def test_latent_node_boxes_edge_features():
# learn the "easy" 2x2 boxes dataset.
# smoketest using a single constant edge feature
X, Y = make_simple_2x2(seed=1, n_samples=40)
latent_crf = EdgeFeatureLatentNodeCRF(n_labels=2,
n_hidden_states=2,
n_features=1)
base_svm = OneSlackSSVM(latent_crf)
base_svm.C = 10
latent_svm = LatentSSVM(base_svm, latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = make_edges_2x2()
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
Y_flat = [y.ravel() for y in Y]
#X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
# add edge features
X_ = [(x, g, np.ones((len(g), 1)), 4) for x, g in zip(X_flat, G)]
latent_svm.fit(X_[:20], Y_flat[:20])
assert_array_equal(latent_svm.predict(X_[:20]), Y_flat[:20])
assert_equal(latent_svm.score(X_[:20], Y_flat[:20]), 1)
# test that score is not always 1
assert_true(.98 < latent_svm.score(X_[20:], Y_flat[20:]) < 1)
def test_latent_node_boxes_edge_features():
# learn the "easy" 2x2 boxes dataset.
# smoketest using a single constant edge feature
X, Y = make_simple_2x2(seed=1, n_samples=40)
latent_crf = EdgeFeatureLatentNodeCRF(n_labels=2, n_hidden_states=2, n_features=1)
base_svm = OneSlackSSVM(latent_crf)
base_svm.C = 10
latent_svm = LatentSSVM(base_svm,
latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = make_edges_2x2()
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
Y_flat = [y.ravel() for y in Y]
#X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
# add edge features
X_ = [(x, g, np.ones((len(g), 1)), 4) for x, g in zip(X_flat, G)]
latent_svm.fit(X_[:20], Y_flat[:20])
assert_array_equal(latent_svm.predict(X_[:20]), Y_flat[:20])
assert_equal(latent_svm.score(X_[:20], Y_flat[:20]), 1)
# test that score is not always 1
assert_true(.98 < latent_svm.score(X_[20:], Y_flat[20:]) < 1)
def test_latent_node_boxes_standard_latent():
# learn the "easy" 2x2 boxes dataset.
# a 2x2 box is placed randomly in a 4x4 grid
# we add a latent variable for each 2x2 patch
# that should make the model fairly simple
X, Y = make_simple_2x2(seed=1, n_samples=40)
latent_crf = LatentNodeCRF(n_labels=2, n_hidden_states=2, n_features=1)
one_slack = OneSlackSSVM(latent_crf)
n_slack = NSlackSSVM(latent_crf)
subgradient = SubgradientSSVM(latent_crf, max_iter=100)
for base_svm in [one_slack, n_slack, subgradient]:
base_svm.C = 10
latent_svm = LatentSSVM(base_svm, latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = make_edges_2x2()
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
Y_flat = [y.ravel() for y in Y]
X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
latent_svm.fit(X_[:20], Y_flat[:20])
assert_array_equal(latent_svm.predict(X_[:20]), Y_flat[:20])
assert_equal(latent_svm.score(X_[:20], Y_flat[:20]), 1)
# test that score is not always 1
assert_true(.98 < latent_svm.score(X_[20:], Y_flat[20:]) < 1)
def test_latent_node_boxes_standard_latent():
