SAM 3：使用概念分割一切#

from ultralytics.models.sam import SAM3SemanticPredictor

# Initialize predictor with configuration
overrides = {
    "conf": 0.25,
    "task": "segment",
    "mode": "predict",
    "model": "sam3.pt",
    "quantize": 16,  # Use FP16 for faster inference
    "save": True,
}
predictor = SAM3SemanticPredictor(overrides=overrides)

# Set image once for multiple queries
predictor.set_image("path/to/image.jpg")

# Query with multiple text prompts
results = predictor(text=["person", "bus", "glasses"])

# Works with descriptive phrases
results = predictor(text=["person with red cloth", "person with blue cloth"])

# Query with a single concept
results = predictor(text=["a person"])

from ultralytics.models.sam import SAM3SemanticPredictor

# Initialize predictor
overrides = {"conf": 0.25, "task": "segment", "mode": "predict", "model": "sam3.pt", "quantize": 16, "save": True}
predictor = SAM3SemanticPredictor(overrides=overrides)

# Set image
predictor.set_image("path/to/image.jpg")

# Provide bounding box examples to segment similar objects
results = predictor(bboxes=[[480.0, 290.0, 590.0, 650.0]])

# Multiple bounding boxes as exemplars of the same visual concept
results = predictor(bboxes=[[539, 599, 589, 639], [343, 267, 499, 662]])

import cv2

from ultralytics.models.sam import SAM3SemanticPredictor
from ultralytics.utils.plotting import Annotator, colors

# Initialize predictors
overrides = {"conf": 0.50, "task": "segment", "mode": "predict", "model": "sam3.pt", "verbose": False}
predictor = SAM3SemanticPredictor(overrides=overrides)
predictor2 = SAM3SemanticPredictor(overrides=overrides)

# Extract features from the first predictor
source = "path/to/image.jpg"
predictor.set_image(source)
src_shape = cv2.imread(source).shape[:2]

# Setup second predictor and reuse features
predictor2.setup_model()

# Perform inference using shared features with text prompt
masks, boxes = predictor2.inference_features(predictor.features, src_shape=src_shape, text=["person"])

# Perform inference using shared features with bounding box prompt
masks, boxes = predictor2.inference_features(predictor.features, src_shape=src_shape, bboxes=[[439, 437, 524, 709]])

# Visualize results
if masks is not None:
    masks, boxes = masks.cpu().numpy(), boxes.cpu().numpy()
    im = cv2.imread(source)
    annotator = Annotator(im, pil=False)
    annotator.masks(masks, [colors(x, True) for x in range(len(masks))])

    cv2.imshow("result", annotator.result())
    cv2.waitKey(0)

from ultralytics.models.sam import SAM3VideoPredictor

# Create video predictor
overrides = {"conf": 0.25, "task": "segment", "mode": "predict", "model": "sam3.pt", "quantize": 16}
predictor = SAM3VideoPredictor(overrides=overrides)

# Track objects using bounding box prompts
results = predictor(source="path/to/video.mp4", bboxes=[[706.5, 442.5, 905.25, 555], [598, 635, 725, 750]], stream=True)

# Process and display results
for r in results:
    r.show()  # Display frame with segmentation masks

from ultralytics.models.sam import SAM3VideoSemanticPredictor

# Initialize semantic video predictor
overrides = {
    "conf": 0.25,
    "task": "segment",
    "mode": "predict",
    "imgsz": 640,
    "model": "sam3.pt",
    "quantize": 16,
    "save": True,
}
predictor = SAM3VideoSemanticPredictor(overrides=overrides)

# Track concepts using text prompts
results = predictor(source="path/to/video.mp4", text=["person", "bicycle"], stream=True)

# Process results
for r in results:
    r.show()  # Display frame with tracked objects

# Alternative: Track with bounding box prompts
results = predictor(
    source="path/to/video.mp4",
    bboxes=[[864, 383, 975, 620], [705, 229, 782, 402]],
    labels=[1, 1],  # Positive labels
    stream=True,
)

from ultralytics import SAM

model = SAM("sam3.pt")

# Single point prompt - segments object at specific location
results = model.predict(source="path/to/image.jpg", points=[900, 370], labels=[1])
results[0].show()

# Multiple points - segments single object with multiple point hints
results = model.predict(source="path/to/image.jpg", points=[[400, 370], [900, 370]], labels=[1, 1])

# Box prompt - segments object within bounding box
results = model.predict(source="path/to/image.jpg", bboxes=[100, 150, 300, 400])
results[0].show()

from ultralytics import ASSETS, SAM, YOLO, FastSAM

# Profile SAM3, SAM2-t, SAM2-b, SAM-b, MobileSAM
for file in ["sam_b.pt", "sam2_b.pt", "sam2_t.pt", "mobile_sam.pt", "sam3.pt"]:
    model = SAM(file)
    model.info()
    model(ASSETS)

# Profile FastSAM-s
model = FastSAM("FastSAM-s.pt")
model.info()
model(ASSETS)

# Profile YOLO models
for file_name in ["yolov8n-seg.pt", "yolo11n-seg.pt", "yolo26n-seg.pt"]:
    model = YOLO(file_name)
    model.info()
    model(ASSETS, nms=False)  # YOLO26 NMS-free head; no-op for YOLOv8/YOLO11