app_caption.py

#!/usr/bin/env python

from __future__ import annotations

import os
import pathlib
import gradio as gr

from prismer_model import Model


def create_demo():
    model = Model()
    model.mode = 'caption'
    with gr.Row():
        with gr.Column():
            image = gr.Image(label='Input', type='filepath')
            model_name = gr.Dropdown(label='Model', choices=['Prismer-Base', 'Prismer-Large'], value='Prismer-Base')
            run_button = gr.Button('Run')
        with gr.Column(scale=1.5):
            caption = gr.Text(label='Model Prediction')
            with gr.Row():
                depth = gr.Image(label='Depth')
                edge = gr.Image(label='Edge')
                normals = gr.Image(label='Normals')
            with gr.Row():
                segmentation = gr.Image(label='Segmentation')
                object_detection = gr.Image(label='Object Detection')
                ocr = gr.Image(label='OCR Detection')

    inputs = [image, model_name]
    outputs = [caption, depth, edge, normals, segmentation, object_detection, ocr]

    paths = sorted(pathlib.Path('prismer/images').glob('*'))
    examples = [[path.as_posix(), 'Prismer-Base'] for path in paths]
    gr.Examples(examples=examples,
                inputs=inputs,
                outputs=outputs,
                fn=model.run_caption,
                cache_examples=os.getenv('SYSTEM') == 'spaces')

    run_button.click(fn=model.run_caption, inputs=inputs, outputs=outputs)


if __name__ == '__main__':
    demo = create_demo()
    demo.queue().launch()