app.py

from __future__ import annotations
import pathlib
import cv2
import gradio as gr
import huggingface_hub
import insightface
import numpy as np
import onnxruntime as ort
from PIL import Image

TITLE = "insightface Person Detection"
DESCRIPTION = "https://github.com/deepinsight/insightface/tree/master/examples/person_detection"


def load_model():
    path = huggingface_hub.hf_hub_download("public-data/insightface", "models/scrfd_person_2.5g.onnx")
    options = ort.SessionOptions()
    options.intra_op_num_threads = 8
    options.inter_op_num_threads = 8
    session = ort.InferenceSession(
        path, sess_options=options, providers=["CPUExecutionProvider"]
    )
    model = insightface.model_zoo.retinaface.RetinaFace(model_file=path, session=session)
    return model


def detect_person(
    img: np.ndarray, detector: insightface.model_zoo.retinaface.RetinaFace
) -> tuple[np.ndarray, np.ndarray]:
    bboxes, kpss = detector.detect(img)
    bboxes = np.round(bboxes[:, :4]).astype(int)
    kpss = np.round(kpss).astype(int)
    kpss[:, :, 0] = np.clip(kpss[:, :, 0], 0, img.shape[1])
    kpss[:, :, 1] = np.clip(kpss[:, :, 1], 0, img.shape[0])
    vbboxes = bboxes.copy()
    vbboxes[:, 0] = kpss[:, 0, 0]
    vbboxes[:, 1] = kpss[:, 0, 1]
    vbboxes[:, 2] = kpss[:, 4, 0]
    vbboxes[:, 3] = kpss[:, 4, 1]
    return bboxes, vbboxes


def visualize(image: np.ndarray, bboxes: np.ndarray, vbboxes: np.ndarray) -> np.ndarray:
    res = image.copy()
    for i in range(bboxes.shape[0]):
        bbox = bboxes[i]
        vbbox = vbboxes[i]
        x1, y1, x2, y2 = bbox
        vx1, vy1, vx2, vy2 = vbbox
        cv2.rectangle(res, (x1, y1), (x2, y2), (0, 255,