app.py

import gradio as gr
import torch
from PIL import ImageDraw
from transformers import AutoModelForObjectDetection, AutoImageProcessor


processor  = AutoImageProcessor.from_pretrained("tanukinet/hanko")
model      = AutoModelForObjectDetection.from_pretrained("tanukinet/hanko", ignore_mismatched_sizes=True,)


def object_detection(image):
    image = image.copy()
    inputs = processor(images=image, return_tensors="pt")
    outputs = model(**inputs)
    target_sizes = torch.tensor([image.size[::-1]])
    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.8)[0]
    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        box = [round(i, 2) for i in box.tolist()]
        print(
                f"Detected {model.config.id2label[label.item()]} with confidence "
                f"{round(score.item(), 3)} at location {box}"
        )
    draw = ImageDraw.Draw(image)
    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        box = [round(i, 2) for i in box.tolist()]
        x, y, x2, y2 = tuple(box)
        draw.rectangle((x, y, x2, y2), outline="red", width=1)
        draw.text((x, y), model.config.id2label[label.item()], fill="white")
    return image


demo = gr.Interface(
    object_detection,
    gr.Image(type="pil"),
    "image",
    examples=[
        "sample1.png",
        "sample2.png",
    ],
)

if __name__ == "__main__":
    demo.launch()