Update app.py

app.py

@@ -7,17 +7,17 @@ import torch
 import torch.nn.functional as F
 from facenet_pytorch import MTCNN, InceptionResnetV1
 import numpy as np
-from flask_socketio import SocketIO, emit
-import time
+from pytorch_grad_cam import GradCAM
+from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
+import os
 
 app = Flask(__name__)
-socketio = SocketIO(app, cors_allowed_origins="*")
 
 # Configuration
 UPLOAD_FOLDER = 'uploads'
 ALLOWED_EXTENSIONS = {'mp4', 'avi', 'mov'}
 app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
-app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024  # 16 MB
+app.config['MAX_CONTENT_LENGTH'] = 16 * 1024 * 1024
 
 os.makedirs(UPLOAD_FOLDER, exist_ok=True)
 
@@ -27,6 +27,7 @@ DEVICE = 'cuda:0' if torch.cuda.is_available() else 'cpu'
 mtcnn = MTCNN(select_largest=False, post_process=False, device=DEVICE).to(DEVICE).eval()
 
 model = InceptionResnetV1(pretrained="vggface2", classify=True, num_classes=1, device=DEVICE)
+# Model Credits: https://huggingface.co/spaces/dhairyashah/deepfake-alpha-version/blob/main/CREDITS.md
 checkpoint = torch.load("resnetinceptionv1_epoch_32.pth", map_location=torch.device('cpu'))
 model.load_state_dict(checkpoint['model_state_dict'])
 model.to(DEVICE)
@@ -60,7 +61,6 @@ def analyze_video(video_path, sample_rate=30):
     frame_count = 0
     fake_count = 0
     total_processed = 0
-    total_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
 
     while cap.isOpened():
         ret, frame = cap.read()
@@ -76,10 +76,6 @@ def analyze_video(video_path, sample_rate=30):
                 if prediction == "fake":
                     fake_count += 1
 
-            # Emit progress update
-            progress = (frame_count / total_frames) * 100
-            socketio.emit('analysis_progress', {'progress': progress})
-
         frame_count += 1
 
     cap.release()
@@ -90,12 +86,7 @@ def analyze_video(video_path, sample_rate=30):
     else:
         return 0
 
-@app.route('/', methods=['GET'])
-def home():
-    return jsonify({'homepage': 'https://deepfake-checker.dhairyashah.dev'})
-
 @app.route('/analyze', methods=['POST'])
-@spaces.GPU
 def analyze_video_api():
     if 'video' not in request.files:
         return jsonify({'error': 'No video file provided'}), 400
@@ -108,23 +99,9 @@ def analyze_video_api():
     if file and allowed_file(file.filename):
         filename = secure_filename(file.filename)
         filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
-        
-        # Save file and emit upload progress
-        chunk_size = 4096
-        file_size = int(request.headers.get('Content-Length', 0))
-        bytes_read = 0
-        with open(filepath, 'wb') as f:
-            while True:
-                chunk = file.read(chunk_size)
-                if not chunk:
-                    break
-                f.write(chunk)
-                bytes_read += len(chunk)
-                progress = (bytes_read / file_size) * 100
-                socketio.emit('upload_progress', {'progress': progress})
+        file.save(filepath)
 
         try:
-            socketio.emit('analysis_start', {'message': 'Starting video analysis'})
             fake_percentage = analyze_video(filepath)
             os.remove(filepath)  # Remove the file after analysis
 
@@ -133,14 +110,12 @@ def analyze_video_api():
                 'is_likely_deepfake': fake_percentage >= 60
             }
 
-            socketio.emit('analysis_complete', result)
             return jsonify(result), 200
         except Exception as e:
             os.remove(filepath)  # Remove the file if an error occurs
-            socketio.emit('analysis_error', {'error': str(e)})
             return jsonify({'error': str(e)}), 500
     else:
         return jsonify({'error': 'Invalid file type'}), 400
 
 if __name__ == '__main__':
-    socketio.run(app, host='0.0.0.0', port=7860, allow_unsafe_werkzeug=True)
+    app.run(host='0.0.0.0', port=7860)