def test_blocks_crf_directional():
# test latent directional CRF on blocks
# test that all results are the same as equivalent LatentGridCRF
X, Y = toy.generate_blocks(n_samples=1)
x, y = X[0], Y[0]
pairwise_weights = np.array([0, 0, 0, -4, -4, 0, -4, -4, 0, 0])
unary_weights = np.repeat(np.eye(2), 2, axis=0)
w = np.hstack([unary_weights.ravel(), pairwise_weights])
pw_directional = np.array(
[0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0, 0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0]
)
w_directional = np.hstack([unary_weights.ravel(), pw_directional])
crf = LatentGridCRF(n_labels=2, n_states_per_label=2)
directional_crf = LatentDirectionalGridCRF(n_labels=2, n_states_per_label=2)
h_hat = crf.inference(x, w)
h_hat_d = directional_crf.inference(x, w_directional)
assert_array_equal(h_hat, h_hat_d)
h = crf.latent(x, y, w)
h_d = directional_crf.latent(x, y, w_directional)
assert_array_equal(h, h_d)
h_hat = crf.loss_augmented_inference(x, y, w)
h_hat_d = directional_crf.loss_augmented_inference(x, y, w_directional)
assert_array_equal(h_hat, h_hat_d)
psi = crf.psi(x, h_hat)
psi_d = directional_crf.psi(x, h_hat)
assert_array_equal(np.dot(psi, w), np.dot(psi_d, w_directional))
def test_k_means_initialization_directional_grid_crf():
X, Y = generate_big_checker(n_samples=10)
crf = LatentDirectionalGridCRF(n_states_per_label=1, n_features=2,
n_labels=2)
#crf.initialize(X, Y)
H = crf.init_latent(X, Y)
assert_array_equal(Y, H)
def test_k_means_initialization_directional_grid_crf():
X, Y = generate_big_checker(n_samples=10)
crf = LatentDirectionalGridCRF(n_states_per_label=1, n_features=2,
n_labels=2)
#crf.initialize(X, Y)
H = crf.init_latent(X, Y)
assert_array_equal(Y, H)
def test_blocks_crf_directional():
# test latent directional CRF on blocks
# test that all results are the same as equivalent LatentGridCRF
X, Y = generate_blocks(n_samples=1)
x, y = X[0], Y[0]
pairwise_weights = np.array([0, 0, 0, -4, -4, 0, -4, -4, 0, 0])
unary_weights = np.repeat(np.eye(2), 2, axis=0)
w = np.hstack([unary_weights.ravel(), pairwise_weights])
pw_directional = np.array([
0, 0, -4, -4, 0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0, 0, 0, -4, -4,
0, 0, -4, -4, -4, -4, 0, 0, -4, -4, 0, 0
])
w_directional = np.hstack([unary_weights.ravel(), pw_directional])
crf = LatentGridCRF(n_states_per_label=2, inference_method='lp')
crf.initialize(X, Y)
directional_crf = LatentDirectionalGridCRF(n_states_per_label=2,
inference_method='lp')
directional_crf.initialize(X, Y)
h_hat = crf.inference(x, w)
h_hat_d = directional_crf.inference(x, w_directional)
assert_array_equal(h_hat, h_hat_d)
h = crf.latent(x, y, w)
h_d = directional_crf.latent(x, y, w_directional)
assert_array_equal(h, h_d)
h_hat = crf.loss_augmented_inference(x, y, w)
h_hat_d = directional_crf.loss_augmented_inference(x, y, w_directional)
assert_array_equal(h_hat, h_hat_d)
joint_feature = crf.joint_feature(x, h_hat)
joint_feature_d = directional_crf.joint_feature(x, h_hat)
assert_array_equal(np.dot(joint_feature, w),
np.dot(joint_feature_d, w_directional))
def test_directional_bars():
# this test is very fragile :-/
X, Y = generate_easy(n_samples=20, noise=2, box_size=2, total_size=6,
seed=2)
n_labels = 2
crf = LatentDirectionalGridCRF(n_labels=n_labels,
n_states_per_label=[1, 4])
clf = SubgradientLatentSSVM(model=crf, max_iter=75, C=10.,
learning_rate=1, momentum=0,
decay_exponent=0.5, decay_t0=10)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
def test_directional_bars():
X, Y = generate_easy(n_samples=10,
noise=5,
box_size=2,
total_size=6,
seed=1)
n_labels = 2
crf = LatentDirectionalGridCRF(n_labels=n_labels,
n_states_per_label=[1, 4])
clf = LatentSSVM(
OneSlackSSVM(model=crf,
max_iter=500,
C=10.,
inference_cache=50,
tol=.01))
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
def test_k_means_initialization_directional_grid_crf():
X, Y = toy.generate_big_checker(n_samples=10)
crf = LatentDirectionalGridCRF(n_labels=2, n_states_per_label=1, inference_method="lp")
H = crf.init_latent(X, Y)
assert_array_equal(Y, H)