def test_added_descriptor_table_caching(self):
cache_elem = DataMemoryElement(readonly=False)
descrs = [random_descriptor() for _ in range(3)]
expected_table = dict((r.uuid(), r) for r in descrs)
i = MemoryDescriptorSet(cache_elem)
self.assertTrue(cache_elem.is_empty())
# Should add descriptors to table, caching to writable element.
i.add_many_descriptors(descrs)
self.assertFalse(cache_elem.is_empty())
self.assertEqual(pickle.loads(i.cache_element.get_bytes()),
expected_table)
# Changing the internal table (remove, add) it should reflect in
# cache
new_d = random_descriptor()
expected_table[new_d.uuid()] = new_d
i.add_descriptor(new_d)
self.assertEqual(pickle.loads(i.cache_element.get_bytes()),
expected_table)
rm_d = list(expected_table.values())[0]
del expected_table[rm_d.uuid()]
i.remove_descriptor(rm_d.uuid())
self.assertEqual(pickle.loads(i.cache_element.get_bytes()),
expected_table)
def test_add_descriptor(self):
index = MemoryDescriptorSet()
d1 = random_descriptor()
index.add_descriptor(d1)
self.assertEqual(index._table[d1.uuid()], d1)
d2 = random_descriptor()
index.add_descriptor(d2)
self.assertEqual(index._table[d2.uuid()], d2)
def test_count(self):
index = MemoryDescriptorSet()
self.assertEqual(index.count(), 0)
d1 = random_descriptor()
index.add_descriptor(d1)
self.assertEqual(index.count(), 1)
d2, d3, d4 = (random_descriptor(), random_descriptor(),
random_descriptor())
index.add_many_descriptors([d2, d3, d4])
self.assertEqual(index.count(), 4)
d5 = random_descriptor()
index.add_descriptor(d5)
self.assertEqual(index.count(), 5)
def test_clustering_equal_descriptors(self):
# Test that clusters of descriptor of size n-features are correctly
# clustered together.
print("Creating dummy descriptors")
n_features = 8
n_descriptors = 20
desr_set = MemoryDescriptorSet()
c = 0
for i in range(n_features):
v = numpy.ndarray((8, ))
v[...] = 0
v[i] = 1
for j in range(n_descriptors):
d = DescriptorMemoryElement('test', c)
d.set_vector(v)
desr_set.add_descriptor(d)
c += 1
print("Creating test MBKM")
mbkm = MiniBatchKMeans(n_features,
batch_size=12,
verbose=True,
compute_labels=False,
random_state=0)
# Initial fit with half of desr_set
d_classes = mb_kmeans_build_apply(desr_set, mbkm, n_descriptors)
# There should be 20 descriptors per class
for c in d_classes:
self.assertEqual(
len(d_classes[c]), n_descriptors,
"Cluster %s did not have expected number of descriptors "
"(%d != %d)" % (c, n_descriptors, len(d_classes[c])))
# Each descriptor in each cluster should be equal to the other
# descriptors in that cluster
uuids = list(d_classes[c])
v = desr_set[uuids[0]].vector()
for uuid in uuids[1:]:
v2 = desr_set[uuid].vector()
numpy.testing.assert_array_equal(
v, v2, "vector in cluster %d did not "
"match other vectors "
"(%s != %s)" % (c, v, v2))