Update multi_video_app.py

multi_video_app.py

@@ -33,18 +33,18 @@ def save_to_csv(observations: List[Dict], output_dir: str = "outputs") -> str:
     return csv_file
 
 # Function to process a single video and return the observation data
-def process_single_video(video_path: str, sitting, hands, location, screen) -> Dict:
+def process_single_video(video_path: str, standing, hands, location, screen) -> Dict:
     video_name = os.path.basename(video_path)  # Extract video name from the path
     query = "Describe this video in detail and answer the questions"
     additional_info = []
-    if sitting:
-        additional_info.append("Is the subject in the video standing or sitting?")
+    if standing:
+        additional_info.append("Is the subject in the video standing or sitting?\n")
     if hands:
-        additional_info.append("Is the subject holding any object in their hands, if so the hands are not free else they are free?")
+        additional_info.append("Is the subject holding any object in their hands?\n")
     if location:
-        additional_info.append("Is the subject present indoors or outdoors?")
+        additional_info.append("Is the subject present indoors?\n")
     if screen:
-        additional_info.append("Is the subject interacting with a screen in the background by facing the screen?")
+        additional_info.append("Is the subject interacting with a screen in the background by facing the screen?\n")
     
     end_query = """Provide the results in <annotation> tags, where 0 indicates False, 1 indicates True, and None indicates that no information is present. Follow the below examples:
         <annotation>indoors: 0</annotation>
@@ -59,6 +59,7 @@ def process_single_video(video_path: str, sitting, hands, location, screen) -> D
     # Assuming your describe_video function handles the video processing
     final_response = describe_video(video_path, final_prompt)
 
+
     conditions = {
         'standing': (standing, 'standing: 1', 'standing: None'),
         'hands': (hands, 'hands.free: 1', 'hands.free: None'),
@@ -98,9 +99,9 @@ def gradio_interface(video_files, sitting, hands, location, screen):
 
 # Inputs
 video_files = gr.File(file_count="multiple", file_types=["video"], label="Upload multiple videos")
-sitting = gr.Checkbox(label="Sitting/Standing")
-hands = gr.Checkbox(label="Hands Free/Not Free")
-location = gr.Checkbox(label="Indoors/Outdoors")
+standing = gr.Checkbox(label="Standing")
+hands = gr.Checkbox(label="Hands Free")
+location = gr.Checkbox(label="Indoors")
 screen = gr.Checkbox(label="Screen Interaction")
 
 # Outputs