def imagenet2bb(annotations_path):
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_imagenet_format(file_path):
continue
# Open XML
img_name = ET.parse(file_path).find('filename').text
img_name = general_utils.get_file_name_only(img_name)
img_width = int(ET.parse(file_path).find('size/width').text)
img_height = int(ET.parse(file_path).find('size/height').text)
img_size = (img_width, img_height)
# Loop through the detections
for box_info in ET.parse(file_path).iter('object'):
obj_class = box_info.find('name').text
x1 = int(float(box_info.find('bndbox/xmin').text))
y1 = int(float(box_info.find('bndbox/ymin').text))
x2 = int(float(box_info.find('bndbox/xmax').text))
y2 = int(float(box_info.find('bndbox/ymax').text))
bb = BoundingBox(image_name=img_name,
class_id=obj_class,
coordinates=(x1, y1, x2, y2),
img_size=img_size,
type_coordinates=CoordinatesType.ABSOLUTE,
bb_type=BBType.GROUND_TRUTH,
format=BBFormat.XYX2Y2)
ret.append(bb)
return ret
def cvat2bb(path):
'''This format supports ground-truth only'''
ret = []
# Get annotation files in the path
annotation_files = _get_annotation_files(path)
# Loop through each file
for file_path in annotation_files:
if not validations.is_cvat_format(file_path):
continue
# Loop through the images
for image_info in ET.parse(file_path).iter('image'):
img_size = (int(image_info.attrib['width']),
int(image_info.attrib['height']))
img_name = image_info.attrib['name']
img_name = general_utils.get_file_name_only(img_name)
# Loop through the boxes
for box_info in image_info.iter('box'):
x1, y1, x2, y2 = float(box_info.attrib['xtl']), float(
box_info.attrib['ytl']), float(
box_info.attrib['xbr']), float(box_info.attrib['ybr'])
x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
bb = BoundingBox(image_name=img_name,
class_id=box_info.attrib['label'],
coordinates=(x1, y1, x2, y2),
img_size=img_size,
type_coordinates=CoordinatesType.ABSOLUTE,
bb_type=BBType.GROUND_TRUTH,
format=BBFormat.XYX2Y2)
ret.append(bb)
return ret
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 coco2bb(path, bb_type=BBType.GROUND_TRUTH):
ret = []
# Get annotation files in the path
annotation_files = _get_annotation_files(path)
# Loop through each file
for file_path in annotation_files:
if not validations.is_coco_format(file_path):
continue
with open(file_path, "r") as f:
json_object = json.load(f)
# COCO json file contains basically 3 lists:
# categories: containing the classes
# images: containing information of the images (width, height and filename)
# annotations: containing information of the bounding boxes (x1, y1, bb_width, bb_height)
classes = {}
if 'categories' in json_object:
classes = json_object['categories']
# into dictionary
classes = {c['id']: c['name'] for c in classes}
images = {}
# into dictionary
for i in json_object['images']:
images[i['id']] = {
'file_name': i['file_name'],
'img_size': (int(i['width']), int(i['height']))
}
annotations = []
if 'annotations' in json_object:
annotations = json_object['annotations']
for annotation in annotations:
img_id = annotation['image_id']
x1, y1, bb_width, bb_height = annotation['bbox']
if bb_type == BBType.DETECTED and 'score' not in annotation.keys():
print('Warning: Confidence not found in the JSON file!')
return ret
confidence = annotation[
'score'] if bb_type == BBType.DETECTED else None
# Make image name only the filename, without extension
img_name = images[img_id]['file_name']
img_name = general_utils.get_file_name_only(img_name)
# create BoundingBox object
bb = BoundingBox(image_name=img_name,
class_id=classes[annotation['category_id']],
coordinates=(x1, y1, bb_width, bb_height),
type_coordinates=CoordinatesType.ABSOLUTE,
img_size=images[img_id]['img_size'],
confidence=confidence,
bb_type=bb_type,
format=BBFormat.XYWH)
ret.append(bb)
return ret
def labelme2bb(annotations_path):
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_labelme_format(file_path):
continue
# Parse the JSON file
with open(file_path, "r") as f:
json_object = json.load(f)
img_path = json_object['imagePath']
img_path = os.path.basename(img_path)
img_path = general_utils.get_file_name_only(img_path)
img_size = (int(json_object['imageWidth']),
int(json_object['imageHeight']))
# If there are annotated objects
if 'shapes' in json_object:
# Loop through bounding boxes
for obj in json_object['shapes']:
obj_label = obj['label']
((x1, y1), (x2, y2)) = obj['points']
# If there is no bounding box annotations, bb coordinates could have been set to None
if x1 is None and y1 is None and x2 is None and y2 is None:
continue
x1, y1, x2, y2 = int(float(x1)), int(float(y1)), int(
float(x2)), int(float(y2))
bb = BoundingBox(image_name=img_path,
class_id=obj_label,
coordinates=(x1, y1, x2, y2),
img_size=img_size,
confidence=None,
type_coordinates=CoordinatesType.ABSOLUTE,
bb_type=BBType.GROUND_TRUTH,
format=BBFormat.XYX2Y2)
ret.append(bb)
return ret
def draw_bounding_boxes(self):
# Load image to obtain a clean image (without BBs)
img_path = os.path.join(self.dir_images,
self.image_files[self.selected_image_index])
img = cv2.imread(img_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# Get bounding boxes of the loaded image
img_name = self.image_files[self.selected_image_index]
img_name = general_utils.get_file_name_only(img_name)
# Add bounding boxes depending if the item is checked
if self.chb_gt_bb.isChecked() and self.gt_annotations is not None:
bboxes = BoundingBox.get_bounding_boxes_by_image_name(
self.gt_annotations, img_name)
if len(bboxes) == 0:
bboxes = BoundingBox.get_bounding_boxes_by_image_name(
self.gt_annotations, img_name)
# Draw bounding boxes
for bb in bboxes:
img = add_bb_into_image(img,
bb,
color=(0, 255, 0),
thickness=2,
label=None)
if self.chb_det_bb.isChecked() and self.det_annotations is not None:
bboxes = BoundingBox.get_bounding_boxes_by_image_name(
self.det_annotations, img_name)
if len(bboxes) == 0:
bboxes = BoundingBox.get_bounding_boxes_by_image_name(
self.det_annotations, img_name)
# Draw bounding boxes
for bb in bboxes:
img = add_bb_into_image(img,
bb,
color=(0, 0, 255),
thickness=2,
label=None)
return img