shuoshuoshuo
/
labelme2yolo
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #7 from GreatV/package 

update export data format: yolo polygon format
This commit is contained in:
Wang Xin 2022-11-25 10:24:42 +08:00 committed by GitHub
parent 53a5b316d2 051c019e3f
commit 7b0087be3c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 132 additions and 100 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -10,6 +10,12 @@
Help converting LabelMe Annotation Tool JSON format to YOLO text file format.
If you've already marked your segmentation dataset by LabelMe, it's easy to use this tool to help converting to YOLO format dataset.
---------
## New
- export data as yolo polygon annotation (for YOLOv5 v7.0 segmentation)
## Installation
```console

3
src/labelme2yolo/__about__.py
View File

@ -1,4 +1,5 @@
# SPDX-FileCopyrightText: 2022-present Wang Xin <xinwang614@gmail.com>
#
# SPDX-License-Identifier: MIT
__version__ = "0.0.2"
__version__ = '0.0.5'

223
src/labelme2yolo/l2y.py
View File

@ -119,122 +119,131 @@ def save_yolo_image(json_data, json_name, image_dir_path, target_dir):
return img_path
class Labelme2YOLO(object):
def __init__(self, json_dir):
self._json_dir = json_dir
self._label_id_map = get_label_id_map(self._json_dir)
self._label_id_map = self._get_label_id_map(self._json_dir)
def _make_train_val_dir(self):
self._label_dir_path = os.path.join(self._json_dir, "YOLODataset/labels/")
self._image_dir_path = os.path.join(self._json_dir, "YOLODataset/images/")
self._label_dir_path = os.path.join(self._json_dir,
'YOLODataset/labels/')
self._image_dir_path = os.path.join(self._json_dir,
'YOLODataset/images/')
for yolo_path in (
os.path.join(self._label_dir_path + "train/"),
os.path.join(self._label_dir_path + "val/"),
os.path.join(self._label_dir_path + "test/"),
os.path.join(self._image_dir_path + "train/"),
os.path.join(self._image_dir_path + "val/"),
os.path.join(self._image_dir_path + "test/"),
):
for yolo_path in (os.path.join(self._label_dir_path + 'train/'),
os.path.join(self._label_dir_path + 'val/'),
os.path.join(self._label_dir_path + 'test/'),
os.path.join(self._image_dir_path + 'train/'),
os.path.join(self._image_dir_path + 'val/'),
os.path.join(self._image_dir_path + 'test/')):
if os.path.exists(yolo_path):
shutil.rmtree(yolo_path)
os.makedirs(yolo_path)
def _get_label_id_map(self, json_dir):
label_set = set()
for file_name in os.listdir(json_dir):
if file_name.endswith('json'):
json_path = os.path.join(json_dir, file_name)
data = json.load(open(json_path))
for shape in data['shapes']:
label_set.add(shape['label'])
return OrderedDict([(label, label_id)
for label_id, label in enumerate(label_set)])
def _train_test_split(self, folders, json_names, val_size, test_size):
if (
len(folders) > 0
and "train" in folders
and "val" in folders
and "test" in folders
):
train_json_names = self.get_json_names("train/")
val_json_names = self.get_json_names("val/")
test_json_names = self.get_json_names("test/")
if len(folders) > 0 and 'train' in folders and 'val' in folders and 'test' in folders:
train_folder = os.path.join(self._json_dir, 'train/')
train_json_names = [train_sample_name + '.json'
for train_sample_name in os.listdir(train_folder)
if os.path.isdir(os.path.join(train_folder, train_sample_name))]
val_folder = os.path.join(self._json_dir, 'val/')
val_json_names = [val_sample_name + '.json'
for val_sample_name in os.listdir(val_folder)
if os.path.isdir(os.path.join(val_folder, val_sample_name))]
test_folder = os.path.join(self._json_dir, 'test/')
test_json_names = [test_sample_name + '.json'
for test_sample_name in os.listdir(test_folder)
if os.path.isdir(os.path.join(test_folder, test_sample_name))]
return train_json_names, val_json_names, test_json_names
train_indexes, val_indexes = train_test_split(
range(len(json_names)), test_size=val_size
)
tmp_train_len = len(train_indexes)
test_indexes = []
if test_size:
train_indexes, test_indexes = train_test_split(
