Update app.py

app.py

@@ -66,7 +66,7 @@ def process_video(video_file, question_parts):
     input = processor([prompt], videos=[video_clip], padding=True, return_tensors="pt").to(model.device)
 
     # Generate output
-    generate_kwargs = {"max_new_tokens": 500, "do_sample": False, "top_p": 0.9}
+    generate_kwargs = {"max_new_tokens": 3000, "do_sample": False, "top_p": 0.9}
     output = model.generate(**input, **generate_kwargs)
     generated_text = processor.batch_decode(output, skip_special_tokens=True)[0]
     
@@ -83,20 +83,21 @@ def process_videos(video_files, question):
 
 # Define Gradio interface for multiple videos
 def gradio_interface(videos, indoors_outdoors, standing_sitting, hands_free, interacting_screen):
-
-    question = "Is the subject in the video"
+    question = "For each question, analyze the given video carefully and base your answers on the observations made."
     if indoors_outdoors:
-        question += "present indoors or outdoors? "
+        question += "Consider the broader environmental context shown in the video’s background. Are there signs of an open-air space, like greenery, structures, or people passing by? If so, it’s an outdoor setting. If the setting looks confined with furniture, walls, or home decorations, it’s an indoor environment."
     if standing_sitting:
-        question += "standing or sitting? "
+        question += "Evaluate the subject’s body posture and movement within the video. Are they standing upright with both feet planted firmly on the ground? If so, they are standing."
     if hands_free:
-        question += "hands free or not? "
+        question += "Examine the subject’s right and left hands in the video to check if they are holding anything like a microphone, book, paper(White color), object, or any electronic device, try segmentations and decide if the hands are free or not."
     if interacting_screen:
-        question += "interacting with any screen in the background?"
-    
+        question += "Assess the surroundings behind the subject in the video. Do they seem to interact with any visible screens, such as laptops, TVs, or digital billboards? If yes, then they are interacting with a screen. If not, they are not interacting with a screen."
+    question_prefix = "By taking these factors into account when watching the video, please answer the questions accurately."
+    question = question + question_prefix 
     answers = process_videos(videos, question)
     return answers
 
+
 iface = gr.Interface(
     fn=gradio_interface,
     inputs=[
@@ -111,5 +112,6 @@ iface = gr.Interface(
     description="Upload multiple videos and select questions to get answers."
 )
 
+    
 if __name__ == "__main__":
     iface.launch(debug=True)