# learn the "easy" 2x2 boxes dataset.
# a 2x2 box is placed randomly in a 4x4 grid
# we add a latent variable for each 2x2 patch
# that should make the model fairly simple
X, Y = make_simple_2x2(seed=1, n_samples=40)
latent_crf = LatentNodeCRF(n_labels=2, n_hidden_states=2, n_features=1)
one_slack = OneSlackSSVM(latent_crf)
n_slack = NSlackSSVM(latent_crf)
subgradient = SubgradientSSVM(latent_crf, max_iter=100)
for base_svm in [one_slack, n_slack, subgradient]:
base_svm.C = 10
latent_svm = LatentSSVM(base_svm,
latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = make_edges_2x2()
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
Y_flat = [y.ravel() for y in Y]
X_ = list(zip(X_flat, G, [2 * 2 for x in X_flat]))
latent_svm.fit(X_[:20], Y_flat[:20])
assert_array_equal(latent_svm.predict(X_[:20]), Y_flat[:20])
assert_equal(latent_svm.score(X_[:20], Y_flat[:20]), 1)
# test that score is not always 1
assert_true(.98 < latent_svm.score(X_[20:], Y_flat[20:]) < 1)
def test_states(states, x, y, x_t, y_t, i, jobs):
latent_pbl = GraphLDCRF(n_states_per_label=states, inference_method="qpbo")
base_ssvm = NSlackSSVM(latent_pbl, C=1, tol=0.01, inactive_threshold=1e-3, batch_size=10, verbose=0, n_jobs=jobs)
latent_svm = LatentSSVM(base_ssvm=base_ssvm, latent_iter=3)
latent_svm.fit(x, y)
test = latent_svm.score(x_t, y_t)
train = latent_svm.score(x, y)
plot_cm(latent_svm, y_t, x_t, str(states), i)
print states, "Test:", test, "Train:", train
return test, train
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_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_with_crosses_bad_init():
# use less perfect initialization
rnd = np.random.RandomState(0)
X, Y = toy.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]
n_labels = 2
crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=2)
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 = OneSlackSSVM(crf, inactive_threshold=1e-8, cache_tol=.0001,
inference_cache=50, max_iter=10000)
n_slack = NSlackSSVM(crf)
subgradient = SubgradientSSVM(crf, max_iter=150, learning_rate=.01,
momentum=0)
for base_ssvm in [one_slack, n_slack, subgradient]:
base_ssvm.C = 10. ** 2
clf = LatentSSVM(base_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_states(states, x, y, x_t, y_t, jobs):
latent_pbl = GraphLDCRF(n_states_per_label=states, inference_method='qpbo')
base_ssvm = NSlackSSVM(latent_pbl,
C=1,
tol=.01,
inactive_threshold=1e-3,
batch_size=10,
verbose=0,
n_jobs=jobs)
latent_svm = LatentSSVM(base_ssvm=base_ssvm, latent_iter=3)
latent_svm.fit(x, y)
test = latent_svm.score(x_t, y_t)
train = latent_svm.score(x, y)
print states, 'Test:', test, 'Train:', train
return test, train
def test_latent_node_boxes_standard_latent_features():
# learn the "easy" 2x2 boxes dataset.
# we make it even easier now by adding features that encode the correct
# latent state. This basically tests that the features are actually used
X, Y = make_simple_2x2(seed=1, n_samples=20, n_flips=6)
latent_crf = LatentNodeCRF(n_labels=2,
n_hidden_states=2,
n_features=1,
latent_node_features=True)
one_slack = OneSlackSSVM(latent_crf)
n_slack = NSlackSSVM(latent_crf)
subgradient = SubgradientSSVM(latent_crf,
max_iter=100,
learning_rate=0.01,
momentum=0)
for base_svm in [one_slack, n_slack, subgradient]:
base_svm.C = 10
latent_svm = LatentSSVM(base_svm, latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = make_edges_2x2()
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
# augment X with the features for hidden units
X_flat = [
np.vstack([x, y[::2, ::2].reshape(-1, 1)])
for x, y in zip(X_flat, Y)
]
Y_flat = [y.ravel() for y in Y]
X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
latent_svm.fit(X_[:10], Y_flat[:10])
assert_array_equal(latent_svm.predict(X_[:10]), Y_flat[:10])
assert_equal(latent_svm.score(X_[:10], Y_flat[:10]), 1)
# we actually become prefect ^^
assert_true(.98 < latent_svm.score(X_[10:], Y_flat[10:]) <= 1)
def test_latent_node_boxes_standard_latent_features():
