app.py

from huggingface_hub import snapshot_download
from insightface.app import FaceAnalysis
import numpy as np
import cv2
import gradio as gr

# Download face encoder
snapshot_download(
    "fal/AuraFace-v1",
    local_dir="models/auraface",
)

app = FaceAnalysis(
    name="auraface",
    providers=["CUDAExecutionProvider", "CPUExecutionProvider"],
    root=".",
)

app.prepare(ctx_id=0, det_size=(640, 640))

def process_image_by_bbox_larger(input_image, bbox_xyxy, min_bbox_ratio=0.2):
    """
    Process an image based on a bounding box, cropping and resizing as necessary.
    Parameters:
    - input_image: PIL Image object.
    - bbox_xyxy: Tuple (x1, y1, x2, y2) representing the bounding box coordinates.
    Returns:
    - A processed image cropped and resized to 1024x1024 if the bounding box is valid,
      or None if the bounding box does not meet the required size criteria.
    """
    # Constants
    target_size = 1024
    # min_bbox_ratio = 0.2  # Bounding box should be at least 20% of the crop

    # Extract bounding box coordinates
    x1, y1, x2, y2 = bbox_xyxy
    bbox_w = x2 - x1
    bbox_h = y2 - y1

    # Calculate the area of the bounding box
    bbox_area = bbox_w * bbox_h

    # Start with the smallest square crop that allows bbox to be at least 20% of the crop area
    crop_size = max(bbox_w, bbox_h)
    initial_crop_area = crop_size * crop_size
    while (bbox_area / initial_crop_area) < min_bbox_ratio:
        crop_size += 10  # Gradually increase until bbox is at least 20% of the area
        initial_crop_area = crop_size * crop_size

    # Once the minimum condition is satisfied, try to expand the crop further
    max_possible_crop_size = min(input_image.width, input_image.height)
    while crop_size < max_possible_crop_size:
        # Calculate a potential new area
        new_crop_size = crop_size + 10
        new_crop_area = new_crop_size * new_crop_size
        if (bbox_area / new_crop_area) < min_bbox_ratio:
            break  # Stop if expanding further violates the 20% rule
        crop_size = new_crop_size

    # Determine the center of the bounding box
    center_x = (x1 + x2) // 2
    center_y = (y1 + y2) // 2

    # Calculate the crop coordinates centered around the bounding box
    crop_x1 = max(0, center_x - crop_size // 2)
    crop_y1 = max(0, center_y - crop_size // 2)
    crop_x2 = min(input_image.width, crop_x1 + crop_size)
    crop_y2 = min(input_image.height, crop_y1 + crop_size)

    # Ensure the crop is square, adjust if it goes out of image bounds
    if crop_x2 - crop_x1 != crop_y2 - crop_y1:
        side_length = min(crop_x2 - crop_x1, crop_y2 - crop_y1)
        crop_x2 = crop_x1 + side_length
        crop_y2 = crop_y1 + side_length

    # Crop the image
    cropped_image = input_image.crop((crop_x1, crop_y1, crop_x2, crop_y2))

    # Resize the cropped image to 1024x1024
    resized_image = cropped_image.resize((target_size, target_size), Image.LANCZOS)

    return resized_image

def calc_emb_cropped(image, app, min_bbox_ratio=0.2):
    face_image = image.copy()

    face_info = app.get(cv2.cvtColor(np.array(face_image), cv2.COLOR_RGB2BGR))

    face_info = face_info[0]

    #print(face_info)

    cropped_face_image = process_image_by_bbox_larger(face_image, face_info["bbox"], min_bbox_ratio=min_bbox_ratio)

    return cropped_face_image

def get_embedding(image):
    face_image = image.copy()

    face_info = app.get(cv2.cvtColor(np.array(face_image), cv2.COLOR_RGB2BGR))
    
    # 获取人脸嵌入
    #face_info = app.get(cv2_image)
    if len(face_info) > 0:
        return face_info[0].normed_embedding
    else:
        return None

'''
from PIL import Image 
im0 = Image.open("Unreal_5_render_of_a_handsome_man_gentle_snowfall_at_dusk_a_bustling_marketplace_in_the_background.png")
calc_emb_cropped(im0, app)
get_embedding(im0)
'''


def calculate_similarity(image1, image2):
    # 获取两张图片的嵌入
    embedding1 = get_embedding(image1)
    embedding2 = get_embedding(image2)
    
    if embedding1 is not None and embedding2 is not None:
        # 计算余弦相似度
        similarity = np.dot(embedding1, embedding2) / (np.linalg.norm(embedding1) * np.linalg.norm(embedding2))
        return f"图片相似度: {similarity:.4f}"
    else:
        return "无法检测到人脸或计算相似度"

# 创建Gradio界面
iface = gr.Interface(
    fn=calculate_similarity,
    inputs=[gr.Image(type="pil"), gr.Image(type="pil")],
    outputs="text",
    title="图片相似度计算",
    description="上传两张图片，计算它们的相似度。"
)

# 启动Gradio应用
iface.launch(share = True)