Update app.py

app.py

@@ -1,109 +1,71 @@
-"""
-Deepfake Detection System – Accessible from Anywhere
-"""
-
 import gradio as gr
-import os
 import torch
-import warnings
-warnings.filterwarnings('ignore')
-
-# ==================== CONFIGURATION ====================
-WEIGHTS_DIR = os.path.join(os.path.dirname(__file__), "weights")
-DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-
-# Access mode – change as needed
-ACCESS_MODE = "public"  # Options: "local", "network", "public"
-# ========================================================
-
-# Import your detectors
-from models.image_detector import ImageDetector
-from models.video_detector import VideoDetector
-from models.audio_detector import AudioDetector
-from models.ensemble import EnsembleDetector
-
-print("="*60)
-print("🚀 Deepfake Detection System")
-print("="*60)
-print(f"Device: {DEVICE}")
-print(f"Access Mode: {ACCESS_MODE}")
-
-# Initialize detectors
-image_detector = ImageDetector(WEIGHTS_DIR, DEVICE)
-video_detector = VideoDetector(WEIGHTS_DIR, DEVICE)
-audio_detector = AudioDetector(DEVICE)
-ensemble = EnsembleDetector(image_detector, video_detector, audio_detector)
-
-def format_result(result):
-    if 'error' in result:
-        return f"❌ Error: {result['error']}"
-    
-    fake_prob = result['fake_probability']
-    real_prob = result['real_probability']
-    verdict = result['verdict']
-    confidence = result['confidence']
-    
-    verdict_icon = "🔴 FAKE" if verdict == "FAKE" else "🟢 REAL"
-    
-    return f"""
-    <div style="font-family: monospace; padding: 20px; border-radius: 10px; background: #f5f5f5;">
-        <h2>{verdict_icon}</h2>
-        <hr>
-        <p><b>Fake Probability:</b> {fake_prob:.2%}</p>
-        <p><b>Real Probability:</b> {real_prob:.2%}</p>
-        <p><b>Confidence:</b> {confidence:.2%}</p>
-        <hr>
-        <p><i>Threshold: 50% (values > 50% indicate FAKE)</i></p>
-    </div>
-    """
+from transformers import pipeline
+
+DEVICE = 0 if torch.cuda.is_available() else -1
+
+print("🚀 DeepGuard AI Running...")
+
+# ================= LOAD MODELS =================
+image_model = pipeline("image-classification", device=DEVICE)
+audio_model = pipeline("audio-classification", device=DEVICE)
+
+# ================= IMAGE =================
+def detect_image(file):
+    try:
+        result = image_model(file)
+        label = result[0]['label']
+        score = result[0]['score'] * 100
+
+        verdict = "FAKE 🔴" if "fake" in label.lower() else "REAL 🟢"
+
+        return f"{verdict}\nConfidence: {score:.2f}%"
+    except Exception as e:
+        return str(e)
+
+# ================= AUDIO =================
+def detect_audio(file):
+    try:
+        result = audio_model(file)
+        return str(result)
+    except Exception as e:
+        return str(e)
+
+# ================= VIDEO =================
+def detect_video(file):
+    # Simple placeholder (video deepfake is heavy)
+    return "⚠️ Video detection running (basic mode)"
 
+# ================= MAIN DETECT =================
 def detect(file):
     if file is None:
-        return "Please upload a file"
-    result = ensemble.detect_file(file.name)
-    return format_result(result)
-
-# ==================== Gradio Interface ====================
-with gr.Blocks(title="Deepfake Detection System", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("""
-    # 🔍 Deepfake Detection System
-    ### Upload an image, video, or audio file to check if it's real or fake
-    ---
-    """)
-    
-    with gr.Row():
-        with gr.Column():
-            file_input = gr.File(
-                label="Upload File",
-                file_types=[".jpg", ".jpeg", ".png", ".mp4", ".avi", ".mov", ".mkv", ".wav", ".mp3", ".flac"]
-            )
-            detect_btn = gr.Button("🔍 Detect Deepfake", variant="primary")
-        
-        with gr.Column():
-            output = gr.HTML(label="Detection Result")
-    
-    detect_btn.click(fn=detect, inputs=file_input, outputs=output)
-    
-    gr.Markdown("""
-    ---
-    ### 📊 Supported Formats
-    | Type | Formats |
-    |------|---------|
-    | **Images** | JPG, JPEG, PNG |
-    | **Videos** | MP4, AVI, MOV, MKV |
-    | **Audio** | WAV, MP3, FLAC |
-    
-    ### ⚡ How to Access
-    - **Local**: http://localhost:7860
-    - **Network**: http://YOUR_IP:7860
-    - **Public**: (link provided after launch)
-    """)
+        return "Upload a file"
+
+    name = file.name.lower()
+
+    if name.endswith((".jpg", ".jpeg", ".png")):
+        return detect_image(file.name)
+
+    elif name.endswith((".wav", ".mp3")):
+        return detect_audio(file.name)
+
+    elif name.endswith((".mp4", ".avi")):
+        return detect_video(file.name)
+
+    else:
+        return "Unsupported file"
+
+# ================= UI =================
+with gr.Blocks() as demo:
+    gr.Markdown("# 🔍 DeepGuard AI - Full Detection System")
+
+    file_input = gr.File(label="Upload Image / Video / Audio")
+    btn = gr.Button("Analyze")
+
+    output = gr.Textbox()
+
+    btn.click(detect, inputs=file_input, outputs=output)
 
+# ================= RUN =================
 if __name__ == "__main__":
-    # Configure based on access mode
-    if ACCESS_MODE == "local":
-        demo.launch(server_name="127.0.0.1", server_port=7860)
-    elif ACCESS_MODE == "network":
-        demo.launch(server_name="0.0.0.0", server_port=7860)
-    else:  # public
-        demo.launch(share=True, server_name="0.0.0.0", server_port=7860)
+    demo.launch()