# learn the "easy" 2x2 boxes dataset.
# we make it even easier now by adding features that encode the correct
# latent state. This basically tests that the features are actually used
X, Y = make_simple_2x2(seed=1, n_samples=20, n_flips=6)
latent_crf = LatentNodeCRF(n_labels=2, n_hidden_states=2, n_features=1,
latent_node_features=True)
one_slack = OneSlackSSVM(latent_crf)
n_slack = NSlackSSVM(latent_crf)
subgradient = SubgradientSSVM(latent_crf, max_iter=100, learning_rate=0.01,
momentum=0)
for base_svm in [one_slack, n_slack, subgradient]:
base_svm.C = 10
latent_svm = LatentSSVM(base_svm,
latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = make_edges_2x2()
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
# augment X with the features for hidden units
X_flat = [np.vstack([x, y[::2, ::2].reshape(-1, 1)])
for x, y in zip(X_flat, Y)]
Y_flat = [y.ravel() for y in Y]
X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
latent_svm.fit(X_[:10], Y_flat[:10])
assert_array_equal(latent_svm.predict(X_[:10]), Y_flat[:10])
assert_equal(latent_svm.score(X_[:10], Y_flat[:10]), 1)
# we actually become prefect ^^
assert_true(.98 < latent_svm.score(X_[10:], Y_flat[10:]) <= 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_with_crosses_perfect_init():
# very simple dataset. k-means init is perfect
for n_states_per_label in [2, [1, 2]]:
# test with 2 states for both foreground and background,
# as well as with single background state
X, Y = generate_crosses(n_samples=10, noise=5, n_crosses=1, total_size=8)
n_labels = 2
crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=n_states_per_label)
clf = LatentSSVM(
OneSlackSSVM(model=crf, max_iter=500, C=10, check_constraints=False, break_on_bad=False, inference_cache=50)
)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
assert_equal(clf.score(X, Y), 1)
def test_with_crosses_base_svms():
# very simple dataset. k-means init is perfect
n_labels = 2
crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=[1, 2])
one_slack = OneSlackSSVM(crf, inference_cache=50)
n_slack = NSlackSSVM(crf)
subgradient = SubgradientSSVM(crf, max_iter=400, learning_rate=0.01, decay_exponent=0, decay_t0=10)
X, Y = generate_crosses(n_samples=10, noise=5, n_crosses=1, total_size=8)
for base_ssvm in [one_slack, n_slack, subgradient]:
base_ssvm.C = 100.0
clf = LatentSSVM(base_ssvm=base_ssvm)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
assert_equal(clf.score(X, Y), 1)
def main():
X, Y = toy.generate_crosses(n_samples=20, noise=5, n_crosses=1,
total_size=8)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5)
n_labels = len(np.unique(Y_train))
crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=[1, 2],
inference_method='lp')
clf = LatentSSVM(problem=crf, max_iter=50, C=1000., verbose=2,
check_constraints=True, n_jobs=-1, break_on_bad=True)
clf.fit(X_train, Y_train)
i = 0
for X_, Y_, H, name in [[X_train, Y_train, clf.H_init_, "train"],
[X_test, Y_test, [None] * len(X_test), "test"]]:
Y_pred = clf.predict(X_)
score = clf.score(X_, Y_)
for x, y, h_init, y_pred in zip(X_, Y_, H, Y_pred):
fig, ax = plt.subplots(4, 1)
ax[0].matshow(y, vmin=0, vmax=crf.n_labels - 1)
ax[0].set_title("Ground truth")
ax[1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1)
ax[1].set_title("Unaries only")
#if h_init is None:
#ax[1, 0].set_visible(False)
#else:
#ax[1, 0].matshow(h_init, vmin=0, vmax=crf.n_states - 1)
#ax[1, 0].set_title("latent initial")
#ax[2].matshow(crf.latent(x, y, clf.w),
#vmin=0, vmax=crf.n_states - 1)
#ax[2].set_title("latent final")
ax[2].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states
- 1)
ax[2].set_title("Prediction for h")
ax[3].matshow(y_pred, vmin=0, vmax=crf.n_labels - 1)
ax[3].set_title("Prediction for y")
for a in ax.ravel():
a.set_xticks(())
a.set_yticks(())
plt.subplots_adjust(hspace=.5)
fig.savefig("data_%s_%03d.png" % (name, i), bbox_inches="tight",
dpi=400)
i += 1
print("score %s set: %f" % (name, score))
print(clf.w)
def test_with_crosses_base_svms():
# very simple dataset. k-means init is perfect
n_labels = 2
crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=[1, 2])
one_slack = OneSlackSSVM(crf, inference_cache=50)
n_slack = NSlackSSVM(crf)
subgradient = SubgradientSSVM(crf,
max_iter=400,
learning_rate=.01,
decay_exponent=0,
decay_t0=10)
X, Y = generate_crosses(n_samples=10, noise=5, n_crosses=1, total_size=8)
for base_ssvm in [one_slack, n_slack, subgradient]:
base_ssvm.C = 100.
