# Ackownledgement: https://huggingface.co/spaces/kadirnar/Yolov10/blob/main/app.py
# Thanks to @kadirnar

import gradio as gr
from ultralytics import YOLOv10
import cv2
import tempfile

def yolov10_inference(image, model_path, image_size, conf_threshold):
    model = YOLOv10(model_path)
    results = model.predict(source=image, imgsz=image_size, conf=conf_threshold)
    annotated_image = results[0].plot()
    return annotated_image[:, :, ::-1], None

def yolov10_inference_video(video, model_path, image_size, conf_threshold):
    model = YOLOv10(model_path)
    video_path = tempfile.mktemp(suffix=".mp4")
    with open(video_path, "wb") as f:
        with open(video, "rb") as g:
            f.write(g.read())

    cap = cv2.VideoCapture(video_path)
    fps = cap.get(cv2.CAP_PROP_FPS)
    frame_width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
    frame_height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))

    output_video_path = tempfile.mktemp(suffix=".mp4")
    out = cv2.VideoWriter(output_video_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (frame_width, frame_height))

    while cap.isOpened():
        ret, frame = cap.read()
        if not ret:
            break

        results = model.predict(source=frame, imgsz=image_size, conf=conf_threshold)
        annotated_frame = results[0].plot()
        out.write(annotated_frame)

    cap.release()
    out.release()
    
    return None, output_video_path

def app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                input_type = gr.Radio(
                    choices=["Image", "Video"],
                    value="Image",
                    label="Input Type",
                )
                image = gr.Image(type="pil", label="Image", visible=True)
                video = gr.Video(label="Video", visible=False)

                model_id = gr.Dropdown(
                    label="Model",
                    choices=[
                        "yolov10n.pt",
                        "yolov10s.pt",
                        "yolov10m.pt",
                        "yolov10b.pt",
                        "yolov10l.pt",
                        "yolov10x.pt",
                    ],
                    value="yolov10s.pt",
                )
                image_size = gr.Slider(
                    label="Image Size",
                    minimum=320,
                    maximum=1280,
                    step=32,
                    value=640,
                )
                conf_threshold = gr.Slider(
                    label="Confidence Threshold",
                    minimum=0.0,
                    maximum=1.0,
                    step=0.1,
                    value=0.25,
                )
                yolov10_infer = gr.Button(value="Detect Objects")

            with gr.Column():
                output_image = gr.Image(type="numpy", label="Annotated Image", visible=True)
                output_video = gr.Video(label="Annotated Video", visible=False)

        def update_visibility(input_type):
            image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
            video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)
            output_image = gr.update(visible=True) if input_type == "Image" else gr.update(visible=False)
            output_video = gr.update(visible=False) if input_type == "Image" else gr.update(visible=True)

            return image, video, output_image, output_video

        input_type.change(
            fn=update_visibility,
            inputs=[input_type],
            outputs=[image, video, output_image, output_video],
        )

        def run_inference(image, video, model_id, image_size, conf_threshold, input_type):
            if input_type == "Image":
                return yolov10_inference(image, model_id, image_size, conf_threshold)
            else:
                return yolov10_inference_video(video, model_id, image_size, conf_threshold)

        yolov10_infer.click(
            fn=run_inference,
            inputs=[image, video, model_id, image_size, conf_threshold, input_type],
            outputs=[output_image, output_video],
        )

        gr.Examples(
            examples=[
                [
                    "ultralytics/assets/bus.jpg",
                    "yolov10s.pt",
                    640,
                    0.25,
                ],
                [
                    "ultralytics/assets/zidane.jpg",
                    "yolov10s.pt",
                    640,
                    0.25,
                ],
            ],
            fn=yolov10_inference,
            inputs=[
                image,
                model_id,
                image_size,
                conf_threshold,
            ],
            outputs=[output_image],
            cache_examples=True,
        )

gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv10: Real-Time End-to-End Object Detection
    </h1>
    """)
    with gr.Row():
        with gr.Column():
            app()

gradio_app.launch(debug=True)