Update app.py

app.py

@@ -15,15 +15,17 @@ def process_and_show_completion(video_input_path, anomaly_threshold_input, fps,
 
         if isinstance(results[0], str) and results[0].startswith("Error"):
             print(f"Error occurred: {results[0]}")
-            return [results[0]] + [None] * 17
-
-        exec_time, results_summary, df, mse_embeddings, mse_posture, \
-            mse_plot_embeddings, mse_histogram_embeddings, \
-            mse_plot_posture, mse_histogram_posture, \
-            mse_heatmap_embeddings, mse_heatmap_posture, \
-            face_samples_frequent, \
-            anomaly_faces_embeddings, anomaly_frames_posture_images, \
-            aligned_faces_folder, frames_folder = results
+            return [results[0]] + [None] * 21  # Adjust this number based on your total outputs
+
+        (exec_time, results_summary, df, mse_embeddings, mse_posture,
+         mse_plot_embeddings, mse_histogram_embeddings,
+         mse_plot_posture, mse_histogram_posture,
+         mse_heatmap_embeddings, mse_heatmap_posture,
+         face_samples_frequent,
+         anomaly_faces_embeddings, anomaly_frames_posture_images,
+         aligned_faces_folder, frames_folder,
+         mse_voice, mse_plot_voice, mse_histogram_voice, mse_heatmap_voice,
+         anomaly_segments_voice) = results
 
         anomaly_faces_embeddings_pil = [Image.fromarray(face) for face in anomaly_faces_embeddings]
         anomaly_frames_posture_pil = [Image.fromarray(frame) for frame in anomaly_frames_posture_images]
@@ -40,6 +42,7 @@ def process_and_show_completion(video_input_path, anomaly_threshold_input, fps,
             face_samples_frequent,
             aligned_faces_folder, frames_folder,
             mse_embeddings, mse_posture,
+            mse_plot_voice, mse_histogram_voice, mse_heatmap_voice, anomaly_segments_voice
         ]
 
         return output
@@ -49,14 +52,14 @@ def process_and_show_completion(video_input_path, anomaly_threshold_input, fps,
         print(error_message)
         import traceback
         traceback.print_exc()
-        return [error_message] + [None] * 17
+        return [error_message] + [None] * 21  # Adjust this number based on your total outputs
 
 with gr.Blocks() as iface:
     gr.Markdown("""
     # Multimodal Behavioral Anomalies Detection
 
-    The purpose of this tool is to detect anomalies in facial expressions and body language over the timeline of a video.
-    It extracts faces and postures from video frames, detects unique facial features and body postures, and analyzes them to identify anomalies using time series analysis, specifically utilizing a variational autoencoder (VAE) approach.
+    This tool detects anomalies in facial expressions, body language, and voice over the timeline of a video.
+    It extracts faces, postures, and voice features from video frames, and analyzes them to identify anomalies using time series analysis and a variational autoencoder (VAE) approach.
     """)
 
     with gr.Row():
@@ -76,8 +79,7 @@ with gr.Blocks() as iface:
             mse_features_hist = gr.Plot(label="MSE Distribution: Facial Features")
             mse_features_heatmap = gr.Plot(label="MSE Heatmap: Facial Features")
             anomaly_frames_features = gr.Gallery(label="Anomaly Frames (Facial Features)", columns=6, rows=2, height="auto")
-            face_samples_most_frequent = gr.Gallery(label="Other Samples", columns=10, rows=2, height="auto")
-            #face_samples_others = gr.Gallery(label="Other Samples", columns=6, rows=1, height="auto")
+            face_samples_most_frequent = gr.Gallery(label="Most Frequent Person Samples", columns=10, rows=2, height="auto")
 
         with gr.Tab("Body Posture"):
             mse_posture_plot = gr.Plot(label="MSE: Body Posture")
@@ -91,7 +93,6 @@ with gr.Blocks() as iface:
             mse_voice_heatmap = gr.Plot(label="MSE Heatmap: Voice")
             anomaly_segments_voice = gr.Audio(label="Anomaly Voice Segments", type="filepath")
 
-
     df_store = gr.State()
     mse_features_store = gr.State()
     mse_posture_store = gr.State()
@@ -109,11 +110,11 @@ with gr.Blocks() as iface:
             mse_features_plot, mse_posture_plot,
             mse_features_hist, mse_posture_hist,
             mse_features_heatmap, mse_posture_heatmap,
-            mse_voice_plot, mse_voice_hist, mse_voice_heatmap, anomaly_segments_voice,
             anomaly_frames_features, anomaly_frames_posture,
             face_samples_most_frequent,
             aligned_faces_folder_store, frames_folder_store,
-            mse_heatmap_embeddings_store, mse_heatmap_posture_store
+            mse_heatmap_embeddings_store, mse_heatmap_posture_store,
+            mse_voice_plot, mse_voice_hist, mse_voice_heatmap, anomaly_segments_voice
         ]
     ).then(
         lambda: gr.Group(visible=True),