def test_celeba_embedding(self):
PATHS_JSON = os.getenv('PATHS_JSON', abspath(join(__file__, '..', '..', 'data', 'paths_celeba.json')))
EMBEDDING_JSON = os.getenv('EMBEDDING_JSON', abspath(join(__file__, '..', '..', 'data', 'embeddings_celeba.json')))
INDEX_FILENAME = os.getenv('INDEX_FILENAME', os.path.abspath(os.path.join(__file__, '..', '..', 'data', 'index_celeba.ann')))
NSW_INDEX_FILENAME = os.getenv('NSW_INDEX_FILENAME', os.path.abspath(os.path.join(__file__, '..', '..', 'data', 'index_celeba_nsw')))
TEST_CASES_FILENAME = os.getenv('TEST_CASES_FILENAME',
os.path.abspath(os.path.join(__file__, '..', '..', 'data', 'index_celeba_test_cases.json')))
with open(PATHS_JSON, 'r') as fp:
print('Loading paths')
paths = np.array(json.load(fp))
with open(EMBEDDING_JSON, 'r') as fp:
print('Loading embeddings')
embeddings = json.load(fp)
with open(TEST_CASES_FILENAME, 'r') as fp:
print('Loading test_cases')
test_cases = json.load(fp)
annoy = AnnoyIndex(len(embeddings[0]))
annoy_index = annoy.load(INDEX_FILENAME)
print('building nsw index')
nsw_index = PyNSW('l2')
print('Creating nodes')
nodes = [create_node(path, vector) for path, vector in zip(paths, embeddings)]
print('Inserting nodes')
for node in tqdm(nodes):
nsw_index.nn_insert(node, 5, 1000)
n, k_annoy, k_nsw = 0, 0, 0
print('Calculating accuracy on CelebA')
for tk in test_cases:
vector = embeddings[int(tk['embedding_index'])]
closest_paths_real = tk['closest_paths_real']
closest_paths_annoy = paths[annoy.get_nns_by_vector(vector, 10, 1000)]
closest_paths_nsw = [n[1] for n in nsw_index.nn_search(create_node('kek', vector), 5, 10)]
assert len(closest_paths_real) == 10
assert len(closest_paths_annoy) == 10
assert len(closest_paths_nsw) == 10
n += 10
k_annoy += len(set(closest_paths_annoy).intersection(closest_paths_real))
k_nsw += len(set(closest_paths_nsw).intersection(closest_paths_real))
print('Annoy accuracy on CelebA embeddings: {:.3f}%'.format(100.0 * k_annoy / n))
print('NSW accuracy on CelebA embeddings: {:.3f}%'.format(100.0 * k_nsw / n))
class PyDistanceTests(unittest.TestCase):
node1 = create_node('kek', [1, 2, 3])
node2 = create_node('lol', [1, 2, 5])
def test_l1(self):
self.assertEqual(2, PyDistance_l1()(self.node1, self.node2))
def test_l2(self):
self.assertEqual(2, PyDistance_l2()(self.node1, self.node2))
def get_closest_vector():
content = request.get_json(silent=True)
vector = content['vector']
closest_celeb_filename = index.nn_search(create_node('1', vector), 1, 1)[0][1]
response = {'closest_celeb_filename': closest_celeb_filename}
response_pickled = jsonpickle.encode(response)
return Response(response=response_pickled, status=200, mimetype="application/json")
class PyNSWTests(unittest.TestCase):
nodes = [create_node(str(i), [i**2]) for i in range(NUM_NODES)]
def _create_index(self, num_neighbors=(NUM_NODES - 1), num_iters=1):
nsw = PyNSW('l2')
# connect each node to `num_neighbors` other nodes
for node in self.nodes:
nsw.nn_insert(node, num_iters, num_neighbors)
return nsw
def test_search_full(self):
nsw = self._create_index()
# check that the node is closest to itself
for node in self.nodes:
neighbors = nsw.nn_search(node, 1, 1)
self.assertEqual(node.file_path, neighbors[0][1])
def test_search_half(self):
nsw = self._create_index(num_neighbors=(NUM_NODES / 2))
# count top3 accuracy depending on number of iterations
NUM_ITERS = 3
count = np.zeros(NUM_ITERS)
for num_iter in range(1, NUM_ITERS + 1):
