app.py

import gradio as gr
import torch
from PIL import Image
# Images
torch.hub.download_url_to_file('https://cdn.pixabay.com/photo/2016/06/15/01/11/soccer-1457988_1280.jpg', 'soccer.jpg')
torch.hub.download_url_to_file('https://cdn.pixabay.com/photo/2016/11/21/14/31/vw-bus-1845719_1280.jpg', 'bus.jpg')
# Model
model = torch.hub.load('ultralytics/yolov3', 'yolov3')  # or yolov3-spp, yolov3-tiny, custom
def yolo(im, size=1920):
    g = (size / max(im.size))  # gain
    im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize
    results = model(im)  # inference
    results.render()  # updates results.imgs with boxes and labels
    return Image.fromarray(results.imgs[0])
inputs = gr.inputs.Image(type='pil', label="Original Image")
outputs = gr.outputs.Image(type="pil", label="Output Image")
title = "YOLOv3"
description = "YOLOv3 Gradio demo for object detection. Upload an image or click an example image to use."
article = "<p style='text-align: center'>YOLOv3 is a family of compound-scaled object detection models trained on the COCO dataset, and includes simple functionality for Test Time Augmentation (TTA), model ensembling, hyperparameter evolution, and export to ONNX, CoreML and TFLite. <a href='https://github.com/ultralytics/yolov3' target='_blank'>Source code</a> |<a href='https://apps.apple.com/app/id1452689527' target='_blank'>iOS App</a></p>"
examples = [['soccer.jpg'], ['bus.jpg']]
gr.Interface(yolo, inputs, outputs, title=title, description=description, article=article, examples=examples, theme="huggingface").launch(
    debug=True)