import spaces
import gradio as gr
from transformers import pipeline

pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

@spaces.GPU
def predict(input_img):
    predictions = pipeline(input_img)
    return input_img, {p["label"]: p["score"] for p in predictions}

_HEADER_ = '''
<h2>Toon3D: Seeing Cartoons from a New Perspective</h2>
Toon3D lifts cartoons into 3D via aligning and warping backprojected monocular depth predictions.<br>
Project page @ <a href='https://toon3d.studio/' target='_blank'>https://toon3d.studio/</a>

**Important Notes:**
- TODO 1
- TODO 2
'''

def check_input_images(input_images):
    if input_images is None:
        raise gr.Error("No images uploaded!")
    
def process_images(input_images):

    for image in input_images:
        print(image)

    return input_images

gradio_app = gr.Interface(
    predict,
    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
    title="Toon3D",
)

with gr.Blocks() as demo:
    gr.Markdown(_HEADER_)
    with gr.Row(variant="panel"):
        with gr.Column():
            with gr.Row():
                input_images = gr.File(label="Upload Images", file_count="multiple", file_types=[".jpg", "jpeg", "png"])
            with gr.Row():
                process_data_button = gr.Button("Process Data", elem_id="process_data", variant="primary")
            with gr.Row():
                processed_data_zip = gr.File(label="Processed Data", file_count="single", file_types=[".zip"])
        with gr.Column():
            with gr.Row():
                labeled_data = gr.File(label="Labeled Points", file_count="single", file_types=[".json"])



# mv_images = gr.State()

    process_data_button.click(fn=check_input_images, inputs=[input_images]).success(
        fn=process_images,
        inputs=[input_images],
        outputs=[processed_data_zip],
    )

if __name__ == "__main__":
    demo.launch()