accuracy = 0.0
for node in self.nodes:
neighbors = nsw.nn_search(node, num_iter, 3)
accuracy += (node.file_path in map(itemgetter(1), neighbors))
count[num_iter - 1] = accuracy / NUM_NODES
self.assertTrue(np.all(count >= 0.8))
def test_search_quarter(self):
nsw = self._create_index(num_neighbors=(NUM_NODES / 4))
# count top3 accuracy depending on number of iterations
NUM_ITERS = 3
count = np.zeros(NUM_ITERS)
for num_iter in range(1, NUM_ITERS + 1):
accuracy = 0.0
for node in self.nodes:
neighbors = nsw.nn_search(node, num_iter, 3)
accuracy += (node.file_path in map(itemgetter(1), neighbors))
count[num_iter - 1] = accuracy / NUM_NODES
self.assertTrue(np.all(count >= np.array([0.5, 0.7, 0.9])))
def create_index(index_path):
index = PyNSW('l2')
if os.path.exists(index_path):
index.load(index_path)
else:
with open(PATHS_JSON, 'r') as fp:
print('Loading paths')
paths = json.load(fp)
with open(EMBEDDING_JSON, 'r') as fp:
print('Loading embeddings')
embeddings = json.load(fp)
print('Creating nodes')
nodes = [create_node(path, vector) for path, vector in zip(paths, embeddings)]
print('Inserting nodes')
for idx, node in enumerate(nodes):
if idx % 500 == 0:
print('{} nodes inserted'.format(idx))
index.nn_insert(node, 3, 1000)
index.save(index_path)
def test_init_list(self):
node = create_node('kek', [1, 2, 3])
self.assertEqual([1., 2., 3.], node.coord)
self.assertEqual('kek', node.file_path)
def test_set_new_values(self):
node = create_node('kek', [1, 2, 3])
new_file_path = 'lol'
node.file_path = new_file_path
self.assertEqual(new_file_path, node.file_path)
def test_init_numpy(self):
node = create_node('kek', np.array([1, 2, 3]))
self.assertEqual([1., 2., 3.], node.coord)
self.assertEqual('kek', node.file_path)
from tqdm import tqdm
from python.index import create_node, PyNSW
PATHS_JSON = getenv('PATHS_JSON',
abspath(join(__file__, '..', '..', 'data', 'paths.json')))
EMBEDDING_JSON = getenv(
'EMBEDDING_JSON',
abspath(join(__file__, '..', '..', 'data', 'embeddings.json')))
if __name__ == '__main__':
with open(PATHS_JSON) as fp:
paths = json.load(fp)
with open(EMBEDDING_JSON) as fp:
embeddings = json.load(fp)
nodes = [
create_node(path, vector) for path, vector in zip(paths, embeddings)
]
nsw = PyNSW('l2')
for node in tqdm(nodes):
nsw.nn_insert(node, 1, 100)
random_vector = embeddings[100]
print(paths[100])
print(random_vector)
neighbors = nsw.nn_search(create_node('kek', random_vector), 5, 3)
print(neighbors)
from python.index import create_node, PyNSW
from tqdm import tqdm
NSW_INDEX_FILENAME = os.getenv(
'NSW_INDEX_FILENAME',
os.path.abspath(
os.path.join(__file__, '..', '..', 'data', 'index_celeba_nsw')))
PATHS_JSON = os.getenv(
'PATHS_JSON',
os.path.abspath(
os.path.join(__file__, '..', '..', 'data', 'paths_celeba.json')))
EMBEDDING_JSON = os.getenv(
'EMBEDDING_JSON',
os.path.abspath(
os.path.join(__file__, '..', '..', 'data', 'embeddings_celeba.json')))
index = PyNSW('l2')
with open(PATHS_JSON, 'r') as fp:
print('Loading paths')
paths = json.load(fp)
with open(EMBEDDING_JSON, 'r') as fp:
print('Loading embeddings')
embeddings = json.load(fp)
print('Creating nodes')
nodes = [create_node(path, vector) for path, vector in zip(paths, embeddings)]
print('Inserting nodes')
for node in tqdm(nodes):
index.nn_insert(node, 3, 10)
index.save(NSW_INDEX_FILENAME)
def setUpClass(cls):
cls.nodes = [
create_node(str('node_{}'.format(i)), [i**2])
for i in range(NUM_NODES)
]