def test_edge_type_graph_crf_energy_lp_integral():
# same test as for graph crf above, using single edge type
crf = EdgeTypeGraphCRF(n_states=2, inference_method="lp", n_edge_types=1)
inf_res, energy_lp = crf.inference((x_1, [g_1]), w_sym, relaxed=True, return_energy=True)
# integral solution
assert_array_almost_equal(np.max(inf_res[0], axis=-1), 1)
y = np.argmax(inf_res[0], axis=-1)
# energy and psi check out
assert_almost_equal(energy_lp, -np.dot(w_sym, crf.psi((x_1, [g_1]), y)))
def test_edge_type_graph_crf_energy_lp_relaxed():
# same test as for graph crf above, using single edge type
crf = EdgeTypeGraphCRF(n_states=2, inference_method="lp", n_edge_types=1)
for i in xrange(10):
w_ = np.random.uniform(size=w_sym.shape)
inf_res, energy_lp = crf.inference((x_1, [g_1]), w_, relaxed=True, return_energy=True)
assert_almost_equal(energy_lp, -np.dot(w_, crf.psi((x_1, [g_1]), inf_res)))
# now with fractional solution
x = np.array([[0, 0], [0, 0], [0, 0]])
inf_res, energy_lp = crf.inference((x, [g_1]), w_sym, relaxed=True, return_energy=True)
assert_almost_equal(energy_lp, -np.dot(w_sym, crf.psi((x, [g_1]), inf_res)))
def test_edge_type_graph_crf():
# create two samples with different graphs
# two states only, pairwise smoothing
# all edges are of the first type. should do the same as GraphCRF
# if we make w symmetric
for inference_method in get_installed(['qpbo', 'lp', 'ad3', 'dai', 'ogm']):
crf = EdgeTypeGraphCRF(n_states=2, inference_method=inference_method,
n_edge_types=1)
assert_array_equal(crf.inference((x_1, [g_1]), w_sym), y_1)
assert_array_equal(crf.inference((x_2, [g_2]), w_sym), y_2)
# same, only with two edge types and no edges of second type
w_sym_ = np.array([1, 0, # unary
0, 1,
.22, 0, # pairwise
0, .22,
2, -1, # second edge type, doesn't exist
-1, 3])
for inference_method in get_installed(['qpbo', 'lp', 'ad3', 'dai', 'ogm']):
crf = EdgeTypeGraphCRF(n_states=2, inference_method=inference_method,
n_edge_types=2)
assert_array_equal(crf.inference((x_1,
[g_1, np.zeros((0, 2),
dtype=np.int)]),
w_sym_), y_1)
assert_array_equal(crf.inference((x_2, [g_2, np.zeros((0, 2),
dtype=np.int)]),
w_sym_), y_2)
print crf.get_pairwise_potentials((x_2, [g_2, np.zeros((0, 2),
dtype=np.int)]),
w_sym_)
def test_edge_type_graph_crf():
# create two samples with different graphs
# two states only, pairwise smoothing
# all edges are of the first type. should do the same as GraphCRF
# if we make w symmetric
for inference_method in ["qpbo", "lp", "ad3", "dai"]:
crf = EdgeTypeGraphCRF(n_states=2, inference_method=inference_method, n_edge_types=1)
assert_array_equal(crf.inference((x_1, [g_1]), w_sym), y_1)
assert_array_equal(crf.inference((x_2, [g_2]), w_sym), y_2)
# same, only with two edge types and no edges of second type
w_sym_ = np.array(
[1, 0, 0, 1, 0.22, 0, 0, 0.22, 2, -1, -1, 3] # unary # pairwise # second edge type, doesn't exist
)
for inference_method in ["qpbo", "lp", "ad3", "dai"]:
crf = EdgeTypeGraphCRF(n_states=2, inference_method=inference_method, n_edge_types=2)
assert_array_equal(crf.inference((x_1, [g_1, np.zeros((0, 2), dtype=np.int)]), w_sym_), y_1)
assert_array_equal(crf.inference((x_2, [g_2, np.zeros((0, 2), dtype=np.int)]), w_sym_), y_2)
def loss_augmented_inference(self, x, y, w, relaxed=False,
return_energy=False):
y_hat = EdgeTypeGraphCRF.loss_augmented_inference(
self, x, y.ravel(), w, relaxed=relaxed,
return_energy=return_energy)
return self._reshape_y(y_hat, x[0].shape[0], return_energy)
def inference(self, x, w, relaxed=False, return_energy=False):
y = EdgeTypeGraphCRF.inference(self, x, w, relaxed=relaxed,
return_energy=return_energy)
return self._reshape_y(y, x[0].shape[0], return_energy)
