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


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(f'{model_path}.pt')
    # set model parameters
    model.overrides['conf'] = conf_threshold  # NMS confidence threshold
    model.overrides['iou'] = iou_threshold  # NMS IoU threshold
    model.overrides['agnostic_nms'] = False  # NMS class-agnostic
    model.overrides['max_det'] = 1000  # maximum number of detections per image
    results = model.predict(image, imgsz=image_size, return_outputs=True)
    object_prediction_list = []
    for _, image_results in enumerate(results):
        if len(image_results)!=0:
            image_predictions_in_xyxy_format = image_results['det']
            for pred in image_predictions_in_xyxy_format:
                x1, y1, x2, y2 = (
                    int(pred[0]),
                    int(pred[1]),
                    int(pred[2]),
                    int(pred[3]),
                )
                bbox = [x1, y1, x2, y2]
                score = pred[4]
                category_name = model.model.names[int(pred[5])]
                category_id = pred[5]
                object_prediction = ObjectPrediction(
                    bbox=bbox,
                    category_id=int(category_id),
                    score=score,
                    category_name=category_name,
                )
                object_prediction_list.append(object_prediction)

    image = read_image(image)
    output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
    return output_image['image']
        

inputs = [
    gr.inputs.Image(type="filepath", label="Input Image"),
    gr.inputs.Dropdown(["yolov8n", "yolov8m", "yolov8l", "yolov8x"], 
                       default="yolov8m", 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 = "State-of-the-Art YOLO Models for Object detection"

# examples = [['demo_01.jpg', 'yolov8n', 640, 0.25, 0.45], ['demo_02.jpg', 'yolov8l', 640, 0.25, 0.45], ['demo_03.jpg', 'yolov8x', 1280, 0.25, 0.45]]
demo_app = gr.Interface(
    fn=yolov8_inference,
    inputs=inputs,
    outputs=outputs,
    title=title,
    examples=examples,
    cache_examples=True,
    theme='huggingface',
)
demo_app.launch(debug=True, enable_queue=True)