Update app.py

app.py

@@ -1,10 +1,12 @@
 import cv2
 import numpy as np
-import argparse
 import json
 from tensorflow.keras.models import load_model
 import os
-
+import base64
+from io import BytesIO
+from PIL import Image
+import gradio as gr
 
 # Set environment variables to suppress TensorFlow warnings
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
@@ -13,6 +15,16 @@ os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
 # Load your pre-trained model
 model = load_model("all_in_one.h5")
 
+def decode_frame(base64_str):
+    """Decodes a base64 string to an image."""
+    try:
+        image_data = base64.b64decode(base64_str)
+        image = Image.open(BytesIO(image_data))
+        return np.array(image)
+    except Exception as e:
+        print(f"Error decoding base64 frame: {e}")
+        return None
+
 def preprocess_frame(frame):
     try:
         # Resize the frame as per your model input requirement
@@ -26,15 +38,22 @@ def preprocess_frame(frame):
 def predict_frames(frames):
     predictions = []
     
-    for i, frame in enumerate(frames):
+    for i, frame_base64 in enumerate(frames):
+        frame = decode_frame(frame_base64)
+        if frame is None:
+            print(f"Skipping frame {i} due to decoding error.")
+            continue
+        
         preprocessed_frame = preprocess_frame(frame)
         if preprocessed_frame is None:
             print(f"Skipping frame {i} due to preprocessing error.")
             continue
+        
         prediction = model.predict(preprocessed_frame)
         if prediction.size == 0:
             print(f"No prediction returned for frame {i}.")
             continue
+        
         predictions.append(prediction)
         print(f"Prediction for frame {i}: {prediction}")
     
@@ -49,9 +68,11 @@ def main(params):
         params = json.loads(params)
     except json.JSONDecodeError as e:
         return {"error": f"Invalid JSON input: {e.msg} at line {e.lineno} column {e.colno}"}
+    
     print(f"JSON : \n{params}")
     frames = params.get("video", [])
     video_path = params.get("file_name")
+    
     predictions = predict_frames(frames)
     print(predictions)
     if len(predictions) == 0:
@@ -65,7 +86,7 @@ def main(params):
     result = 'Deepfake' if avg_prediction > 0.5 else 'Real'
     confidence = float(avg_prediction) * 100  # Convert numpy float to Python float and scale
 
-    # Save the result as a JSON file
+    # Prepare the result as a JSON response
     output_data = {
         "file_name": video_path,
         "solution": {
@@ -73,14 +94,12 @@ def main(params):
             "confidence": float("{:.2f}".format(confidence))
         }
     }
-    return json.dump(output_data)
     
-    print("Processing complete.")
-    os.remove(video_path)
+    return output_data
 
-import gradio as gr
-inputt = gr.Textbox(label='''Parameters (JSON format) Eg. {"contexts" : ["context1","context2",...],"nums" : [num1,num2,...]} nums represent the number of question answers pairs''')
+# Gradio interface
+inputt = gr.Textbox(label='''Parameters (JSON format) Eg. {"video" : ["base64_frame1","base64_frame2",...], "file_name": "video.mp4"}''')
 outputs = gr.JSON()
 
-application = gr.Interface(fn=main, inputs=inputt, outputs=outputs, title="QnA Generator based on Weather with API")
-application.launch()
+application = gr.Interface(fn=main, inputs=inputt, outputs=outputs, title="Deepfake Detection Model")
+application.launch()