Tiện ích đơn giản

from ultralytics.data.converter import convert_segment_masks_to_yolo_seg

# The classes here is the total classes in the dataset, for COCO dataset we have 80 classes
convert_segment_masks_to_yolo_seg(masks_dir="path/to/masks_dir", output_dir="path/to/output_dir", classes=80)

data
|__ images
    ├─ 001.jpg
    ├─ 002.jpg
    ├─ ..
    └─ NNN.jpg
|__ labels
    ├─ 001.txt
    ├─ 002.txt
    ├─ ..
    └─ NNN.txt

import numpy as np

from ultralytics.utils.ops import segments2boxes

segments = np.array(
    [
        [805, 392, 797, 400, ..., 808, 714, 808, 392],
        [115, 398, 113, 400, ..., 150, 400, 149, 298],
        [267, 412, 265, 413, ..., 300, 413, 299, 412],
    ]
)

segments2boxes([s.reshape(-1, 2) for s in segments])
# >>> array([[ 741.66, 631.12, 133.31, 479.25],
#           [ 146.81, 649.69, 185.62, 502.88],
#           [ 281.81, 636.19, 118.12, 448.88]],
#           dtype=float32) # xywh bounding boxes

import numpy as np

from ultralytics.data.utils import polygon2mask

imgsz = (1080, 810)
polygon = np.array([805, 392, 797, 400, ..., 808, 714, 808, 392])  # (238, 2)

mask = polygon2mask(
    imgsz,  # tuple
    [polygon],  # input as list
    color=255,  # 8-bit binary
    downsample_ratio=1,
)

import numpy as np

from ultralytics.utils.instance import Bboxes

boxes = Bboxes(
    bboxes=np.array(
        [
            [22.878, 231.27, 804.98, 756.83],
            [48.552, 398.56, 245.35, 902.71],
            [669.47, 392.19, 809.72, 877.04],
            [221.52, 405.8, 344.98, 857.54],
            [0, 550.53, 63.01, 873.44],
            [0.0584, 254.46, 32.561, 324.87],
        ]
    ),
    format="xyxy",
)

boxes.areas()
# >>> array([ 4.1104e+05,       99216,       68000,       55772,       20347,      2288.5])

boxes.convert("xywh")
print(boxes.bboxes)
# >>> array(
#     [[ 413.93, 494.05,  782.1, 525.56],
#      [ 146.95, 650.63,  196.8, 504.15],
#      [  739.6, 634.62, 140.25, 484.85],
#      [ 283.25, 631.67, 123.46, 451.74],
#      [ 31.505, 711.99,  63.01, 322.91],
#      [  16.31, 289.67, 32.503,  70.41]]
# )

import numpy as np

from ultralytics.utils.ops import xyxy2xywh

xyxy_boxes = np.array(
    [
        [22.878, 231.27, 804.98, 756.83],
        [48.552, 398.56, 245.35, 902.71],
        [669.47, 392.19, 809.72, 877.04],
        [221.52, 405.8, 344.98, 857.54],
        [0, 550.53, 63.01, 873.44],
        [0.0584, 254.46, 32.561, 324.87],
    ]
)
xywh = xyxy2xywh(xyxy_boxes)

print(xywh)
# >>> array(
#     [[ 413.93,  494.05,   782.1, 525.56],
#     [  146.95,  650.63,   196.8, 504.15],
#     [   739.6,  634.62,  140.25, 484.85],
#     [  283.25,  631.67,  123.46, 451.74],
#     [  31.505,  711.99,   63.01, 322.91],
#     [   16.31,  289.67,  32.503,  70.41]]
# )

from ultralytics.utils.ops import (
    ltwh2xywh,
    ltwh2xyxy,
    xywh2ltwh,  # xywh → top-left corner, w, h
    xywh2xyxy,
    xywhn2xyxy,  # normalized → pixel
    xyxy2ltwh,  # xyxy → top-left corner, w, h
    xyxy2xywhn,  # pixel → normalized
)

for func in (ltwh2xywh, ltwh2xyxy, xywh2ltwh, xywh2xyxy, xywhn2xyxy, xyxy2ltwh, xyxy2xywhn):
    print(help(func))  # print function docstrings

