def test_split_classes(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/same_faces')
data1, data2 = data.split_classes()
self.assertEqual(data.classes_length,
data1.classes_length + data2.classes_length)
def test_get_embeddings(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/same_faces')
X, y = data.get_embeddings()
self.assertTrue(isinstance(X, np.ndarray))
self.assertEqual(X.shape[0], y.shape[0])
def test_save(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/newdata')
data.save('tests/fixtures/faces/newdata/newdata.pkl')
self.assertTrue(
os.path.exists('tests/fixtures/faces/newdata/newdata.pkl'))
def test_split_instances_of_classes(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/newdata')
data1, data2 = data.split_instances_of_classes()
self.assertEqual(data1.classes_length, data2.classes_length)
for cls, images in data.items():
self.assertEqual(data[cls].length,
data1[cls].length + data2[cls].length)
def test_load(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/newdata')
data.save('tests/fixtures/faces/newdata/newdata.pkl')
new_data = FaceDataset.load('tests/fixtures/faces/newdata/newdata.pkl')
self.assertEqual(data.classes_length, new_data.classes_length)
for cls in data.get_classes():
self.assertTrue(cls in new_data.get_classes())
self.assertEqual(data[cls].length, new_data[cls].length)
def setUp(self):
data1 = FaceDataset()
data1.read_dataset('tests/fixtures/faces/same_faces')
data2 = FaceDataset()
data2.read_dataset('tests/fixtures/faces/newdata')
data1.append(data2)
data1.save(os.path.join('tests/fixtures/faces/testset.pkl'))
def test_unknown_dataset(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/same_faces')
unk_data = data.create_unknown_class()
self.assertEqual(unk_data.classes_length, 1)
self.assertTrue(Config.UNKNOWN_TAG in unk_data.dataset)
s = 0
for _, images in unk_data.items():
s += images.length
self.assertEqual(unk_data[Config.UNKNOWN_TAG].length, s)
def test_read_dataset(self):
data = FaceDataset()
data.read_dataset('tests/fixtures/faces/same_faces')
self.assertEqual(data.classes_length, 150)
self.assertEqual(data['George_W_Bush'].length, 26)
parser.add_argument("-o",
"--output",
dest="output",
help="Path to the output folder.")
parser.add_argument("-n",
"--n_clusters",
type=int,
help="Number of clusters for hierarchical clustering.")
parser.add_argument("--analyze",
action='store_true',
help="Print clustering details.")
args = parser.parse_args()
logger.info(sys.argv)
all_data = FaceDataset()
all_data.read_dataset(args.input)
clustering_algo = get_dbscan() if not hasattr(
args, 'n_clusters') or not args.n_clusters else get_hierarchical(
args.n_clusters)
time_start = time.time()
labels = clustering(all_data, clustering_algo, args.analyze)
time_end = time.time()
logger.info('The clustering took {:.3f} ms'.format(
(time_start - time_end) * 1000.0))
write_clusters(args.output, all_data, labels)