app.py

from huggingface_hub import hf_hub_download
from ultralytics import YOLO
from supervision import Detections
import cv2
import gradio as gr
from PIL import Image
import numpy as np

model_path = hf_hub_download(repo_id="arnabdhar/YOLOv8-Face-Detection", filename="model.pt")
model = YOLO(model_path)

def detect_faces(image):

    print(type(image))

    output = model(image)
    results = Detections.from_ultralytics(output[0])

    im = np.array(image)
    for i in results:
        im = cv2.rectangle(im, (int(i[0][0]),int(i[0][1])), (int(i[0][2]),int(i[0][3])), (255,0,0), 2)

    image_np = np.array(image)
    gray_image = cv2.cvtColor(image_np, cv2.COLOR_RGB2GRAY)
    
    face_cascade_face_1 = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_default.xml")
    face_cascade_face_2 = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_alt.xml")
    face_cascade_face_3 = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_frontalface_alt2.xml")

    faces1 = face_cascade_face_1.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(5, 5))
    faces2 = face_cascade_face_2.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(5, 5))
    faces3 = face_cascade_face_3.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(5, 5))
    
    if (len(faces1) >= len(faces2)) and (len(faces1) >= len(faces3)):
        faces = faces1
    elif len(faces2) >= len(faces3):
        faces = faces2
    else:
        faces = faces3

    face_cascade_eye = cv2.CascadeClassifier(cv2.data.haarcascades + "haarcascade_eye.xml")
    eyes = face_cascade_eye.detectMultiScale(gray_image, scaleFactor=1.1, minNeighbors=5, minSize=(5, 5))

    for (x, y, w, h) in faces:
        cv2.rectangle(image_np, (x, y), (x+w, y+h), (0, 255, 0), 2)
    for (x, y, w, h) in eyes:
        cv2.rectangle(image_np, (x, y), (x+w, y+h), (0, 0, 255), 2)

    return (image_np,im)

interface = gr.Interface(
    fn=detect_faces,
    inputs=gr.Image(label='Upload Image'),
    outputs=[gr.Image(label='Original'),gr.Image(label='Deep learning')],
    title="Face Detection Deep Learning",
    description="Upload an image, and the model will detect faces and draw bounding boxes around them.",
)
interface.launch()