def generate_vec():
#getting dorsal vectors and class
dorsal_paths = filter_images('dorsal')
_, dorsal_vectors = get_all_vectors(model, f={'path': {'$in': dorsal_paths}})
#getting palmar vectors and class
palmar_paths = filter_images('palmar')
_, palmar_vectors = get_all_vectors(model, f={'path': {'$in': palmar_paths}})
#getting test vectors and their path
test_data_paths, test_data = get_all_vectors(model, f={}, unlabelled_db=True)
# Return the calculated values
return dorsal_vectors, palmar_vectors, test_data, test_data_paths
def get_data_matrix(cls,
feature,
label=None,
unlabelled=False,
ignore_metadata=False):
min_max_scaler = MinMaxScaler()
f = {}
if label:
label_images = utils.filter_images(label)
f = {'path': {'$in': label_images}}
# Build and scale feature matrix
images, feature_space = utils.get_all_vectors(feature,
f=f,
unlabelled_db=unlabelled)
feature_space = min_max_scaler.fit_transform(feature_space)
# Not including metadata boosts accuracy of Set 2
# Including metadata boosts accuracy of Set 1
if ignore_metadata:
meta = utils.get_metadata(unlabelled_db=unlabelled)
# Mapping between image file path name and the metadata
meta = {m['path']: m for m in meta}
return images, meta, feature_space
# Build and scale metadata matrix
meta, metadata_space = cls.get_metadata_space(images,
unlabelled_db=unlabelled)
metadata_space = min_max_scaler.fit_transform(metadata_space)
# Column stack them
data_matrix = np.c_[feature_space, metadata_space]
return images, meta, data_matrix
def build_unlabelled(model):
#DORSAL TEST_DATA
dorsal_paths = filter_images('dorsal', unlabelled_db=True)
_, u_dorsal_vectors = get_all_vectors(model, f={'path': {'$in': dorsal_paths}}, unlabelled_db=True)
dorsal_class = np.array([-1] * len(u_dorsal_vectors))
#PALMAR TEST DATA
palmar_paths = filter_images('palmar', unlabelled_db=True)
_, u_palmar_vectors = get_all_vectors(model, f={'path': {'$in': palmar_paths}}, unlabelled_db=True)
palmar_class = np.array([1] * len(u_palmar_vectors))
#STACK ALL TEST DATA AND LABELS
test_data = np.vstack((u_dorsal_vectors, u_palmar_vectors))
test_labels = np.concatenate((dorsal_class,palmar_class))
return test_data, test_labels, np.concatenate((dorsal_paths,palmar_paths))
def build_labelled(model):
# DORSAL TRAIN DATA
dorsal_paths = filter_images('dorsal')
_, dorsal_vectors = get_all_vectors(model, f={'path':{'$in': dorsal_paths}})
dorsal_class = np.array([-1] * len(dorsal_vectors))
#PALMAR TRAIN DATA
_, palmar_vectors = get_all_vectors(model, f={'path': {'$nin': dorsal_paths}})
palmar_class = np.array([1] * len(palmar_vectors))
#TRAIN DATA STACKED AND CLASSES
train_data = np.vstack((dorsal_vectors, palmar_vectors))
train_class = np.concatenate((dorsal_class, palmar_class))
return train_data, train_class
palmar_kmeans.centroids,
return_min=True)
return 'dorsal' if dorsal_dist <= palmar_dist else 'palmar'
if __name__ == "__main__":
parser = prepare_parser()
args = parser.parse_args()
n_clusters = args.n_clusters
#get the absolute data path and models whose features to concatenate
data_path = Path(settings.path_for(settings.DATA_PATH))
model = settings.TASK2_CONFIG.MODEL
#Fetch training data for dorsal and palmer images from LABELLED DB
dorsal_paths = filter_images('dorsal')
dorsal_paths, dorsal_vectors = get_all_vectors(
model, f={'path': {
'$in': dorsal_paths
}})
palmar_paths, palmar_vectors = get_all_vectors(
model, f={'path': {
'$nin': dorsal_paths
}})
#Fetch test data from UNLABELLED DB
test_data_paths, test_data = get_all_vectors(model, unlabelled_db=True)
#Get centroids and centroid_labels for dorsal and palmar vectors
print("Clustering dorsal vectors")
dorsal_kmeans = Kmeans(dorsal_vectors, n_clusters)
print("converting annotations ...")
# Convert annotations
if args.task == "bbox":
oi["annotations"] = utils.convert_instance_annotations(
original_annotations,
oi["images"],
oi["categories"],
start_index=0,
classes=args.classes,
)
elif args.task == "panoptic":
oi["annotations"] = utils.convert_segmentation_annotations(
original_segmentations,
oi["images"],
oi["categories"],
original_mask_dir,
segmentation_out_dir,
start_index=0,
)
oi["images"] = utils.filter_images(oi["images"], oi["annotations"])
# Write annotations into .json file
filename = os.path.join(
base_dir,
"annotations/",
"openimages_{}_{}_{}.json".format(args.version, subset, args.task),
)
print("writing output to {}".format(filename))
json.dump(oi, open(filename, "w"))
print("Done")
{'id': 2, 'name': 'Attribution-NonCommercial License', 'url': 'http://creativecommons.org/licenses/by-nc/2.0/'},
{'id': 3, 'name': 'Attribution-NonCommercial-NoDerivs License', 'url': 'http://creativecommons.org/licenses/by-nc-nd/2.0/'},
{'id': 4, 'name': 'Attribution License', 'url': 'http://creativecommons.org/licenses/by/2.0/'},
{'id': 5, 'name': 'Attribution-ShareAlike License', 'url': 'http://creativecommons.org/licenses/by-sa/2.0/'},
{'id': 6, 'name': 'Attribution-NoDerivs License', 'url': 'http://creativecommons.org/licenses/by-nd/2.0/'},
{'id': 7, 'name': 'No known copyright restrictions', 'url': 'http://flickr.com/commons/usage/'},
{'id': 8, 'name': 'United States Government Work', 'url': 'http://www.usa.gov/copyright.shtml'}]
# Convert category information
print('converting category info')
oi['categories'] = utils.convert_category_annotations(original_category_info)
# Convert image mnetadata
print('converting image info ...')
image_dir = os.path.join(base_dir, subset)
oi['images'] = utils.convert_image_annotations(original_image_metadata, original_image_annotations, original_image_sizes, image_dir, oi['categories'], oi['licenses'])
# Convert instance annotations
print('converting annotations ...')
# Convert annotations
if args.task == 'bbox':
oi['annotations'] = utils.convert_instance_annotations(original_annotations, oi['images'], oi['categories'], start_index=0)
elif args.task == 'panoptic':
oi['annotations'] = utils.convert_segmentation_annotations(original_segmentations, oi['images'], oi['categories'], original_mask_dir, segmentation_out_dir, start_index=0)
oi['images'] = utils.filter_images(oi['images'], oi['annotations'])
# Write annotations into .json file
filename = os.path.join(base_dir, 'annotations/', 'openimages_{}_{}_{}.json'.format(args.version, subset, args.task))
print('writing output to {}'.format(filename))
json.dump(oi, open(filename, "w"))
print('Done')