Перейти к содержимому

Сегментация экземпляров

Примеры сегментации экземпляров

Instance segmentation goes a step further than object detection and involves identifying individual objects in an image and segmenting them from the rest of the image.

Выход модели сегментации экземпляров - это набор масок или контуров, очерчивающих каждый объект на изображении, а также метки классов и баллы доверия для каждого объекта. Сегментация экземпляров полезна, когда тебе нужно знать не только местоположение объектов на изображении, но и их точную форму.



Смотри: Run Segmentation with Pre-Trained Ultralytics YOLO Model in Python.

Наконечник

YOLO11 Segment models use the -seg суффикс, то есть yolo11n-seg.pt и предварительно обучены на COCO.

Модели

YOLO11 pretrained Segment models are shown here. Detect, Segment and Pose models are pretrained on the COCO dataset, while Classify models are pretrained on the ImageNet dataset.

Модели автоматически загружаются с последнегорелиза Ultralytics при первом использовании.

Модель Размер
(пикселей)
mAPbox
50-95
mAPmask
50-95
Скорость
CPU ONNX
(мс)
Speed
T4 TensorRT10
(ms)
params
(M)
FLOPs
(B)
YOLO11n-seg 640 38.9 32.0 65.9 ± 1.1 1.8 ± 0.0 2.9 10.4
YOLO11s-seg 640 46.6 37.8 117.6 ± 4.9 2.9 ± 0.0 10.1 35.5
YOLO11m-seg 640 51.5 41.5 281.6 ± 1.2 6.3 ± 0.1 22.4 123.3
YOLO11l-seg 640 53.4 42.9 344.2 ± 3.2 7.8 ± 0.2 27.6 142.2
YOLO11x-seg 640 54.7 43.8 664.5 ± 3.2 15.8 ± 0.7 62.1 319.0
  • mAPval Значения приведены для одномодельного одномасштабного на COCO val2017 Набор данных.
    Размножайся с помощью yolo val segment data=coco-seg.yaml device=0
  • Скорость Усреднение изображений COCO val с помощью Amazon EC2 P4d например.
    Размножайся с помощью yolo val segment data=coco-seg.yaml batch=1 device=0|cpu

Поезд

Train YOLO11n-seg on the COCO128-seg dataset for 100 epochs at image size 640. For a full list of available arguments see the Configuration page.

Пример

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-seg.yaml")  # build a new model from YAML
model = YOLO("yolo11n-seg.pt")  # load a pretrained model (recommended for training)
model = YOLO("yolo11n-seg.yaml").load("yolo11n.pt")  # build from YAML and transfer weights

# Train the model
results = model.train(data="coco8-seg.yaml", epochs=100, imgsz=640)
# Build a new model from YAML and start training from scratch
yolo segment train data=coco8-seg.yaml model=yolo11n-seg.yaml epochs=100 imgsz=640

# Start training from a pretrained *.pt model
yolo segment train data=coco8-seg.yaml model=yolo11n-seg.pt epochs=100 imgsz=640

# Build a new model from YAML, transfer pretrained weights to it and start training
yolo segment train data=coco8-seg.yaml model=yolo11n-seg.yaml pretrained=yolo11n-seg.pt epochs=100 imgsz=640

Формат датасета

YOLO Формат набора данных сегментации можно подробно изучить в руководстве по набору данных. Чтобы преобразовать существующий набор данных из других форматов (например, COCO и т.д.) в формат YOLO , воспользуйся инструментом JSON2YOLO по адресу Ultralytics.

Вэл

Validate trained YOLO11n-seg model accuracy on the COCO128-seg dataset. No arguments are needed as the model сохраняет свою подготовку data и аргументы в качестве атрибутов модели.

Пример

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-seg.pt")  # load an official model
model = YOLO("path/to/best.pt")  # load a custom model

# Validate the model
metrics = model.val()  # no arguments needed, dataset and settings remembered
metrics.box.map  # map50-95(B)
metrics.box.map50  # map50(B)
metrics.box.map75  # map75(B)
metrics.box.maps  # a list contains map50-95(B) of each category
metrics.seg.map  # map50-95(M)
metrics.seg.map50  # map50(M)
metrics.seg.map75  # map75(M)
metrics.seg.maps  # a list contains map50-95(M) of each category
yolo segment val model=yolo11n-seg.pt  # val official model
yolo segment val model=path/to/best.pt  # val custom model

Предсказывай

Use a trained YOLO11n-seg model to run predictions on images.

Пример

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-seg.pt")  # load an official model
model = YOLO("path/to/best.pt")  # load a custom model

# Predict with the model
results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
yolo segment predict model=yolo11n-seg.pt source='https://ultralytics.com/images/bus.jpg'  # predict with official model
yolo segment predict model=path/to/best.pt source='https://ultralytics.com/images/bus.jpg'  # predict with custom model

Смотреть полностью predict Подробности о режиме в Предсказывай Страница.

