def yolo2bb(annotations_path, images_dir, file_obj_names, bb_type=BBType.GROUND_TRUTH):
ret = []
if not os.path.isfile(file_obj_names):
print(f'Warning: File with names of classes {file_obj_names} not found.')
return ret
# Load classes
all_classes = []
with open(file_obj_names, "r") as f:
all_classes = [line.replace('\n', '') for line in f]
# Get annotation files in the path
annotation_files = _get_annotation_files(annotations_path)
# Loop through each file
for file_path in annotation_files:
if not validations.is_yolo_format(file_path, bb_types=[bb_type]):
continue
img_name = os.path.basename(file_path)
img_file = general_utils.find_file(images_dir, img_name, match_extension=False)
img_resolution = general_utils.get_image_resolution(img_file)
if img_resolution is None:
print(f'Warning: It was not possible to find the resolution of image {img_name}')
continue
img_size = (img_resolution['width'], img_resolution['height'])
# Loop through lines
with open(file_path, "r") as f:
for line in f:
splitted_line = line.split(' ')
class_id = splitted_line[0]
if not general_utils.is_str_int(class_id):
print(
f'Warning: Class id represented in the {file_path} is not a valid integer.')
return []
class_id = int(class_id)
if class_id not in range(len(all_classes)):
print(
f'Warning: Class id represented in the {file_path} is not in the range of classes specified in the file {file_obj_names}.'
)
return []
if bb_type == BBType.GROUND_TRUTH:
confidence = None
x1 = float(splitted_line[1])
y1 = float(splitted_line[2])
w = float(splitted_line[3])
h = float(splitted_line[4])
elif bb_type == BBType.DETECTED:
confidence = float(splitted_line[1])
x1 = float(splitted_line[2])
y1 = float(splitted_line[3])
w = float(splitted_line[4])
h = float(splitted_line[5])
bb = BoundingBox(image_name=general_utils.get_file_name_only(img_file),
class_id=all_classes[class_id],
coordinates=(x1, y1, w, h),
img_size=img_size,
confidence=confidence,
type_coordinates=CoordinatesType.RELATIVE,
bb_type=bb_type,
format=BBFormat.XYWH)
ret.append(bb)
return ret
def openimage2bb(annotations_path, images_dir, bb_type=BBType.GROUND_TRUTH):
ret = []
# Get annotation files in the path
annotation_files = _get_annotation_files(annotations_path)
# Loop through each file
for file_path in annotation_files:
if not validations.is_openimage_format(file_path):
continue
images_shapes = {}
# Open csv
csv = pd.read_csv(file_path, sep=',')
for i, row in csv.iterrows():
# Get image resolution if it was not loaded yet
if row['ImageID'] not in images_shapes:
img_name = row['ImageID']
image_file = general_utils.find_file(images_dir, img_name)
images_shapes[image_file] = general_utils.get_image_resolution(
image_file)
if images_shapes[image_file] is None:
print(
f'Warning: It was not possible to find the resolution of image {img_name}'
)
continue
# Three is no bounding box for the given image
if pd.isna(row['LabelName']) or pd.isna(row['XMin']) or pd.isna(
row['XMax']) or pd.isna(row['YMin']) or pd.isna(
row['YMax']):
continue
# images_shapes[image_file] = general_utils.get_image_resolution(image_file)
img_size = (images_shapes[image_file]['width'],
images_shapes[image_file]['height'])
x1, x2, y1, y2 = (row['XMin'], row['XMax'], row['YMin'],
row['YMax'])
x1 = x1.replace(',', '.') if isinstance(x1, str) else x1
x2 = x2.replace(',', '.') if isinstance(x2, str) else x2
y1 = y1.replace(',', '.') if isinstance(y1, str) else y1
y2 = y2.replace(',', '.') if isinstance(y2, str) else y2
x1, x2, y1, y2 = float(x1), float(x2), float(y1), float(y2)
confidence = None if pd.isna(row['Confidence']) else float(
row['Confidence'])
if bb_type == BBType.DETECTED and confidence is None:
print(
f'Warning: Confidence value found in the CSV file for the image {img_name}'
)
return ret
bb = BoundingBox(image_name=general_utils.get_file_name_only(
row['ImageID']),
class_id=row['LabelName'],
coordinates=(x1, y1, x2, y2),
img_size=img_size,
confidence=confidence,
type_coordinates=CoordinatesType.RELATIVE,
bb_type=bb_type,
format=BBFormat.XYX2Y2)
ret.append(bb)
return ret
def text2bb(annotations_path,
bb_type=BBType.GROUND_TRUTH,
bb_format=BBFormat.XYWH,
type_coordinates=CoordinatesType.ABSOLUTE,
img_dir=None):
ret = []
# Get annotation files in the path
annotation_files = _get_annotation_files(annotations_path)
for file_path in annotation_files:
if type_coordinates == CoordinatesType.ABSOLUTE:
if bb_type == BBType.GROUND_TRUTH and not validations.is_absolute_text_format(
file_path, num_blocks=[5], blocks_abs_values=[4]):
continue
if bb_type == BBType.DETECTED and not validations.is_absolute_text_format(
file_path, num_blocks=[6], blocks_abs_values=[4]):
continue
elif type_coordinates == CoordinatesType.RELATIVE:
if bb_type == BBType.GROUND_TRUTH and not validations.is_relative_text_format(
file_path, num_blocks=[5], blocks_rel_values=[4]):
continue
if bb_type == BBType.DETECTED and not validations.is_relative_text_format(
file_path, num_blocks=[6], blocks_rel_values=[4]):
continue
# Loop through lines
with open(file_path, "r") as f:
img_filename = os.path.basename(file_path)
img_filename = os.path.splitext(img_filename)[0]
img_size = None
# If coordinates are relative, image size must be obtained in the img_dir
if type_coordinates == CoordinatesType.RELATIVE:
img_path = general_utils.find_file(img_dir,
img_filename,
match_extension=False)
if img_path is None or os.path.isfile(img_path) is False:
print(
f'Warning: Image not found in the directory {img_path}. It is required to get its dimensions'
)
return ret
resolution = general_utils.get_image_resolution(img_path)
img_size = (resolution['width'], resolution['height'])
for line in f:
if line.replace(' ', '') == '\n':
continue
splitted_line = line.split(' ')
class_id = splitted_line[0]
if bb_type == BBType.GROUND_TRUTH:
confidence = None
x1 = float(splitted_line[1])
y1 = float(splitted_line[2])
w = float(splitted_line[3])
h = float(splitted_line[4])
elif bb_type == BBType.DETECTED:
confidence = float(splitted_line[1])
x1 = float(splitted_line[2])
y1 = float(splitted_line[3])
w = float(splitted_line[4])
h = float(splitted_line[5])
bb = BoundingBox(image_name=img_filename,
class_id=class_id,
coordinates=(x1, y1, w, h),
img_size=img_size,
confidence=confidence,
type_coordinates=type_coordinates,
bb_type=bb_type,
format=bb_format)
# If the format is correct, x,y,w,h,x2,y2 must be positive
x, y, w, h = bb.get_absolute_bounding_box(format=BBFormat.XYWH)
_, _, x2, y2 = bb.get_absolute_bounding_box(
format=BBFormat.XYX2Y2)
if x < 0 or y < 0 or w < 0 or h < 0 or x2 < 0 or y2 < 0:
continue
ret.append(bb)
return ret