app.py

import gradio as gr
import cv2
import numpy as np
from transformers import pipeline
import os
import torch
import torch.nn.functional as F
from torchvision import transforms
from torchvision.transforms import Compose
import spaces

title = "# Video Summarization using Timesformer Demo"
description = """ Author: Nguyen Hoai Nam."""
css = """
#img-display-container {
    max-height: 100vh;
    }
#img-display-input {
    max-height: 80vh;
    }
#img-display-output {
    max-height: 80vh;
    }
"""

with gr.Blocks(css=css) as demo:
    gr.Markdown(title)
    gr.Markdown(description)
    gr.Markdown("### Video Summarization demo")

    with gr.Row():
        input_video = gr.Video(label="Input Video")
        model_type = gr.Dropdown(["K-means", "Sum of Squared Difference 01", "Sum of Squared Difference 02"], type="value", label='Model Type')
    submit = gr.Button("Submit")
    processed_video = gr.Video(label="Summarized Video")

    def on_submit(uploaded_video,model_type):
        pass        
        # Process the video and get the path of the output video
        #output_video_path = make_video(uploaded_video,encoder=model_type)

        #return output_video_path
        
    submit.click(on_submit, inputs=[input_video, model_type], outputs=processed_video)

    example_files = os.listdir('assets/examples_video')
    example_files.sort()
    example_files = [os.path.join('assets/examples_video', filename) for filename in example_files]
    examples = gr.Examples(examples=example_files, inputs=[input_video], outputs=processed_video, fn=on_submit, cache_examples=True)

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