Q：在github找的cv代码基本都是根据现有且流行的公共数据集格式组织的训练数据集，这导致我使用labelme标注好之后需要我们重新组织数据集
labelme2coco
#!/usr/bin/env python
import argparse
import collections
import datetime
import glob
import json
import os
import os.path as osp
import sys
import uuid
import imgviz
import numpy as np
import labelme
try:
import pycocotools.mask
except ImportError:
print("Please install pycocotools:\n\n pip install pycocotools\n")
sys.exit(1)
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument("input_dir",default=r"data_annotated", help="input annotated directory")
parser.add_argument("output_dir",default=r"data_coco", help="output dataset directory")
parser.add_argument("--labels",default=r"labels.txt", help="labels file", required=True)
parser.add_argument(
"--noviz", help="no visualization", action="store_true"
)
args = parser.parse_args()
if osp.exists(args.output_dir):
print("Output directory already exists:", args.output_dir)
sys.exit(1)
os.makedirs(args.output_dir)
os.makedirs(osp.join(args.output_dir, "JPEGImages"))
if not args.noviz:
os.makedirs(osp.join(args.output_dir, "Visualization"))
print("Creating dataset:", args.output_dir)
now = datetime.datetime.now()
data = dict(
info=dict(
description=None,
url=None,
version=None,
year=now.year,
contributor=None,
date_created=now.strftime("%Y-%m-%d %H:%M:%S.%f"),
),
licenses=[dict(url=None, id=0, name=None,)],
images=[
# license, url, file_name, height, width, date_captured, id
],
type="instances",
annotations=[
# segmentation, area, iscrowd, image_id, bbox, category_id, id
],
categories=[
# supercategory, id, name
],
)
class_name_to_id = {}
for i, line in enumerate(open(args.labels).readlines()):
class_id = i - 1 # starts with -1
class_name = line.strip()
if class_id == -1:
assert class_name == "__ignore__"
continue
class_name_to_id[class_name] = class_id
data["categories"].append(
dict(supercategory=None, id=class_id, name=class_name,)
)
out_ann_file = osp.join(args.output_dir, "annotations.json")
label_files = glob.glob(osp.join(args.input_dir, "*.json"))
for image_id, filename in enumerate(label_files):
print("Generating dataset from:", filename)
label_file = labelme.LabelFile(filename=filename)
base = osp.splitext(osp.basename(filename))[0]
out_img_file = osp.join(args.output_dir, "JPEGImages", base + ".jpg")
img = labelme.utils.img_data_to_arr(label_file.imageData)
imgviz.io.imsave(out_img_file, img)
data["images"].append(
dict(
license=0,
url=None,
file_name=osp.relpath(out_img_file, osp.dirname(out_ann_file)),
height=img.shape[0],
width=img.shape[1],
date_captured=None,
id=image_id,
)
)
masks = {} # for area
segmentations = collections.defaultdict(list) # for segmentation
for shape in label_file.shapes:
points = shape["points"]
label = shape["label"]
group_id = shape.get("group_id")
shape_type = shape.get("shape_type", "polygon")
mask = labelme.utils.shape_to_mask(
img.shape[:2], points, shape_type
)
if group_id is None:
group_id = uuid.uuid1()
instance = (label, group_id)
if instance in masks:
masks[instance] = masks[instance] | mask
else:
masks[instance] = mask
if shape_type == "rectangle":
(x1, y1), (x2, y2) = points
x1, x2 = sorted([x1, x2])
y1, y2 = sorted([y1, y2])
points = [x1, y1, x2, y1, x2, y2, x1, y2]
if shape_type == "circle":
(x1, y1), (x2, y2) = points
r = np.linalg.norm([x2 - x1, y2 - y1])
# r(1-cos(a/2))<x, a=2*pi/N => N>pi/arccos(1-x/r)
# x: tolerance of the gap between the arc and the line segment
n_points_circle = max(int(np.pi / np.arccos(1 - 1 / r)), 12)
i = np.arange(n_points_circle)
x = x1 + r * np.sin(2 * np.pi / n_points_circle * i)
y = y1 + r * np.cos(2 * np.pi / n_points_circle * i)
points = np.stack((x, y), axis=1).flatten().tolist()
else:
points = np.asarray(points).flatten().tolist()
segmentations[instance].append(points)
segmentations = dict(segmentations)
for instance, mask in masks.items():
cls_name, group_id = instance
