Add application file

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.git/assets/Jumps.mp4 filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,52 @@
+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()