clf = LatentSSVM(base_ssvm=base_ssvm)
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
assert_equal(clf.score(X, Y), 1)
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)
def test_latent_node_boxes_standard_latent():
# learn the "easy" 2x2 boxes dataset.
# a 2x2 box is placed randomly in a 4x4 grid
# we add a latent variable for each 2x2 patch
# that should make the model fairly simple
X, Y = toy.make_simple_2x2(seed=1)
latent_crf = LatentNodeCRF(n_labels=2, inference_method='lp',
n_hidden_states=2, n_features=1)
one_slack = OneSlackSSVM(latent_crf)
n_slack = StructuredSVM(latent_crf)
subgradient = SubgradientSSVM(latent_crf, max_iter=100, learning_rate=0.01,
momentum=0)
for base_svm in [one_slack, n_slack, subgradient]:
base_svm.C = 10
latent_svm = LatentSSVM(base_svm,
latent_iter=10)
G = [make_grid_edges(x) for x in X]
# make edges for hidden states:
edges = []
node_indices = np.arange(4 * 4).reshape(4, 4)
for i, (x, y) in enumerate(itertools.product([0, 2], repeat=2)):
for j in xrange(x, x + 2):
for k in xrange(y, y + 2):
edges.append([i + 4 * 4, node_indices[j, k]])
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# reshape / flatten x and y
X_flat = [x.reshape(-1, 1) for x in X]
Y_flat = [y.ravel() for y in Y]
X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
latent_svm.fit(X_, Y_flat)
assert_equal(latent_svm.score(X_, Y_flat), 1)
def test_with_crosses_perfect_init():
# very simple dataset. k-means init is perfect
for n_states_per_label in [2, [1, 2]]:
# test with 2 states for both foreground and background,
# as well as with single background state
X, Y = generate_crosses(n_samples=10,
noise=5,
n_crosses=1,
total_size=8)
n_labels = 2
crf = LatentGridCRF(n_labels=n_labels,
n_states_per_label=n_states_per_label)
clf = LatentSSVM(
OneSlackSSVM(model=crf,
max_iter=500,
C=10,
check_constraints=False,
break_on_bad=False,
inference_cache=50))
clf.fit(X, Y)
Y_pred = clf.predict(X)
assert_array_equal(np.array(Y_pred), Y)
assert_equal(clf.score(X, Y), 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 = toy.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]
n_labels = 2
crf = LatentGridCRF(n_labels=n_labels, n_states_per_label=2,
inference_method='qpbo')
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='ad3bb', C=10. ** 3)
clf = LatentSSVM(base_ssvm)
clf.fit(X, Y, H_init=H_init)
# we actually switch back from ad3bb to the original
assert_equal(clf.model.inference_method, "qpbo")
# unfortunately this test only works with ad3
clf.base_ssvm.model.inference_method = 'ad3bb'
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)
show_loss_every=10,
inference_cache=50)
latent_svm = LatentSSVM(ssvm)
# make edges for hidden states:
edges = []
node_indices = np.arange(4 * 4).reshape(4, 4)
for i, (x, y) in enumerate(itertools.product([0, 2], repeat=2)):
for j in xrange(x, x + 2):
for k in xrange(y, y + 2):
edges.append([i + 4 * 4, node_indices[j, k]])
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# Random initialization
H_init = [
np.hstack([y.ravel(), np.random.randint(2, 4, size=2 * 2)]) for y in Y
]
plot_boxes(H_init,
title="Top: Random initial hidden states. Bottom: Ground"
"truth labeling.")
X_ = zip(X_flat, G, [2 * 2 for x in X_flat])
latent_svm.fit(X_, Y_flat, H_init)
print("Training score with latent nodes: %f " % latent_svm.score(X_, Y_flat))
H = latent_svm.predict_latent(X_)
plot_boxes(H, title="Top: Hidden states after training. Bottom: Prediction.")