if cls_name not in class_name_to_id:
continue
cls_id = class_name_to_id[cls_name]
mask = np.asfortranarray(mask.astype(np.uint8))
mask = pycocotools.mask.encode(mask)
area = float(pycocotools.mask.area(mask))
bbox = pycocotools.mask.toBbox(mask).flatten().tolist()
data["annotations"].append(
dict(
id=len(data["annotations"]),
image_id=image_id,
category_id=cls_id,
segmentation=segmentations[instance],
area=area,
bbox=bbox,
iscrowd=0,
)
)
if not args.noviz:
viz = img
if masks:
labels, captions, masks = zip(
*[
(class_name_to_id[cnm], cnm, msk)
for (cnm, gid), msk in masks.items()
if cnm in class_name_to_id
]
)
viz = imgviz.instances2rgb(
image=img,
labels=labels,
masks=masks,
captions=captions,
font_size=15,
line_width=2,
)
out_viz_file = osp.join(
args.output_dir, "Visualization", base + ".jpg"
)
imgviz.io.imsave(out_viz_file, viz)
with open(out_ann_file, "w") as f:
json.dump(data, f)
if __name__ == "__main__":
main()labelme2voc
#!/usr/bin/env python
from __future__ import print_function
import argparse
import glob
import os
import os.path as osp
import sys
import imgviz
import numpy as np
import labelme
def main():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
parser.add_argument("input_dir", help="input annotated directory")
parser.add_argument("output_dir",help="output dataset directory")
parser.add_argument("--labels", help="labels file", required=True)
parser.add_argument(
"--noviz", help="no visualization", action="store_true"
)
args = parser.parse_args()
if osp.exists(args.output_dir):
print("Output directory already exists:", args.output_dir)
sys.exit(1)
os.makedirs(args.output_dir)
os.makedirs(osp.join(args.output_dir, "JPEGImages"))
os.makedirs(osp.join(args.output_dir, "SegmentationClass"))
os.makedirs(osp.join(args.output_dir, "SegmentationClassPNG"))
if not args.noviz:
os.makedirs(
osp.join(args.output_dir, "SegmentationClassVisualization")
)
os.makedirs(osp.join(args.output_dir, "SegmentationObject"))
os.makedirs(osp.join(args.output_dir, "SegmentationObjectPNG"))
if not args.noviz:
os.makedirs(
osp.join(args.output_dir, "SegmentationObjectVisualization")
)
print("Creating dataset:", args.output_dir)
class_names = []
class_name_to_id = {}
for i, line in enumerate(open(args.labels).readlines()):
class_id = i - 1 # starts with -1
class_name = line.strip()
class_name_to_id[class_name] = class_id
if class_id == -1:
assert class_name == "__ignore__"
continue
elif class_id == 0:
assert class_name == "_background_"
class_names.append(class_name)
class_names = tuple(class_names)
print("class_names:", class_names)
out_class_names_file = osp.join(args.output_dir, "class_names.txt")
with open(out_class_names_file, "w") as f:
f.writelines("\n".join(class_names))
print("Saved class_names:", out_class_names_file)
for filename in glob.glob(osp.join(args.input_dir, "*.json")):
print("Generating dataset from:", filename)
label_file = labelme.LabelFile(filename=filename)
base = osp.splitext(osp.basename(filename))[0]
out_img_file = osp.join(args.output_dir, "JPEGImages", base + ".jpg")
out_cls_file = osp.join(
args.output_dir, "SegmentationClass", base + ".npy"
)
out_clsp_file = osp.join(
args.output_dir, "SegmentationClassPNG", base + ".png"
)
if not args.noviz:
out_clsv_file = osp.join(
args.output_dir,
"SegmentationClassVisualization",
base + ".jpg",
)
out_ins_file = osp.join(
args.output_dir, "SegmentationObject", base + ".npy"
)
out_insp_file = osp.join(
args.output_dir, "SegmentationObjectPNG", base + ".png"
)
if not args.noviz:
out_insv_file = osp.join(
args.output_dir,
"SegmentationObjectVisualization",
base + ".jpg",
)
img = labelme.utils.img_data_to_arr(label_file.imageData)
imgviz.io.imsave(out_img_file, img)
cls, ins = labelme.utils.shapes_to_label(
img_shape=img.shape,
shapes=label_file.shapes,
label_name_to_value=class_name_to_id,
)
ins[cls == -1] = 0 # ignore it.
