Update app.py

app.py

@@ -1,5 +1,5 @@
 import gradio as gr
-from transformers import pipeline
+from transformers import AutoModelForVideoClassification, AutoTokenizer, VideoClassificationPipeline
 import cv2  # OpenCV for video processing
 
 # Model ID for video classification (UCF101 subset)
@@ -9,11 +9,19 @@ def analyze_video(video):
     # Extract key frames from the video using OpenCV
     frames = extract_key_frames(video)
     
+    # Load model and tokenizer manually
+    model = AutoModelForVideoClassification.from_pretrained(model_id)
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+    # Create the pipeline
+    classifier = VideoClassificationPipeline(model=model, tokenizer=tokenizer, device=-1)
+    
     # Analyze key frames using video classification model
     results = []
-    classifier = pipeline("video-classification", model=model_id)
     for frame in frames:
-        predictions = classifier(images=frame)  # Assuming model outputs probabilities
+        # OpenCV uses BGR, convert to RGB for the model
+        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        predictions = classifier(images=[frame_rgb])  # Assuming model outputs probabilities
         # Analyze predictions for insights related to the play
         result = analyze_predictions_ucf101(predictions)
         results.append(result)