plt.show()
latent_pbl = LatentGraphCRF(n_states_per_label=5, inference_method='unary')
base_ssvm = NSlackSSVM(latent_pbl,
C=1,
tol=.01,
inactive_threshold=1e-3,
batch_size=10)
latent_svm = LatentSSVM(base_ssvm=base_ssvm, latent_iter=2)
latent_svm.fit(X_train_, y_train)
print("Score with binary SVM:")
print("Train: {:2.2f}".format(svm.score(X_train_, y_train)))
print("Test: {:2.2f}".format(svm.score(X_test_, y_test)))
print("Score with latent SVM:")
print("Train: {:2.2f}".format(latent_svm.score(X_train_, y_train)))
print("Test: {:2.2f}".format(latent_svm.score(X_test_, y_test)))
h_pred = np.hstack(latent_svm.predict_latent(X_test_))
print("Latent class counts: %s" % repr(np.bincount(h_pred)))
# plot first few digits from each latent class
plt.figure(figsize=(3, 5))
plt.suptitle("Example digits from each of\nthe ten latent classes.")
n_latent_classes = 10
n_examples = 7
for latent_class in xrange(n_latent_classes):
examples = X_test[h_pred == latent_class][:n_examples]
for k, example in enumerate(examples):
plt.subplot(n_latent_classes, n_examples,
from pystruct.learners import LatentSSVM, OneSlackSSVM
from pystruct.datasets import generate_crosses
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5)
crf = LatentGridCRF(n_states_per_label=[1, 2])
base_ssvm = OneSlackSSVM(model=crf,
C=10.,
n_jobs=-1,
inference_cache=20,
tol=.1)
clf = LatentSSVM(base_ssvm=base_ssvm)
clf.fit(X_train, Y_train)
print("loss training set: %f" % clf.score(X_train, Y_train))
print("loss test set: %f" % clf.score(X_test, Y_test))
Y_pred = clf.predict(X_test)
x, y, y_pred = X_test[1], Y_test[1], Y_pred[1]
fig, ax = plt.subplots(3, 2)
ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1)
ax[0, 0].set_title("ground truth")
ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1)
ax[0, 1].set_title("unaries only")
ax[1, 0].set_visible(False)
ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1)
ax[1, 1].set_title("latent final")
ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1)
ax[2, 0].set_title("prediction latent")
# Now, use a latent-variabile CRF model with SVM training.
# 5 states per label is enough capacity to encode the 5 digit classes.
latent_pbl = LatentGraphCRF(n_states_per_label=5,
inference_method='unary')
base_ssvm = NSlackSSVM(latent_pbl, C=1, tol=.01,
inactive_threshold=1e-3, batch_size=10)
latent_svm = LatentSSVM(base_ssvm=base_ssvm, latent_iter=2)
latent_svm.fit(X_train_, y_train)
print("Score with binary SVM:")
print("Train: {:2.2f}".format(svm.score(X_train_, y_train)))
print("Test: {:2.2f}".format(svm.score(X_test_, y_test)))
print("Score with latent SVM:")
print("Train: {:2.2f}".format(latent_svm.score(X_train_, y_train)))
print("Test: {:2.2f}".format(latent_svm.score(X_test_, y_test)))
h_pred = np.hstack(latent_svm.predict_latent(X_test_))
print("Latent class counts: %s" % repr(np.bincount(h_pred)))
# plot first few digits from each latent class
plt.figure(figsize=(3, 5))
plt.suptitle("Example digits from each of\nthe ten latent classes.")
n_latent_classes = 10
n_examples = 7
for latent_class in range(n_latent_classes):
examples = X_test[h_pred == latent_class][:n_examples]
for k, example in enumerate(examples):
plt.subplot(n_latent_classes, n_examples,
inference_method='lp')
ssvm = OneSlackSSVM(model=latent_crf, max_iter=200, C=100,
n_jobs=-1, show_loss_every=10, inference_cache=50)
latent_svm = LatentSSVM(ssvm)
# make edges for hidden states:
edges = []
node_indices = np.arange(4 * 4).reshape(4, 4)
for i, (x, y) in enumerate(itertools.product([0, 2], repeat=2)):
for j in range(x, x + 2):
for k in range(y, y + 2):
edges.append([i + 4 * 4, node_indices[j, k]])
G = [np.vstack([make_grid_edges(x), edges]) for x in X]
# Random initialization
H_init = [np.hstack([y.ravel(), np.random.randint(2, 4, size=2 * 2)])
for y in Y]
plot_boxes(H_init, title="Top: Random initial hidden states. Bottom: Ground"
"truth labeling.")
