app.py

import gradio as gr
import spaces
from huggingface_hub import hf_hub_download


# def download_models(model_id):
#     hf_hub_download("SakshiRathi77/void-space-detection/weights", filename=f"{model_id}", local_dir=f"./")
#     return f"./{model_id}"


def yolov9_inference(img_path, model_id, image_size, conf_threshold, iou_threshold):
    """
    Load a YOLOv9 model, configure it, perform inference on an image, and optionally adjust 
    the input size and apply test time augmentation.
    
    :param model_path: Path to the YOLOv9 model file.
    :param conf_threshold: Confidence threshold for NMS.
    :param iou_threshold: IoU threshold for NMS.
    :param img_path: Path to the image file.
    :param size: Optional, input size for inference.
    :return: A tuple containing the detections (boxes, scores, categories) and the results object for further actions like displaying.
    """
    # Import YOLOv9
    import yolov9
    
    # Load the model
    # model_path = download_models()
    model = yolov9.load(best.pt, device="cuda:0")
    
    # Set model parameters
    model.conf = conf_threshold
    model.iou = iou_threshold
    
    # Perform inference
    results = model(img_path, size=image_size)

    # Optionally, show detection bounding boxes on image
    output = results.render()
    
    return output[0]


def app():
    with gr.Blocks():
        with gr.Row():
            with gr.Column():
                img_path = gr.Image(type="filepath", label="Image")
                model_path = "best.pt"
                image_size = gr.Slider(
                    label="Image Size",
                    minimum=320,
                    maximum=1280,
                    step=32,
                    value=640,
                )
                conf_threshold = gr.Slider(
                    label="Confidence Threshold",
                    minimum=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.4,
                )
                iou_threshold = gr.Slider(
                    label="IoU Threshold",
                    minimum=0.1,
                    maximum=1.0,
                    step=0.1,
                    value=0.5,
                )
                yolov9_infer = gr.Button(value="Inference")

            with gr.Column():
                output_numpy = gr.Image(type="numpy",label="Output")

        yolov9_infer.click(
            fn=yolov9_inference,
            inputs=[
                img_path,
                model_path,
                image_size,
                conf_threshold,
                iou_threshold,
            ],
            outputs=[output_numpy],
        )
        
  


gradio_app = gr.Blocks()
with gradio_app:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information
    </h1>
    """)
    gr.HTML(
        """
        <h3 style='text-align: center'>
        Follow me for more!
        </h3>
        """)
    with gr.Row():
        with gr.Column():
            app()

gradio_app.launch(debug=True)

# make sure you have the following dependencies
# import gradio as gr
# import torch
# from torchvision import transforms
# from PIL import Image

# # Load the YOLOv9 model
# model_path = "best.pt"  # Replace with the path to your YOLOv9 model
# model = torch.load(model_path)

# # Define preprocessing transforms
# preprocess = transforms.Compose([
#     transforms.Resize((640, 640)),  # Resize image to model input size
#     transforms.ToTensor(),           # Convert image to tensor
# ])

# # Define a function to perform inference
# def detect_void(image):
#     # Preprocess the input image
#     image = Image.fromarray(image)
#     image = preprocess(image).unsqueeze(0)  # Add batch dimension

#     # Perform inference
#     with torch.no_grad():
#         output = model(image)

#     # Post-process the output if needed
#     # For example, draw bounding boxes on the image

#     # Convert the image back to numpy array
#     # and return the result
#     return output.squeeze().numpy()

# # Define Gradio interface components
# input_image = gr.inputs.Image(shape=(640, 640), label="Input Image")
# output_image = gr.outputs.Image(label="Output Image")

# # Create Gradio interface
# gr.Interface(fn=detect_void, inputs=input_image, outputs=output_image, title="Void Detection App").launch()