range(tmp_train_len), test_size=test_size / (1 - val_size)
)
train_json_names = [json_names[train_idx] for train_idx in train_indexes]
val_json_names = [json_names[val_idx] for val_idx in val_indexes]
test_json_names = [json_names[test_idx] for test_idx in test_indexes]
train_idxs, val_idxs = train_test_split(range(len(json_names)),
test_size=val_size)
tmp_train_len = len(train_idxs)
test_idxs = []
if test_size > 1e-8:
train_idxs, test_idxs = train_test_split(
range(tmp_train_len), test_size=test_size / (1 - val_size))
train_json_names = [json_names[train_idx] for train_idx in train_idxs]
val_json_names = [json_names[val_idx] for val_idx in val_idxs]
test_json_names = [json_names[test_idx] for test_idx in test_idxs]
return train_json_names, val_json_names, test_json_names
def get_json_names(self, data_type: str):
data_folder = os.path.join(self._json_dir, data_type)
data_json_names = [
data_sample_name + ".json"
for data_sample_name in os.listdir(data_folder)
if os.path.isdir(os.path.join(data_folder, data_sample_name))
]
return data_json_names
def convert(self, val_size, test_size):
json_names = [
file_name
for file_name in os.listdir(self._json_dir)
if os.path.isfile(os.path.join(self._json_dir, file_name))
and file_name.endswith(".json")
]
folders = [
file_name
for file_name in os.listdir(self._json_dir)
if os.path.isdir(os.path.join(self._json_dir, file_name))
]
json_names = [file_name for file_name in os.listdir(self._json_dir)
if os.path.isfile(os.path.join(self._json_dir, file_name)) and
file_name.endswith('.json')]
folders = [file_name for file_name in os.listdir(self._json_dir)
if os.path.isdir(os.path.join(self._json_dir, file_name))]
train_json_names, val_json_names, test_json_names = self._train_test_split(
folders, json_names, val_size, test_size
)
folders, json_names, val_size, test_size)
self._make_train_val_dir()
# convert labelme object to yolo format object, and save them to files
# also get image from labelme json file and save them under images folder
for target_dir, json_names in zip(
("train/", "val/", "test/"),
(train_json_names, val_json_names, test_json_names),
):
pool = Pool(NUM_THREADS)
for target_dir, json_names in zip(('train/', 'val/', 'test/'),
(train_json_names, val_json_names, test_json_names)):
pool = Pool(os.cpu_count() - 1)
for json_name in json_names:
pool.apply_async(self.covert_json_to_text, args=(target_dir, json_name))
pool.apply_async(self.covert_json_to_text,
args=(target_dir, json_name))
pool.close()
pool.join()
print("Generating dataset.yaml file ...")
print('Generating dataset.yaml file ...')
self._save_dataset_yaml()
def covert_json_to_text(self, target_dir, json_name):
json_path = os.path.join(self._json_dir, json_name)
json_data = json.load(open(json_path))
print("Converting %s for %s ..." % (json_name, target_dir.replace("/", "")))
img_path = save_yolo_image(
json_data, json_name, self._image_dir_path, target_dir
)
print('Converting %s for %s ...' %
(json_name, target_dir.replace('/', '')))
img_path = self._save_yolo_image(json_data,
json_name,
self._image_dir_path,
target_dir)
yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
save_yolo_label(json_name, self._label_dir_path, target_dir, yolo_obj_list)
self._save_yolo_label(json_name,
self._label_dir_path,
target_dir,
yolo_obj_list)
def convert_one(self, json_name):
json_path = os.path.join(self._json_dir, json_name)
json_data = json.load(open(json_path))
print("Converting %s ..." % json_name)
print('Converting %s ...' % json_name)
img_path = save_yolo_image(json_data, json_name, self._json_dir, "")
img_path = self._save_yolo_image(json_data, json_name,
self._json_dir, '')
yolo_obj_list = self._get_yolo_object_list(json_data, img_path)
save_yolo_label(json_name, self._json_dir, "", yolo_obj_list)
self._save_yolo_label(json_name, self._json_dir,
'', yolo_obj_list)
def _get_yolo_object_list(self, json_data, img_path):
yolo_obj_list = []