X_ = list(zip(X_flat, G, [2 * 2 for x in X_flat]))
latent_svm.fit(X_, Y_flat, H_init)
print("Training score with latent nodes: %f " % latent_svm.score(X_, Y_flat))
H = latent_svm.predict_latent(X_)
plot_boxes(H, title="Top: Hidden states after training. Bottom: Prediction.")
plt.show()
from pystruct.learners import LatentSSVM, OneSlackSSVM
from pystruct.datasets import generate_crosses
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5)
crf = LatentGridCRF(n_states_per_label=[1, 2])
base_ssvm = OneSlackSSVM(model=crf,
C=10.,
n_jobs=-1,
inference_cache=20,
tol=.1)
clf = LatentSSVM(base_ssvm=base_ssvm)
clf.fit(X_train, Y_train)
print("Score training set: %f" % clf.score(X_train, Y_train))
print("Score test set: %f" % clf.score(X_test, Y_test))
Y_pred = clf.predict(X_test)
x, y, y_pred = X_test[1], Y_test[1], Y_pred[1]
fig, ax = plt.subplots(3, 2)
ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1)
ax[0, 0].set_title("ground truth")
ax[0, 1].matshow(np.argmax(x, axis=-1), vmin=0, vmax=crf.n_labels - 1)
ax[0, 1].set_title("unaries only")
ax[1, 0].set_visible(False)
ax[1, 1].matshow(crf.latent(x, y, clf.w), vmin=0, vmax=crf.n_states - 1)
ax[1, 1].set_title("latent final")
ax[2, 0].matshow(crf.inference(x, clf.w), vmin=0, vmax=crf.n_states - 1)
ax[2, 0].set_title("prediction latent")
from pystruct.models import LatentGridCRF
from pystruct.learners import LatentSSVM, OneSlackSSVM
from pystruct.datasets import generate_crosses
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5,
force_arrays=False)
crf = LatentGridCRF(n_states_per_label=[1, 2])
base_ssvm = OneSlackSSVM(model=crf, C=10., n_jobs=-1, inference_cache=20,
tol=.1)
clf = LatentSSVM(base_ssvm=base_ssvm)
clf.fit(X_train, Y_train)
print("Score training set: %f" % clf.score(X_train, Y_train))
print("Score test set: %f" % clf.score(X_test, Y_test))
Y_pred = clf.predict(X_test)
x, y, y_pred = X_test[1], Y_test[1], Y_pred[1]
fig, ax = plt.subplots(3, 2)
ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1)
ax[0, 0].set_title("ground truth")
ax[0, 1].matshow(np.argmax(x, axis=-1),
vmin=0, vmax=crf.n_labels - 1)
ax[0, 1].set_title("unaries only")
ax[1, 0].set_visible(False)
ax[1, 1].matshow(crf.latent(x, y, clf.w),
vmin=0, vmax=crf.n_states - 1)
ax[1, 1].set_title("latent final")
from pystruct.models import LatentGridCRF
from pystruct.learners import LatentSSVM, OneSlackSSVM
from pystruct.datasets import generate_crosses
X, Y = generate_crosses(n_samples=20, noise=5, n_crosses=1, total_size=8)
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5,
allow_nd=True)
crf = LatentGridCRF(n_states_per_label=[1, 2])
base_ssvm = OneSlackSSVM(model=crf, C=10., n_jobs=-1, inference_cache=20,
tol=.1)
clf = LatentSSVM(base_ssvm=base_ssvm)
clf.fit(X_train, Y_train)
print("loss training set: %f" % clf.score(X_train, Y_train))
print("loss test set: %f" % clf.score(X_test, Y_test))
Y_pred = clf.predict(X_test)
x, y, y_pred = X_test[1], Y_test[1], Y_pred[1]
fig, ax = plt.subplots(3, 2)
ax[0, 0].matshow(y, vmin=0, vmax=crf.n_labels - 1)
ax[0, 0].set_title("ground truth")
ax[0, 1].matshow(np.argmax(x, axis=-1),
vmin=0, vmax=crf.n_labels - 1)
ax[0, 1].set_title("unaries only")
ax[1, 0].set_visible(False)
ax[1, 1].matshow(crf.latent(x, y, clf.w),
vmin=0, vmax=crf.n_states - 1)
ax[1, 1].set_title("latent final")
