دمج المهام في مسار واحد

from ultralytics import YOLO

detector = YOLO("yolo26n.pt")
classifier = YOLO("yolo26n-cls.pt")  # swap in your own fine-tuned classifier

result = detector("https://ultralytics.com/images/bus.jpg", conf=0.5)[0]
crops, labels = [], []
for box in result.boxes:
    x1, y1, x2, y2 = box.xyxy[0].int().tolist()
    crops.append(result.orig_img[y1:y2, x1:x2])  # BGR numpy crop, same as the detector saw
    labels.append(result.names[int(box.cls)])

for label, crop_result in zip(labels, classifier(crops, verbose=False)):  # one batched call for all crops
    probs = crop_result.probs
    print(f"{label:6s} -> {crop_result.names[probs.top1]} ({float(probs.top1conf):.2f})")

bus    -> bullet_train (0.31)
person -> sweatshirt (0.24)
person -> abaya (0.50)
person -> loudspeaker (0.49)
person -> frilled_lizard (0.24)

from ultralytics import YOLO

detector = YOLO("yolo26n.pt")
classifier = YOLO("yolo26n-cls.pt")  # swap in your own fine-tuned classifier
source = "https://github.com/ultralytics/assets/releases/download/v0.0.0/decelera_portrait_min.mov"

labels = {}  # track id -> (label, confidence), filled once per person
frames = boxes_seen = 0
for result in detector.track(source, classes=[0], stream=True, persist=True, verbose=False):  # people only
    frames += 1
    if result.boxes.id is None:
        continue
    for track_id, (x1, y1, x2, y2) in zip(result.boxes.id.int().tolist(), result.boxes.xyxy.int().tolist()):
        boxes_seen += 1
        if track_id not in labels:  # first sighting: classify once, then reuse
            probs = classifier(result.orig_img[y1:y2, x1:x2], verbose=False)[0].probs
            labels[track_id] = (classifier.names[probs.top1], round(float(probs.top1conf), 2))

print(f"{frames} frames, {boxes_seen} person boxes, {len(labels)} classifier calls")
print(labels)

11 frames, 33 person boxes, 3 classifier calls
{1: ('basketball', 0.51), 2: ('maillot_(tights)', 0.14), 3: ('bulletproof_vest', 0.23)}

from collections import defaultdict

import numpy as np

from ultralytics import YOLO

def angle(a, b, c):
    """Angle at b, in degrees, formed by points a-b-c."""
    ba, bc = a - b, c - b
    return np.degrees(np.arccos(np.dot(ba, bc) / (np.linalg.norm(ba) * np.linalg.norm(bc))))

model = YOLO("yolo26n-pose.pt")
source = "https://github.com/ultralytics/assets/releases/download/v0.0.0/decelera_portrait_min.mov"
HIP, KNEE, ANKLE = 11, 13, 15  # left leg, COCO keypoint order
knee_angles = defaultdict(list)  # track id -> knee angle per frame

for result in model.track(source, stream=True, persist=True, verbose=False):
    if result.boxes.id is None:  # no confirmed tracks in this frame
        continue
    kpts = result.keypoints.cpu().numpy()
    for track_id, xy, conf in zip(result.boxes.id.int().tolist(), kpts.xy, kpts.conf):
        if conf[[HIP, KNEE, ANKLE]].min() > 0.5:  # skip occluded legs
            knee_angles[track_id].append(angle(xy[HIP], xy[KNEE], xy[ANKLE]))

for track_id, angles in sorted(knee_angles.items()):
    print(f"id {track_id}: {len(angles)} frames, left knee {min(angles):.0f}-{max(angles):.0f} deg")

id 1: 11 frames, left knee 170-176 deg
id 2: 11 frames, left knee 96-118 deg
id 3: 11 frames, left knee 177-180 deg