@ -243,22 +252,22 @@ class Labelme2YOLO(object):
for shape in json_data["shapes"]:
# labelme circle shape is different from others
# it only has 2 points, 1st is circle center, 2nd is drag end point
if shape["shape_type"] == "circle":
yolo_obj = self._get_circle_shape_yolo_object(shape, img_h, img_w)
if shape['shape_type'] == 'circle':
yolo_obj = self._get_circle_shape_yolo_object(
shape, img_h, img_w)
else:
yolo_obj = self._get_other_shape_yolo_object(shape, img_h, img_w)
yolo_obj = self._get_other_shape_yolo_object(
shape, img_h, img_w)
yolo_obj_list.append(yolo_obj)
return yolo_obj_list
def _get_circle_shape_yolo_object(self, shape, img_h, img_w):
obj_center_x, obj_center_y = shape["points"][0]
obj_center_x, obj_center_y = shape['points'][0]
radius = math.sqrt(
(obj_center_x - shape["points"][1][0]) ** 2
+ (obj_center_y - shape["points"][1][1]) ** 2
)
radius = math.sqrt((obj_center_x - shape['points'][1][0]) ** 2 +
(obj_center_y - shape['points'][1][1]) ** 2)
obj_w = 2 * radius
obj_h = 2 * radius
@ -267,41 +276,57 @@ class Labelme2YOLO(object):
yolo_w = round(float(obj_w / img_w), 6)
yolo_h = round(float(obj_h / img_h), 6)
label_id = self._label_id_map[shape["label"]]
label_id = self._label_id_map[shape['label']]
return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
def _get_other_shape_yolo_object(self, shape, img_h, img_w):
def __get_object_desc(obj_port_list):
def __get_dist(int_list):
return max(int_list) - min(int_list)
x_lists = [port[0] for port in obj_port_list]
y_lists = [port[1] for port in obj_port_list]
point_list = shape['points']
points = np.zeros(2 * len(point_list))
points[::2] = [float(point[0]) / img_w for point in point_list]
points[1::2] = [float(point[1]) / img_h for point in point_list]
label_id = self._label_id_map[shape['label']]
return min(x_lists), __get_dist(x_lists), min(y_lists), __get_dist(y_lists)
return (label_id, points.tolist())
obj_x_min, obj_w, obj_y_min, obj_h = __get_object_desc(shape["points"])
def _save_yolo_label(self, json_name, label_dir_path, target_dir, yolo_obj_list):
txt_path = os.path.join(label_dir_path,
target_dir,
json_name.replace('.json', '.txt'))
yolo_center_x = round(float((obj_x_min + obj_w / 2.0) / img_w), 6)
yolo_center_y = round(float((obj_y_min + obj_h / 2.0) / img_h), 6)
yolo_w = round(float(obj_w / img_w), 6)
yolo_h = round(float(obj_h / img_h), 6)
with open(txt_path, 'w+') as f:
for yolo_obj in yolo_obj_list:
label, points = yolo_obj
points = [str(item) for item in points]
yolo_obj_line = f"{label} {' '.join(points)}\n"
f.write(yolo_obj_line)
label_id = self._label_id_map[shape["label"]]
def _save_yolo_image(self, json_data, json_name, image_dir_path, target_dir):
img_name = json_name.replace('.json', '.png')
img_path = os.path.join(image_dir_path, target_dir, img_name)
return label_id, yolo_center_x, yolo_center_y, yolo_w, yolo_h
if not os.path.exists(img_path):
img = img_b64_to_arr(json_data['imageData'])
PIL.Image.fromarray(img).save(img_path)
return img_path
def _save_dataset_yaml(self):
yaml_path = os.path.join(self._json_dir, "YOLODataset", "dataset.yaml")
yaml_path = os.path.join(
self._json_dir, 'YOLODataset/', 'dataset.yaml')
with open(yaml_path, "w+") as yaml_file:
yaml_file.write("train: %s\n" % os.path.join(self._image_dir_path, "train"))
yaml_file.write("val: %s\n\n" % os.path.join(self._image_dir_path, "val"))
yaml_file.write("test: %s\n\n" % os.path.join(self._image_dir_path, "test"))
yaml_file.write("nc: %i\n\n" % len(self._label_id_map))
with open(yaml_path, 'w+') as yaml_file:
yaml_file.write('train: %s\n' %
os.path.join(self._image_dir_path, 'train/'))
yaml_file.write('val: %s\n' %
os.path.join(self._image_dir_path, 'val/'))
yaml_file.write('test: %s\n' %
os.path.join(self._image_dir_path, 'test/'))
yaml_file.write('nc: %i\n' % len(self._label_id_map))
names_str = ''
names_str = ""
for label, _ in self._label_id_map.items():
names_str += "'%s', " % label
names_str = names_str.rstrip(", ")