app.py

import gradio as gr
import torch
from sahi.prediction import ObjectPrediction
from sahi.utils.cv import visualize_object_predictions, read_image
from ultralyticsplus import YOLO, render_result

image_path = [
    ['test/web form.jpg', 'foduucom/web-form-ui-field-detection', 640, 0.25, 0.45],
    ['test/web form2.jpg', 'foduucom/web-form-ui-field-detection', 640, 0.25, 0.45]
]


def yolov8_inference(
    image: gr.inputs.Image = None,
    model_path: gr.inputs.Dropdown = None,
    image_size: gr.inputs.Slider = 640,
    conf_threshold: gr.inputs.Slider = 0.25,
    iou_threshold: gr.inputs.Slider = 0.45,
):
    """
    YOLOv8 inference function
    Args:
        image: Input image
        model_path: Path to the model
        image_size: Image size
        conf_threshold: Confidence threshold
        iou_threshold: IOU threshold
    Returns:
        Rendered image
    """
    model = YOLO(model_path)
    model.overrides['conf'] = conf_threshold
    model.overrides['iou']= iou_threshold
    model.overrides['agnostic_nms'] = False  # NMS class-agnostic
    model.overrides['max_det'] = 1000 
    image = read_image(image)
    results = model.predict(image)
    render = render_result(model=model, image=image, result=results[0])
    
    return render
        

inputs = [
    gr.inputs.Image(type="filepath", label="Input Image"),
    gr.inputs.Dropdown(["foduucom/web-form-ui-field-detection"], 
                       default="foduucom/web-form-ui-field-detection", label="Model"),
    gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"),
    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold"),
]

outputs = gr.outputs.Image(type="filepath", label="Output Image")
title = "Ui form : web form ui field Detection in Images"

interface_image = gr.Interface(
    fn=yolov8_inference,
    inputs=inputs,
    outputs=outputs,
    title=title,
    examples=image_path,
    cache_examples=False,
    theme='huggingface'
)

gr.TabbedInterface(
    [interface_image],
    tab_names=['Image inference']
).queue().launch()