YOLO Face Person Detector EU AI Act Compliance Profile

YOLOv8x Face & Person Detector

Model Description

This model is a fine-tuned version of YOLOv8x specialized in detecting two specific classes: Face and Person.

It has been trained on a large-scale proprietary dataset consisting of approximately 150,000 images. The high capacity of the YOLOv8x architecture combined with a diverse proprietary dataset ensures high accuracy and robustness in various scenarios.

How to Use

Installation

pip install ultralytics==8.1.0 torch==2.5.1 transformers huggingface_hub

1. Use with transformers

You can load the model using the Hugging Face transformers library by enabling custom code execution.

from transformers import AutoModel
from PIL import Image
import torch

# 1. Load model with trust_remote_code=True
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = AutoModel.from_pretrained(
    "iitolstykh/YOLO-Face-Person-Detector", 
    trust_remote_code=True,
    dtype=torch_dtype,
).to(device)

# 2. Load image (You can use URL, PIL.Image or np.ndarray)
image = Image.open("path/to/your/image.jpg")
# image = cv2.imread("path/to/your/image.jpg")

# 3. Perform inference
results = model(image, conf=0.4, iou=0.7)[0]

# 4. Process results
print("Found objects:", [results.names[int(det.cls)] for det in results.boxes])
print("Boxes:", results.boxes)
# render_result(model=model.yolo, image=image, result=results).show()

2. Use with ultralytics

If you

Your obligations as a YOLO Face Person Detector deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library