# class label
labelme.utils.lblsave(out_clsp_file, cls)
np.save(out_cls_file, cls)
if not args.noviz:
clsv = imgviz.label2rgb(
cls,
imgviz.rgb2gray(img),
label_names=class_names,
font_size=15,
loc="rb",
)
imgviz.io.imsave(out_clsv_file, clsv)
# instance label
labelme.utils.lblsave(out_insp_file, ins)
np.save(out_ins_file, ins)
if not args.noviz:
instance_ids = np.unique(ins)
instance_names = [str(i) for i in range(max(instance_ids) + 1)]
insv = imgviz.label2rgb(
ins,
imgviz.rgb2gray(img),
label_names=instance_names,
font_size=15,
loc="rb",
)
imgviz.io.imsave(out_insv_file, insv)
if __name__ == "__main__":
main()使用说明：
cd进入你的数据库(data_annotated文件夹所在位置)，原始标注好文件(jpg、json)存放在data_annotated文件夹，先建立一个labels.txt文件内容为：
__ignore__
_background_
类别1
类别2
类别3
...
重要说明：
- 第一行必须是 __ignore__
- 第二行必须是 _background_
从第三行开始才是您的实际类别名称
- 每个类别占一行
- 不能有空行
- 注意下划线的数量：
- __ignore__ 是两个下划线
- _background_ 是一个下划线
然后根据你的需求选择下列命令之一
python labelme2voc.py data_annotated data_dataset_voc --labels labels.txt
python labelme2coco.py data_annotated data_dataset_coco --labels labels.txt
运行画面：
如果运行报错大概率是环境问题
环境参考：
Package Version
----------------------- --------------------
absl-py 2.1.0
asttokens 2.4.1
backcall 0.2.0
beautifulsoup4 4.12.3
cachetools 5.3.3
certifi 2024.2.2
charset-normalizer 3.3.2
colorama 0.4.6
coloredlogs 15.0.1
contourpy 1.1.1
cycler 0.12.1
Cython 3.0.9
decorator 5.1.1
executing 2.0.1
filelock 3.13.1
flatbuffers 24.3.7
fonttools 4.50.0
gdown 5.1.0
gitdb 4.0.11
GitPython 3.1.42
google-auth 2.29.0
google-auth-oauthlib 1.0.0
grpcio 1.62.1
humanfriendly 10.0
idna 3.6
imageio 2.34.0
imgviz 1.7.5
importlib_metadata 7.1.0
importlib_resources 6.4.0
ipython 8.12.3
jedi 0.19.1
kiwisolver 1.4.5
labelImg 1.8.6
labelme 5.4.1
lazy_loader 0.3
lxml 5.1.0
Markdown 3.6
MarkupSafe 2.1.5
matplotlib 3.7.5
matplotlib-inline 0.1.6
mpmath 1.3.0
natsort 8.4.0
networkx 3.1
numpy 1.24.4
oauthlib 3.2.2
onnxruntime 1.17.1
opencv-python 4.9.0.80
packaging 24.0
pandas 2.0.3
parso 0.8.3
pickleshare 0.7.5
pillow 10.2.0
pip 23.3.1
prompt-toolkit 3.0.43
protobuf 5.26.0
psutil 5.9.8
pure-eval 0.2.2
py-cpuinfo 9.0.0
pyasn1 0.5.1
pyasn1-modules 0.3.0
pycocotools-windows 2.0.0.2
Pygments 2.17.2
pyparsing 3.1.2
PyQt5 5.15.10
PyQt5-Qt5 5.15.2
PyQt5-sip 12.13.0
pyreadline3 3.4.1
PySocks 1.7.1
python-dateutil 2.9.0.post0
pytz 2024.1
PyWavelets 1.4.1
PyYAML 6.0.1
QtPy 2.4.1
requests 2.31.0
requests-oauthlib 2.0.0
rsa 4.9
scikit-image 0.21.0
scipy 1.10.1
seaborn 0.13.2
setuptools 68.2.2
six 1.16.0
smmap 5.0.1
soupsieve 2.5
stack-data 0.6.3
sympy 1.12
tensorboard 2.14.0
tensorboard-data-server 0.7.2
termcolor 2.4.0
thop 0.1.1.post2209072238
tifffile 2023.7.10
torch 1.8.0+cu111
torchaudio 0.8.0
torchvision 0.9.0+cu111
tqdm 4.66.2
traitlets 5.14.2
typing_extensions 4.10.0
tzdata 2024.1
ultralytics 8.1.34
urllib3 2.2.1
wcwidth 0.2.13
Werkzeug 3.0.1
wheel 0.41.2
zipp 3.18.1
![IM 即时通讯系统-50-[特殊字符]cim(cross IM) 适用于开发者的分布式即时通讯系统](https://i-blog.csdnimg.cn/img_convert/796d0677346f8a7499ffdcdbfe37decf.jpeg)
