Update app.py

app.py

@@ -1,33 +1,40 @@
 import gradio as gr
-import cv2
 import numpy as np
+from PIL import Image
+import io
+from huggingface_hub import hf_hub_download
+
+# Download the model
+model_path = hf_hub_download("dima806/deepfake_vs_real_image_detection", "model.pkl")
+
+# Load the model (you might need to adjust this based on how the model is saved)
+import pickle
+with open(model_path, 'rb') as f:
+    model = pickle.load(f)
 
-# Assuming you have a function to process individual frames
 def process_frame(frame):
-    # Load the model
-    model = gr.load("models/dima806/deepfake_vs_real_image_detection")
-    
     # Process the frame using the model
-    result = model(frame)
-    
+    # You might need to preprocess the frame to match the model's input requirements
+    result = model.predict(np.array(frame))
     return result
 
-def process_video(video_path):
-    cap = cv2.VideoCapture(video_path)
-    results = []
+def process_video(video_file):
+    video = video_file.read()
     
-    while cap.isOpened():
-        ret, frame = cap.read()
-        if not ret:
-            break
-        
-        # Process each frame
-        result = process_frame(frame)
-        results.append(result)
-    
-    cap.release()
-    
-    # Analyze results (e.g., calculate average score, majority vote, etc.)
+    # Use Pillow to open the video file
+    with Image.open(io.BytesIO(video)) as img:
+        # Check if it's an animated image (like GIF)
+        if hasattr(img, 'n_frames') and img.n_frames > 1:
+            results = []
+            for frame in range(img.n_frames):
+                img.seek(frame)
+                frame_result = process_frame(img.convert('RGB'))
+                results.append(frame_result)
+        else:
+            # If it's a single image, process it once
+            results = [process_frame(img.convert('RGB'))]
+
+    # Analyze results
     final_result = analyze_results(results)
     
     return final_result
@@ -39,7 +46,7 @@ def analyze_results(results):
 
 iface = gr.Interface(
     fn=process_video,
-    inputs=gr.Video(),
+    inputs=gr.File(label="Upload Video"),
     outputs=gr.Text(label="Deepfake Detection Result")
 )