
train_generator = Generator1D(32,
t_min=t_min,
t_max=t_max,
method='equally-spaced-noisy')
if valid_generator is None:
valid_generator = Generator1D(32,
t_min=t_min,
t_max=t_max,
method='equally-spaced')
self.t_min, self.t_max = t_min, t_max
super(Solver1D, self).__init__(
diff_eqs=ode_system,
conditions=conditions,
nets=nets,
train_generator=train_generator,
valid_generator=valid_generator,
analytic_solutions=analytic_solutions,
optimizer=optimizer,
criterion=criterion,
n_batches_train=n_batches_train,
n_batches_valid=n_batches_valid,
metrics=metrics,
n_input_units=1,
n_output_units=n_output_units,
shuffle=shuffle,
batch_size=batch_size,
)
def test_generator1d_log_spaced_input(method):
size = 32
with pytest.raises(ValueError):
Generator1D(size=size, t_min=0.0, t_max=1.0, method=method)
with pytest.raises(ValueError):
Generator1D(size=size, t_min=1.0, t_max=0.0, method=method)
with pytest.raises(ValueError):
Generator1D(size=size, t_min=-1.0, t_max=1.0, method=method)
with pytest.raises(ValueError):
Generator1D(size=size, t_min=1.0, t_max=-1.0, method=method)
def test_ensemble_generator():
size = 100
generator1 = Generator1D(size)
ensemble_generator = EnsembleGenerator(generator1)
x = ensemble_generator.get_examples()
assert _check_shape_and_grad(ensemble_generator, size, x)
old_x = torch.rand(size)
old_y = torch.rand(size)
old_z = torch.rand(size)
generator1 = PredefinedGenerator(old_x)
generator2 = PredefinedGenerator(old_y)
generator3 = PredefinedGenerator(old_z)
ensemble_generator = EnsembleGenerator(generator1, generator2, generator3)
x, y, z = ensemble_generator.get_examples()
assert _check_shape_and_grad(ensemble_generator, size, x, y, z)
assert _check_iterable_equal(old_x, x)
assert _check_iterable_equal(old_y, y)
assert _check_iterable_equal(old_z, z)
old_x = torch.rand(size)
old_y = torch.rand(size)
generator1 = PredefinedGenerator(old_x)
generator2 = PredefinedGenerator(old_y)
product_generator = generator1 * generator2
x, y = product_generator.get_examples()
assert _check_shape_and_grad(product_generator, size, x, y)
assert _check_iterable_equal(old_x, x)
assert _check_iterable_equal(old_y, y)
str(ensemble_generator)
repr(ensemble_generator)
def test_generator1d():
size = 32
generator = Generator1D(size=size, t_min=0.0, t_max=2.0, method='uniform')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size, t_min=0.0, t_max=2.0, method='equally-spaced')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size, t_min=0.0, t_max=2.0, method='equally-spaced-noisy')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size, t_min=np.log10(0.1), t_max=np.log10(2.0), method='log-spaced')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size, t_min=np.log10(0.1), t_max=np.log10(2.0), method='log-spaced-noisy')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size, t_min=np.log10(0.1), t_max=np.log10(2.0), method='log-spaced-noisy',
noise_std=0.01)
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
with raises(ValueError):
generator = Generator1D(size=size, t_min=0.0, t_max=2.0, method='magic')
print('ExampleGenerator test passed.')
def test_sampler_geneartor():
size = 10
generator = Generator1D(size)
sampler_generator = SamplerGenerator(generator)
x = sampler_generator.get_examples()
assert isinstance(x, (list, tuple))
x, = x
assert x.shape == (size, 1)
print('testing generator name: ', sampler_generator)
def test_sampler_geneartor():
size = 10
generator = Generator1D(size)
sampler_generator = SamplerGenerator(generator)
x = sampler_generator.get_examples()
assert isinstance(x, (list, tuple))
x, = x
assert x.shape == (size, 1)
str(sampler_generator)
repr(sampler_generator)
def test_train_generator():
exponential = lambda x, t: diff(x, t) - x
init_val_ex = IVP(t_0=0.0, x_0=1.0)
train_gen = Generator1D(size=32, t_min=0.0, t_max=2.0, method='uniform')
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.0, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
train_gen = Generator1D(size=32, t_min=0.0, t_max=2.0, method='equally-spaced')
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.0, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
train_gen = Generator1D(size=32, t_min=0.0, t_max=2.0, method='equally-spaced-noisy')
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.0, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
train_gen = Generator1D(size=32, t_min=0.0, t_max=2.0, method='equally-spaced-noisy', noise_std=0.01)
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.0, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
train_gen = Generator1D(size=32, t_min=np.log10(0.1), t_max=np.log10(2.0), method='log-spaced')
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.1, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
train_gen = Generator1D(size=32, t_min=np.log10(0.1), t_max=np.log10(2.0), method='log-spaced-noisy')
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.1, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
train_gen = Generator1D(size=32, t_min=np.log10(0.1), t_max=np.log10(2.0), method='log-spaced-noisy', noise_std=0.01)
solution_ex, _ = solve(ode=exponential, condition=init_val_ex,
t_min=0.1, t_max=2.0,
train_generator=train_gen,
max_epochs=3)
with raises(ValueError):
train_gen = Generator1D(size=32, t_min=0.0, t_max=2.0, method='magic')
print('ExampleGenerator test passed.')