Экспорт

Export a YOLO11n-seg model to a different format like ONNX, CoreML, etc.

Пример

from ultralytics import YOLO

# Load a model
model = YOLO("yolo11n-seg.pt")  # load an official model
model = YOLO("path/to/best.pt")  # load a custom trained model

# Export the model
model.export(format="onnx")
yolo export model=yolo11n-seg.pt format=onnx  # export official model
yolo export model=path/to/best.pt format=onnx  # export custom trained model

Available YOLO11-seg export formats are in the table below. You can export to any format using the format аргумент, то есть format='onnx' или format='engine'. Ты можешь предсказывать или проверять непосредственно на экспортированных моделях, то есть yolo predict model=yolo11n-seg.onnx. Примеры использования будут показаны для твоей модели после завершения экспорта.

Формат format Аргумент Модель Метаданные Аргументы
PyTorch - yolo11n-seg.pt -
TorchScript torchscript yolo11n-seg.torchscript imgsz, optimize, batch
ONNX onnx yolo11n-seg.onnx imgsz, half, dynamic, simplify, opset, batch
OpenVINO openvino yolo11n-seg_openvino_model/ imgsz, half, int8, batch
TensorRT engine yolo11n-seg.engine imgsz, half, dynamic, simplify, workspace, int8, batch
CoreML coreml yolo11n-seg.mlpackage imgsz, half, int8, nms, batch
TF SavedModel saved_model yolo11n-seg_saved_model/ imgsz, keras, int8, batch
TF GraphDef pb yolo11n-seg.pb imgsz, batch
TF Lite tflite yolo11n-seg.tflite imgsz, half, int8, batch
TF Край TPU edgetpu yolo11n-seg_edgetpu.tflite imgsz
TF.js tfjs yolo11n-seg_web_model/ imgsz, half, int8, batch
PaddlePaddle paddle yolo11n-seg_paddle_model/ imgsz, batch
NCNN ncnn yolo11n-seg_ncnn_model/ imgsz, half, batch

Смотреть полностью export подробности в Экспорт Страница.

ВОПРОСЫ И ОТВЕТЫ

How do I train a YOLO11 segmentation model on a custom dataset?

To train a YOLO11 segmentation model on a custom dataset, you first need to prepare your dataset in the YOLO segmentation format. You can use tools like JSON2YOLO to convert datasets from other formats. Once your dataset is ready, you can train the model using Python or CLI commands:

Пример

from ultralytics import YOLO

# Load a pretrained YOLO11 segment model
model = YOLO("yolo11n-seg.pt")

# Train the model
results = model.train(data="path/to/your_dataset.yaml", epochs=100, imgsz=640)
yolo segment train data=path/to/your_dataset.yaml model=yolo11n-seg.pt epochs=100 imgsz=640

Проверь страницу "Конфигурация", чтобы узнать больше доступных аргументов.

What is the difference between object detection and instance segmentation in YOLO11?

Object detection identifies and localizes objects within an image by drawing bounding boxes around them, whereas instance segmentation not only identifies the bounding boxes but also delineates the exact shape of each object. YOLO11 instance segmentation models provide masks or contours that outline each detected object, which is particularly useful for tasks where knowing the precise shape of objects is important, such as medical imaging or autonomous driving.

Why use YOLO11 for instance segmentation?

Ultralytics YOLO11 is a state-of-the-art model recognized for its high accuracy and real-time performance, making it ideal for instance segmentation tasks. YOLO11 Segment models come pretrained on the COCO dataset, ensuring robust performance across a variety of objects. Additionally, YOLO supports training, validation, prediction, and export functionalities with seamless integration, making it highly versatile for both research and industry applications.

How do I load and validate a pretrained YOLO segmentation model?

Loading and validating a pretrained YOLO segmentation model is straightforward. Here's how you can do it using both Python and CLI:

Пример

from ultralytics import YOLO

# Load a pretrained model
model = YOLO("yolo11n-seg.pt")

# Validate the model
metrics = model.val()
print("Mean Average Precision for boxes:", metrics.box.map)
print("Mean Average Precision for masks:", metrics.seg.map)
yolo segment val model=yolo11n-seg.pt

These steps will provide you with validation metrics like Mean Average Precision (mAP), crucial for assessing model performance.

How can I export a YOLO segmentation model to ONNX format?

Exporting a YOLO segmentation model to ONNX format is simple and can be done using Python or CLI commands:

Пример

from ultralytics import YOLO

# Load a pretrained model
model = YOLO("yolo11n-seg.pt")

# Export the model to ONNX format
model.export(format="onnx")
yolo export model=yolo11n-seg.pt format=onnx

Подробнее об экспорте в различные форматы читай на странице " Экспорт ".


📅 Created 11 months ago ✏️ Updated 5 days ago

Комментарии