app.py

import gradio as gr
import sahi
import torch
from ultralyticsplus import YOLO

# Download images

model_names = [
    "yolov8n-seg.pt",
    "yolov8s-seg.pt",
    "yolov8m-seg.pt",
    "yolov8l-seg.pt",
    "yolov8x-seg.pt",
]

current_model_name = "yolov8m-seg.pt"
model = YOLO(current_model_name)


def yolov8_inference(
    image: gr.Image = None,
    model_name: gr.Dropdown = None,
    image_size: gr.Slider = 640,
    conf_threshold: gr.Slider = 0.25,
    iou_threshold: gr.Slider = 0.45,
):
    """
    YOLOv8 inference function
    Args:
        image: Input image
        model_name: Name of the model
        image_size: Image size
        conf_threshold: Confidence threshold
        iou_threshold: IOU threshold
    Returns:
        Bounding box coordinates in xyxy format
    """
    global model
    global current_model_name
    if model_name != current_model_name:
        model = YOLO(model_name)
        current_model_name = model_name
    model.overrides["conf"] = conf_threshold
    model.overrides["iou"] = iou_threshold
    results = model.predict(image, imgsz=image_size)
    
    boxes1 = []
    for result in results:
        # Extract bounding boxes (xyxy format)
        for i,box in enumerate(result.boxes):
            boxes1.append(box.xyxy[0].tolist())
    return boxes1


inputs = [
    gr.Image(type="filepath", label="Input Image"),
    gr.Dropdown(
        model_names,
        value=current_model_name,
        label="Model type",
    ),
    gr.Slider(minimum=320, maximum=1280, value=640, step=32, label="Image Size"),
    gr.Slider(
        minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold"
    ),
    gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold"),
]

outputs = gr.JSON(label="Bounding Boxes (xyxy format)")
title = "YOLOv8 Bounding Box Extraction Demo"

demo_app = gr.Interface(
    fn=yolov8_inference,
    inputs=inputs,
    outputs=outputs,
    title=title,
    theme="default"
)
demo_app.queue().launch(debug=True)