تحميل YOLOv5 من PyTorch Hub#

pip install -r https://raw.githubusercontent.com/ultralytics/yolov5/master/requirements.txt

import torch

# Model
model = torch.hub.load("ultralytics/yolov5", "yolov5s")

# Image
im = "https://ultralytics.com/images/zidane.jpg"

# Inference
results = model(im)

results.pandas().xyxy[0]
# xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 1  433.50  433.50   517.5  714.5    0.687988     27     tie
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie

import cv2
import torch
from PIL import Image

# Model
model = torch.hub.load("ultralytics/yolov5", "yolov5s")

# Images
for f in "zidane.jpg", "bus.jpg":
    torch.hub.download_url_to_file(f"https://ultralytics.com/images/{f}", f)  # download 2 images
im1 = Image.open("zidane.jpg")  # PIL image
im2 = cv2.imread("bus.jpg")[..., ::-1]  # OpenCV image (BGR to RGB)

# Inference
results = model([im1, im2], size=640)  # batch of images

# Results
results.print()
results.save()  # or .show()

results.xyxy[0]  # im1 predictions (tensor)
results.pandas().xyxy[0]  # im1 predictions (pandas)
#      xmin    ymin    xmax   ymax  confidence  class    name
# 0  749.50   43.50  1148.0  704.5    0.874023      0  person
# 1  433.50  433.50   517.5  714.5    0.687988     27     tie
# 2  114.75  195.75  1095.0  708.0    0.624512      0  person
# 3  986.00  304.00  1028.0  420.0    0.286865     27     tie

model.conf = 0.25  # ⁨عتبة ثقة NMS⁩
model.iou = 0.45  # ⁨عتبة IoU لـ NMS⁩
model.agnostic = False  # ⁨NMS دون اعتبار للفئة⁩
model.multi_label = False  # ⁨تسميات متعددة لكل صندوق في NMS⁩
model.classes = None  # ⁨(قائمة اختيارية) التصفية حسب الفئة، مثل = [0, 15, 16] للأشخاص والقطط والكلاب في COCO⁩
model.max_det = 1000  # ⁨الحد الأقصى لعدد الاكتشافات لكل صورة⁩
model.amp = False  # ⁨الاستدلال بدقة مختلطة تلقائية (AMP)⁩

results = model(im, size=320)  # ⁨حجم استدلال مخصص⁩

model.cpu()  # CPU
model.cuda()  # GPU
model.to(device)  # ⁨أي device=torch.device⁩(0)

model = torch.hub.load("ultralytics/yolov5", "yolov5s", device="cpu")  # ⁨التحميل على CPU⁩

model = torch.hub.load("ultralytics/yolov5", "yolov5s", _verbose=False)  # ⁨التحميل بصمت⁩

model = torch.hub.load("ultralytics/yolov5", "yolov5s", channels=4)

model = torch.hub.load("ultralytics/yolov5", "yolov5s", classes=10)

model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True)  # ⁨فرض إعادة التحميل⁩

import torch
from PIL import ImageGrab

# Model
model = torch.hub.load("ultralytics/yolov5", "yolov5s")

# Image
im = ImageGrab.grab()  # ⁨التقاط لقطة شاشة⁩

# Inference
results = model(im)

import threading

import torch

def run(model, im):
    """Performs inference on an image using a given model and saves the output; model must support `.save()` method."""
    results = model(im)
    results.save()

# Models
model0 = torch.hub.load("ultralytics/yolov5", "yolov5s", device=0)
model1 = torch.hub.load("ultralytics/yolov5", "yolov5s", device=1)

# Inference
threading.Thread(target=run, args=[model0, "https://ultralytics.com/images/zidane.jpg"], daemon=True).start()
threading.Thread(target=run, args=[model1, "https://ultralytics.com/images/bus.jpg"], daemon=True).start()

import torch

model = torch.hub.load("ultralytics/yolov5", "yolov5s", autoshape=False)  # ⁨تحميل نموذج مدرّب مسبقًا⁩
model = torch.hub.load("ultralytics/yolov5", "yolov5s", autoshape=False, pretrained=False)  # ⁨تحميل نموذج من البداية⁩

import base64
from io import BytesIO

from PIL import Image

results = model(im)  # inference

results.ims  # ⁨مصفوفة الصور الأصلية (على هيئة مصفوفة np) الممررة إلى النموذج للاستدلال⁩
results.render()  # ⁨يحدّث results.ims بالمربعات والتسميات⁩
for im in results.ims:
    buffered = BytesIO()
    im_base64 = Image.fromarray(im)
    im_base64.save(buffered, format="JPEG")
    print(base64.b64encode(buffered.getvalue()).decode("utf-8"))  # ⁨صورة مرمّزة بـ base64 تتضمن النتائج⁩

results = model(im)  # inference
crops = results.crop(save=True)  # ⁨قاموس الاكتشافات المقصوصة⁩

results = model(im)  # inference
results.pandas().xyxy[0]  # ⁨إطار بيانات Pandas⁩

results = model(im)  # inference
results.pandas().xyxy[0].sort_values("xmin")  # ⁨مرتبة من اليسار إلى اليمين⁩

results = model(im)  # inference
results.pandas().xyxy[0].to_json(orient="records")  # ⁨تنبؤات JSON للصورة1⁩

import torch

model = torch.hub.load("ultralytics/yolov5", "custom", path="path/to/best.pt")  # ⁨نموذج محلي⁩
model = torch.hub.load("path/to/yolov5", "custom", path="path/to/best.pt", source="local")  # ⁨مستودع محلي⁩

import torch

model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s.pt")  # PyTorch
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s.torchscript")  # TorchScript
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s.onnx")  # ONNX
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s_openvino_model/")  # OpenVINO
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s.engine")  # TensorRT
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s.mlpackage")  # ⁨CoreML (لـ macOS فقط)⁩
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s.tflite")  # TFLite
model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s_paddle_model/")  # PaddlePaddle