def test_image_stats(self):
expected_mean = [100, 50, 150]
expected_std = [20, 50, 10]
dataset = Dataset.from_iterable([
DatasetItem(id=i, image=np.random.normal(
expected_mean, expected_std, size=(h, w, 3))
)
for i, (w, h) in enumerate([
(3000, 100), (800, 600), (400, 200), (700, 300)
])
])
dataset.put(dataset.get('1'), id='5', subset='train')
actual = compute_image_statistics(dataset)
self.assertEqual(actual['dataset'], {
'images count': 5,
'unique images count': 4,
'repeated images count': 1,
'repeated images': [[('1', 'default'), ('5', 'train')]],
})
self.assertEqual(actual['subsets']['default']['images count'], 4)
self.assertEqual(actual['subsets']['train']['images count'], 1)
actual_mean = actual['subsets']['default']['image mean'][::-1]
actual_std = actual['subsets']['default']['image std'][::-1]
for em, am in zip(expected_mean, actual_mean):
self.assertAlmostEqual(em, am, places=0)
for estd, astd in zip(expected_std, actual_std):
self.assertAlmostEqual(estd, astd, places=0)
def stats_command(args):
project = load_project(args.project_dir)
dataset = project.make_dataset()
stats = {}
stats.update(compute_image_statistics(dataset))
stats.update(compute_ann_statistics(dataset))
dst_file = generate_next_file_name('statistics', ext='.json')
log.info("Writing project statistics to '%s'" % dst_file)
with open(dst_file, 'w') as f:
json.dump(stats, f, indent=4, sort_keys=True)
def stats_command(args):
project = None
try:
project = scope_add(load_project(args.project_dir))
except ProjectNotFoundError:
if args.project_dir:
raise
dataset, target_project = parse_full_revpath(args.target, project)
if target_project:
scope_add(target_project)
if args.subset:
dataset = dataset.get_subset(args.subset)
stats = {}
if args.image_stats:
stats.update(compute_image_statistics(dataset))
if args.ann_stats:
stats.update(compute_ann_statistics(dataset))
dst_file = generate_next_file_name('statistics', ext='.json')
log.info("Writing project statistics to '%s'" % dst_file)
dump_json_file(dst_file, stats, indent=True)