Fixing an Inference App Using Hugging Face Spaces and a YOLOv5 Model (Trained on NDL-DocL Dataset)

import gradio as gr
from PIL import Image
import yolov5
import json

model = yolov5.load("nakamura196/yolov5-ndl-layout")

def yolo(im):

    results = model(im)  # inference

    df = results.pandas().xyxy[0].to_json(orient="records")
    res = json.loads(df)

    im_with_boxes = results.render()[0]  # results.render() returns a list of images

    # Convert the numpy array back to an image
    output_image = Image.fromarray(im_with_boxes)

    return [
        output_image,
        res
    ]


inputs = gr.Image(type='pil', label="Original Image")
outputs = [
    gr.Image(type="pil", label="Output Image"),
    gr.JSON()
]

title = "YOLOv5 NDL-DocL Datasets"
description = "YOLOv5 NDL-DocL Datasets Gradio demo for object detection. Upload an image or click an example image to use."
article = "<p style='text-align: center'>YOLOv5 NDL-DocL Datasets is an object detection model trained on the <a href=\"https://github.com/ndl-lab/layout-dataset\">NDL-DocL Datasets</a>.</p>"

examples = [
    ['『源氏物語』(東京大学総合図書館所蔵).jpg'],
    ['『源氏物語』(京都大学所蔵).jpg'],
    ['『平家物語』(国文学研究資料館提供).jpg']
]
demo = gr.Interface(yolo, inputs, outputs, title=title, description=description, article=article, examples=examples)

demo.launch(share=False)