def eval_extract_faces(path, check_if_known=True, max_num_proc_imgs=None, central_con=None, local_con=None,
close_connections=True):
path_to_local_db = DBManager.get_local_db_file_path(path)
path_id = DBManager.get_path_id(path)
if path_id is None:
# path not yet known
path_id = DBManager.store_directory_path(path, con=central_con, close_connections=False)
DBManager.store_path_id(path_id, path_to_local_db=path_to_local_db, con=local_con, close_connections=False)
imgs_names_and_date = set(DBManager.get_images_attributes(path_to_local_db=path_to_local_db))
# Note: 'MAX' returns None / (None, ) as a default value
max_img_id = DBManager.get_max_image_id(path_to_local_db=path_to_local_db)
start_img_id = max_img_id + 1
initial_max_embedding_id = DBManager.get_max_embedding_id()
def get_counted_img_loader():
img_loader = load_imgs_from_path(path, recursive=True, output_file_names=True, output_file_paths=True)
if max_num_proc_imgs is not None:
return zip(range(start_img_id, max_num_proc_imgs + 1), img_loader)
return enumerate(img_loader, start=start_img_id)
def store_embedding_row_dicts(con):
print('----- get_embedding_row_dicts -----')
# TODO: Also auto-increment emb_id etc.
embedding_id = initial_max_embedding_id + 1
for img_id, (img_path, img_name, img) in get_counted_img_loader():
print_progress(img_id, 'image')
last_modified = datetime.datetime.fromtimestamp(round(os.stat(img_path).st_mtime))
if check_if_known and (img_name, last_modified) in imgs_names_and_date:
continue
DBManager.store_image(img_id=img_id, rel_file_path=img_name, last_modified=last_modified,
path_to_local_db=path_to_local_db, con=local_con, close_connections=False)
DBManager.store_image_path(img_id=img_id, path_id=path_id, con=central_con, close_connections=False)
face = Models.altered_mtcnn.forward_return_results(img)
if face is None:
log_error(f"no faces found in image '{img_path}'")
continue
embedding_row_dict = {Columns.cluster_id.col_name: 'NULL',
Columns.embedding.col_name: face_to_embedding(face),
Columns.thumbnail.col_name: face,
Columns.image_id.col_name: img_id,
Columns.embedding_id.col_name: embedding_id}
DBManager.store_embedding(embedding_row_dict, con=con, close_connections=False)
embedding_id += 1
DBManager.connection_wrapper(store_embedding_row_dicts, con=central_con, close_connections=close_connections)
def extract_faces(path,
check_if_known=True,
central_con=None,
local_con=None,
close_connections=True):
# TODO: Refactor (extract functions)? + rename
# TODO: Generate Thumbnails differently? (E.g. via Image.thumbnail or sth. like that)
# TODO: Store + update max_img_id and max_embedding_id somewhere rather than (always) get them via DB query?
path_to_local_db = DBManager.get_local_db_file_path(path)
path_id = DBManager.get_path_id(path)
if path_id is None:
# path not yet known
path_id = DBManager.store_directory_path(path,
con=central_con,
close_connections=False)
DBManager.store_path_id(path_id,
path_to_local_db=path_to_local_db,
con=local_con,
close_connections=False)
imgs_rel_paths_and_dates = set(
DBManager.get_images_attributes(path_to_local_db=path_to_local_db))
# Note: 'MAX' returns None / (None, ) as a default value
max_img_id = DBManager.get_max_image_id(path_to_local_db=path_to_local_db)
start_img_id = max_img_id + 1
initial_max_embedding_id = DBManager.get_max_embedding_id()
def get_counted_img_loader():
img_loader = load_imgs_from_path(path,
recursive=True,
output_file_names=True,
output_file_paths=True)
return enumerate(img_loader, start=start_img_id)
def store_embedding_row_dicts(con):
# TODO: Also auto-increment emb_id etc.
max_embedding_id = initial_max_embedding_id
for img_id, (img_abs_path, img_rel_path,
img) in get_counted_img_loader():
