def test_switch_to_ad3():
# smoketest only
# test if switching between qpbo and ad3 works inside latent svm
# use less perfect initialization
if not get_installed(['qpbo']) or not get_installed(['ad3']):
return
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_test, Y_test = X[10:], Y[10:]
X, Y = X[:10], Y[:10]
crf = LatentGridCRF(n_states_per_label=2,
inference_method='qpbo')
crf.initialize(X, Y)
H_init = crf.init_latent(X, Y)
np.random.seed(0)
mask = np.random.uniform(size=H_init.shape) > .7
H_init[mask] = 2 * (H_init[mask] / 2)
base_ssvm = OneSlackSSVM(crf, inactive_threshold=1e-8, cache_tol=.0001,
inference_cache=50, max_iter=10000,
switch_to=('ad3', {'branch_and_bound': True}),
C=10. ** 3)
clf = LatentSSVM(base_ssvm)
clf.fit(X, Y, H_init=H_init)
assert_equal(clf.model.inference_method[0], 'ad3')
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
# test that score is not always 1
assert_true(.98 < clf.score(X_test, Y_test) < 1)
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_with_crosses_bad_init():
# use less perfect initialization
rnd = np.random.RandomState(0)
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_test, Y_test = X[10:], Y[10:]
X, Y = X[:10], Y[:10]
crf = LatentGridCRF(n_states_per_label=2)
crf.initialize(X, Y)
H_init = crf.init_latent(X, Y)
mask = rnd.uniform(size=H_init.shape) > .7
H_init[mask] = 2 * (H_init[mask] / 2)
one_slack_ssvm = OneSlackSSVM(crf,
inactive_threshold=1e-8,
cache_tol=.0001,
inference_cache=50,
C=100)
clf = LatentSSVM(one_slack_ssvm)
clf.fit(X, Y, H_init=H_init)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
# test that score is not always 1
assert_true(.98 < clf.score(X_test, Y_test) < 1)
def test_switch_to_ad3():
# smoketest only
# test if switching between qpbo and ad3 works inside latent svm
# use less perfect initialization
if not get_installed(["qpbo"]) or not get_installed(["ad3"]):
return
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_test, Y_test = X[10:], Y[10:]
X, Y = X[:10], Y[:10]
crf = LatentGridCRF(n_states_per_label=2, inference_method="qpbo")
crf.initialize(X, Y)
H_init = crf.init_latent(X, Y)
np.random.seed(0)
mask = np.random.uniform(size=H_init.shape) > 0.7
H_init[mask] = 2 * (H_init[mask] / 2)
base_ssvm = OneSlackSSVM(
crf,
inactive_threshold=1e-8,
cache_tol=0.0001,
inference_cache=50,
max_iter=10000,
switch_to=("ad3", {"branch_and_bound": True}),
C=10.0 ** 3,
)
clf = LatentSSVM(base_ssvm)
# evil hackery to get rid of ad3 output
try:
devnull = open("/dev/null", "w")
oldstdout_fno = os.dup(sys.stdout.fileno())
os.dup2(devnull.fileno(), 1)
replaced_stdout = True
except:
replaced_stdout = False
clf.fit(X, Y, H_init=H_init)
if replaced_stdout:
os.dup2(oldstdout_fno, 1)
assert_equal(clf.model.inference_method[0], "ad3")
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
# test that score is not always 1
assert_true(0.98 < clf.score(X_test, Y_test) < 1)
def test_switch_to_ad3():
# smoketest only
# test if switching between qpbo and ad3 works inside latent svm
# use less perfect initialization
if not get_installed(['qpbo']) or not get_installed(['ad3']):
return
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_test, Y_test = X[10:], Y[10:]
X, Y = X[:10], Y[:10]
crf = LatentGridCRF(n_states_per_label=2, inference_method='qpbo')
crf.initialize(X, Y)
H_init = crf.init_latent(X, Y)
np.random.seed(0)
mask = np.random.uniform(size=H_init.shape) > .7
H_init[mask] = 2 * (H_init[mask] / 2)
base_ssvm = OneSlackSSVM(crf,
inactive_threshold=1e-8,
cache_tol=.0001,
inference_cache=50,
max_iter=10000,
switch_to=('ad3', {
'branch_and_bound': True
}),
C=10.**3)
clf = LatentSSVM(base_ssvm)
# evil hackery to get rid of ad3 output
try:
devnull = open('/dev/null', 'w')
oldstdout_fno = os.dup(sys.stdout.fileno())
os.dup2(devnull.fileno(), 1)
replaced_stdout = True
except:
replaced_stdout = False
clf.fit(X, Y, H_init=H_init)
if replaced_stdout:
os.dup2(oldstdout_fno, 1)
assert_equal(clf.model.inference_method[0], 'ad3')
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
# test that score is not always 1
assert_true(.98 < clf.score(X_test, Y_test) < 1)
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)
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_objective():
# test that SubgradientLatentSSVM does the same as SubgradientSVM,
# in particular that it has the same loss, if there are no latent states.
X, Y = generate_blocks_multinomial(n_samples=10, noise=.3, seed=1)
inference_method = get_installed(["qpbo", "ad3", "lp"])[0]
n_labels = 3
crfl = LatentGridCRF(n_labels=n_labels, n_states_per_label=1,
inference_method=inference_method)
clfl = SubgradientLatentSSVM(model=crfl, max_iter=20, C=10.,
learning_rate=0.001, momentum=0.98)
crfl.initialize(X, Y)
clfl.w = np.zeros(crfl.size_joint_feature) # this disables random init
clfl.fit(X, Y)
crf = GridCRF(n_states=n_labels, inference_method=inference_method)
clf = SubgradientSSVM(model=crf, max_iter=20, C=10., learning_rate=0.001,
momentum=0.98)
clf.fit(X, Y)
assert_array_almost_equal(clf.w, clfl.w)
assert_almost_equal(clf.objective_curve_[-1], clfl.objective_curve_[-1])
assert_array_equal(clf.predict(X), clfl.predict(X))
assert_array_equal(clf.predict(X), Y)
def test_with_crosses_bad_init():
# use less perfect initialization
rnd = np.random.RandomState(0)
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_test, Y_test = X[10:], Y[10:]
X, Y = X[:10], Y[:10]
crf = LatentGridCRF(n_states_per_label=2)
crf.initialize(X, Y)
H_init = crf.init_latent(X, Y)
mask = rnd.uniform(size=H_init.shape) > 0.7
H_init[mask] = 2 * (H_init[mask] / 2)
one_slack_ssvm = OneSlackSSVM(crf, inactive_threshold=1e-8, cache_tol=0.0001, inference_cache=50, C=100)
clf = LatentSSVM(one_slack_ssvm)
clf.fit(X, Y, H_init=H_init)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
# test that score is not always 1
assert_true(0.98 < clf.score(X_test, Y_test) < 1)