def test_static_generator():
size = 100
generator = Generator1D(size)
static_generator = StaticGenerator(generator)
x1 = static_generator.get_examples()
x2 = static_generator.get_examples()
assert _check_shape_and_grad(generator, size)
assert _check_shape_and_grad(static_generator, size, x1, x2)
assert (x1 == x2).all()
size = 100
generator = GeneratorSpherical(size)
static_generator = StaticGenerator(generator)
r1, theta1, phi1 = static_generator.get_examples()
r2, theta2, phi2 = static_generator.get_examples()
assert _check_shape_and_grad(generator, size)
assert _check_shape_and_grad(static_generator, size, r1, theta1, phi1, r2, theta2, phi2)
assert (r1 == r2).all() and (theta1 == theta2).all() and (phi1 == phi2).all()
def test_mesh_generator():
size = 10
x_min, x_max = 0.0, 1.0
y_min, y_max = 1.0, 2.0
z_min, z_max = 2.0, 3.0
generator1 = Generator1D(size)
mesh_generator = MeshGenerator(generator1)
x = mesh_generator.get_examples()
assert _check_shape_and_grad(mesh_generator, size, x)
mesh_generator = MeshGenerator(generator1, generator1, generator1)
m1, m2, m3 = mesh_generator.get_examples()
assert _check_shape_and_grad(mesh_generator, (size**3), m1, m2, m3)
generator1x = Generator1D(size, x_min, x_max, method="equally-spaced")
generator1y = Generator1D(size, y_min, y_max, method="equally-spaced")
generator1z = Generator1D(size, z_min, z_max, method="equally-spaced")
generator3 = Generator3D((size, size, size), (x_min, y_min, z_min),
(x_max, y_max, z_max),
method="equally-spaced")
mesh_generator = MeshGenerator(generator1x, generator1y, generator1z)
m1, m2, m3 = mesh_generator.get_examples()
g1, g2, g3 = generator3.get_examples()
assert _check_shape_and_grad(mesh_generator, (size**3), m1, m2, m3)
assert _check_iterable_equal(g1, m1)
assert _check_iterable_equal(g2, m2)
assert _check_iterable_equal(g3, m3)
generator1x = Generator1D(size, x_min, x_max, method="equally-spaced")
generator1y = Generator1D(size, y_min, y_max, method="equally-spaced")
generator1z = Generator1D(size, z_min, z_max, method="equally-spaced")
generator3 = Generator3D((size, size, size), (x_min, y_min, z_min),
(x_max, y_max, z_max),
method="equally-spaced")
xor_generator = generator1x ^ generator1y ^ generator1z
m1, m2, m3 = xor_generator.get_examples()
g1, g2, g3 = generator3.get_examples()
assert _check_shape_and_grad(xor_generator, (size**3), m1, m2, m3)
assert _check_iterable_equal(g1, m1)
assert _check_iterable_equal(g2, m2)
assert _check_iterable_equal(g3, m3)
str(mesh_generator)
repr(mesh_generator)
def test_generator1d():
size = 32
generator = Generator1D(size=size, t_min=0.0, t_max=2.0, method='uniform')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.0,
t_max=2.0,
method='equally-spaced')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.0,
t_max=2.0,
method='equally-spaced-noisy')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.1,
t_max=2.0,
method='log-spaced')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.1,
t_max=2.0,
method='log-spaced-noisy')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.1,
t_max=2.0,
method='log-spaced-noisy',
noise_std=0.01)
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.1,
t_max=2.0,
method='chebyshev')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.1,
t_max=2.0,
method='chebyshev1')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
generator = Generator1D(size=size,
t_min=0.1,
t_max=2.0,
method='chebyshev2')
x = generator.getter()
assert _check_shape_and_grad(generator, size, x)
with raises(ValueError):
generator = Generator1D(size=size,
t_min=0.0,
t_max=2.0,
method='magic')
str(generator)
repr(generator)