# TODO: Implement automatic deletion cascade! (Using among other things on_conflict clause and FKs)
# ---> Done?
# Check if image already stored --> don't process again
# known = (name, last modified) as a pair known for this director
last_modified = datetime.datetime.fromtimestamp(
round(os.stat(img_abs_path).st_mtime))
if check_if_known and (img_rel_path,
last_modified) in imgs_rel_paths_and_dates:
continue
DBManager.store_image(img_id=img_id,
rel_file_path=img_rel_path,
last_modified=last_modified,
path_to_local_db=path_to_local_db,
con=local_con,
close_connections=False)
DBManager.store_image_path(img_id=img_id,
path_id=path_id,
con=central_con,
close_connections=False)
faces = Models.altered_mtcnn.forward_return_results(img)
if not faces:
log_error(f"no faces found in image '{img_abs_path}'")
continue
# TODO: Better way to create these row_dicts?
embeddings_row_dicts = [{
Columns.cluster_id.col_name:
'NULL',
Columns.embedding.col_name:
face_to_embedding(face),
Columns.thumbnail.col_name:
face,
Columns.image_id.col_name:
img_id,
Columns.embedding_id.col_name:
embedding_id
} for embedding_id, face in enumerate(faces,
start=max_embedding_id + 1)]
DBManager.store_embeddings(embeddings_row_dicts,
con=con,
close_connections=False)
max_embedding_id += len(faces)
DBManager.connection_wrapper(store_embedding_row_dicts,
con=central_con,
close_connections=close_connections)
def extract_faces_measure(path,
n,
check_if_known=True,
central_con=None,
local_con=None,
close_connections=True):
path_to_local_db = DBManager.get_local_db_file_path(path)
path_id = DBManager.get_path_id(path)
if path_id is None:
# path not yet known
path_id = DBManager.store_directory_path(path,
con=central_con,
close_connections=False)
DBManager.store_path_id(path_id,
path_to_local_db=path_to_local_db,
con=local_con,
close_connections=False)
imgs_names_and_date = set(
DBManager.get_images_attributes(path_to_local_db=path_to_local_db))
# Note: 'MAX' returns None / (None, ) as a default value
max_img_id = DBManager.get_max_image_id(
path_to_local_db=path_to_local_db)
start_img_id = max_img_id + 1
initial_max_embedding_id = DBManager.get_max_embedding_id()
def get_counted_img_loader():
img_loader = load_imgs_from_path(path,
recursive=True,
output_file_names=True,
output_file_paths=True)
nums = range(start_img_id, start_img_id + n)
return zip(nums, img_loader)
def store_embedding_row_dicts(con):
max_embedding_id = initial_max_embedding_id
for img_id, (img_path, img_name, img) in get_counted_img_loader():
# Check if image already stored --> don't process again
# known = (name, last modified) as a pair known for this director
last_modified = datetime.datetime.fromtimestamp(
round(os.stat(img_path).st_mtime))
if check_if_known and (img_name,
last_modified) in imgs_names_and_date:
continue
DBManager.store_image(img_id=img_id,
rel_file_path=img_name,
last_modified=last_modified,
path_to_local_db=path_to_local_db,
con=local_con,
close_connections=False)
DBManager.store_image_path(img_id=img_id,
path_id=path_id,
con=central_con,
close_connections=False)
faces = Models.altered_mtcnn.forward_return_results(img)
if not faces:
log_error(f"no faces found in image '{img_path}'")
continue
embeddings_row_dicts = [{
Columns.cluster_id.col_name:
'NULL',
Columns.embedding.col_name:
face_to_embedding(face),
Columns.thumbnail.col_name:
face,
Columns.image_id.col_name:
img_id,
Columns.embedding_id.col_name:
embedding_id
} for embedding_id, face in enumerate(
faces, start=max_embedding_id + 1)]
DBManager.store_embeddings(embeddings_row_dicts,
con=con,
close_connections=False)
max_embedding_id += len(faces)
DBManager.connection_wrapper(store_embedding_row_dicts,
con=central_con,
close_connections=close_connections)