import cv2 as cv
import numpy as np

from ultralytics.utils.plotting import Annotator, colors

obb_names = {10: "small vehicle"}
obb_image = cv.imread("datasets/dota8/images/train/P1142__1024__0___824.jpg")
obb_boxes = np.array(
    [
        [0, 635, 560, 919, 719, 1087, 420, 803, 261],  # class-idx x1 y1 x2 y2 x3 y2 x4 y4
        [0, 331, 19, 493, 260, 776, 70, 613, -171],
        [9, 869, 161, 886, 147, 851, 101, 833, 115],
    ]
)
ann = Annotator(
    obb_image,
    line_width=None,  # default auto-size
    font_size=None,  # default auto-size
    font="Arial.ttf",  # must be ImageFont compatible
    pil=False,  # use PIL, otherwise uses OpenCV
)
for obb in obb_boxes:
    c_idx, *obb = obb
    obb = np.array(obb).reshape(-1, 4, 2).squeeze()
    label = f"{obb_names.get(int(c_idx))}"
    ann.box_label(
        obb,
        label,
        color=colors(c_idx, True),
        rotated=True,
    )

image_with_obb = ann.result()

import cv2

from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator

model = YOLO("yolo11s.pt")
names = model.names
cap = cv2.VideoCapture("path/to/video/file.mp4")

w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
writer = cv2.VideoWriter("Ultralytics circle annotation.avi", cv2.VideoWriter_fourcc(*"MJPG"), fps, (w, h))

while True:
    ret, im0 = cap.read()
    if not ret:
        break

    annotator = Annotator(im0)
    results = model.predict(im0)
    boxes = results[0].boxes.xyxy.cpu()
    clss = results[0].boxes.cls.cpu().tolist()

    for box, cls in zip(boxes, clss):
        annotator.circle_label(box, label=names[int(cls)])

    writer.write(im0)
    cv2.imshow("Ultralytics circle annotation", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

writer.release()
cap.release()
cv2.destroyAllWindows()

import cv2

from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator

model = YOLO("yolo11s.pt")
names = model.names
cap = cv2.VideoCapture("path/to/video/file.mp4")

w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
writer = cv2.VideoWriter("Ultralytics text annotation.avi", cv2.VideoWriter_fourcc(*"MJPG"), fps, (w, h))

while True:
    ret, im0 = cap.read()
    if not ret:
        break

    annotator = Annotator(im0)
    results = model.predict(im0)
    boxes = results[0].boxes.xyxy.cpu()
    clss = results[0].boxes.cls.cpu().tolist()

    for box, cls in zip(boxes, clss):
        annotator.text_label(box, label=names[int(cls)])

    writer.write(im0)
    cv2.imshow("Ultralytics text annotation", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

writer.release()
cap.release()
cv2.destroyAllWindows()

from ultralytics.utils.ops import Profile

with Profile(device="cuda:0") as dt:
    pass  # operation to measure

print(dt)
# >>> "Elapsed time is 9.5367431640625e-07 s"

from ultralytics.data.utils import IMG_FORMATS, VID_FORMATS

print(IMG_FORMATS)
# {'tiff', 'pfm', 'bmp', 'mpo', 'dng', 'jpeg', 'png', 'webp', 'tif', 'jpg'}

print(VID_FORMATS)
# {'avi', 'mpg', 'wmv', 'mpeg', 'm4v', 'mov', 'mp4', 'asf', 'mkv', 'ts', 'gif', 'webm'}

from ultralytics.utils.ops import make_divisible

make_divisible(7, 3)
# >>> 9
make_divisible(7, 2)
# >>> 8

from ultralytics.data.annotator import auto_annotate

auto_annotate(
    data="path/to/new/data",
    det_model="yolo11n.pt",
    sam_model="mobile_sam.pt",
    device="cuda",
    output_dir="path/to/save_labels",
)

from ultralytics.data.converter import convert_coco

convert_coco(
    "../datasets/coco/annotations/",
    use_segments=False,
    use_keypoints=False,
    cls91to80=True,
)

from ultralytics.data.converter import yolo_bbox2segment

yolo_bbox2segment(
    im_dir="path/to/images",
    save_dir=None,  # saved to "labels-segment" in the images directory
    sam_model="sam_b.pt",
)