اكتشاف الأجسام: YOLO وFaster-RCNN

class="tok-comment"># pip install ultralytics
from ultralytics import YOLO
import numpy as np
import cv2

class="tok-comment"># ── class="tok-num">1. Load pretrained YOLO v8 ────────────────────────────────────────────────
model = YOLO(class="tok-str">"yolov8n.pt")   class="tok-comment"># nano model (class="tok-num">3.2M params, fastest)
class="tok-comment"># Other sizes: yolov8s.pt, yolov8m.pt, yolov8l.pt, yolov8x.pt

class="tok-comment"># ── class="tok-num">2. Inference on a single image ────────────────────────────────────────────
results = model(class="tok-str">"path/to/image.jpg", conf=class="tok-num">0.25, iou=class="tok-num">0.5)

for r in results:
    boxes = r.boxes                  class="tok-comment"># Boxes object
    for box in boxes:
        x1, y1, x2, y2 = box.xyxy[class="tok-num">0].tolist()  class="tok-comment"># absolute pixel coords
        conf  = box.conf[class="tok-num">0].item()              class="tok-comment"># confidence score
        cls   = int(box.cls[class="tok-num">0].item())          class="tok-comment"># class index
        label = model.names[cls]
        print(fclass="tok-str">"{label}: {conf:.2f} at ({x1:.0f},{y1:.0f},{x2:.0f},{y2:.0f})")

class="tok-comment"># ── class="tok-num">3. Fine-tuning on custom dataset ─────────────────────────────────────────
class="tok-comment"># Dataset format: YOLO txt format
class="tok-comment"># data.yaml:
class="tok-comment">#   train: /path/to/train/images
class="tok-comment">#   val:   /path/to/val/images
class="tok-comment">#   nc: class="tok-num">3                       # number of classes
class="tok-comment">#   names: [class="tok-str">'cat', class="tok-str">'dog', class="tok-str">'car']

model = YOLO(class="tok-str">"yolov8s.pt")     class="tok-comment"># start from ImageNet pretrained
results = model.train(
    data=class="tok-str">"data.yaml",
    epochs=class="tok-num">50,
    imgsz=class="tok-num">640,
    batch=class="tok-num">16,
    lr0=class="tok-num">0.01,                   class="tok-comment"># initial learning rate
    lrf=class="tok-num">0.01,                   class="tok-comment"># final lr fraction
    augment=True,               class="tok-comment"># mosaic, flip, scale augmentation
    device=class="tok-num">0,                   class="tok-comment"># GPU class="tok-num">0
)
print(fclass="tok-str">"mAP50: {results.metrics.mAP50:.4f}")

class="tok-comment"># ── class="tok-num">4. IoU calculation from scratch ──────────────────────────────────────────
def iou(box1, box2):
    class="tok-str">"""box = [x1, y1, x2, y2]"""
    x1 = max(box1[class="tok-num">0], box2[class="tok-num">0]); y1 = max(box1[class="tok-num">1], box2[class="tok-num">1])
    x2 = min(box1[class="tok-num">2], box2[class="tok-num">2]); y2 = min(box1[class="tok-num">3], box2[class="tok-num">3])
    inter = max(class="tok-num">0, x2-x1) * max(class="tok-num">0, y2-y1)
    area1 = (box1[class="tok-num">2]-box1[class="tok-num">0]) * (box1[class="tok-num">3]-box1[class="tok-num">1])
    area2 = (box2[class="tok-num">2]-box2[class="tok-num">0]) * (box2[class="tok-num">3]-box2[class="tok-num">1])
    return inter / (area1 + area2 - inter + class="tok-num">1e-6)

gt   = [class="tok-num">100, class="tok-num">50, class="tok-num">250, class="tok-num">200]
pred = [class="tok-num">110, class="tok-num">60, class="tok-num">260, class="tok-num">210]
print(fclass="tok-str">"\nIoU = {iou(gt, pred):.4f}")

class="tok-comment"># ── class="tok-num">5. Manual NMS ─────────────────────────────────────────────────────────────
def nms(boxes, scores, iou_threshold=class="tok-num">0.5):
    class="tok-str">"""Boxes: (N,class="tok-num">4) xyxy, Scores: (N,)"""
    order = np.argsort(scores)[::-class="tok-num">1]
    keep  = []
    while len(order) > class="tok-num">0:
        i = order[class="tok-num">0]
        keep.append(i)
        ious = np.array([iou(boxes[i], boxes[j]) for j in order[class="tok-num">1:]])
        order = order[class="tok-num">1:][ious < iou_threshold]
    return keep

boxes  = np.array([[class="tok-num">100,class="tok-num">50,class="tok-num">250,class="tok-num">200],[class="tok-num">105,class="tok-num">55,class="tok-num">255,class="tok-num">205],[class="tok-num">200,class="tok-num">100,class="tok-num">350,class="tok-num">250]])
scores = np.array([class="tok-num">0.95, class="tok-num">0.87, class="tok-num">0.72])
kept   = nms(boxes, scores)
print(fclass="tok-str">"Kept boxes: {kept}")  class="tok-comment"># [class="tok-num">0, class="tok-num">2] — box class="tok-num">1 suppressed (overlaps with class="tok-num">0)