first commit

.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+*.mp4
+*.pkl
+*.log

app.py

@@ -0,0 +1,93 @@
+import gradio as gr
+import cv2
+import torch
+import dlib
+import numpy as np
+from imutils import face_utils
+from torchvision import models, transforms
+from tempfile import NamedTemporaryFile
+
+# Load face detector and landmark predictor
+face_detector = dlib.get_frontal_face_detector()
+PREDICTOR_PATH = "./lib/shape_predictor_81_face_landmarks.dat"
+face_predictor = dlib.shape_predictor(PREDICTOR_PATH)
+
+# Load deepfake detection model
+model = models.resnet34()
+model.fc = torch.nn.Linear(model.fc.in_features, 2)
+ckpt_path = "./resnet34.pkl"
+model.load_state_dict(torch.load(ckpt_path, map_location="cpu"))
+model.eval()
+
+# Define transformation for face images
+transform = transforms.Compose([
+    transforms.ToPILImage(),
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+])
+
+def process_video(video_path: str):
+    cap = cv2.VideoCapture(video_path)
+    width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    fps = int(cap.get(cv2.CAP_PROP_FPS))
+
+    output_path = video_path.replace(".mp4", "_processed.mp4")
+    output_video = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (width, height))
+
+    while cap.isOpened():
+        ret, frame = cap.read()
+        if not ret:
+            break
+
+        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+        faces = face_detector(rgb_frame, 1)
+
+        for face in faces:
+            landmarks = face_utils.shape_to_np(face_predictor(rgb_frame, face))
+            x_min, y_min = np.min(landmarks, axis=0)
+            x_max, y_max = np.max(landmarks, axis=0)
+
+            face_crop = rgb_frame[y_min:y_max, x_min:x_max]
+            if face_crop.size == 0:
+                continue
+
+            face_tensor = transform(face_crop).unsqueeze(0)
+            with torch.no_grad():
+                output = torch.softmax(model(face_tensor), dim=1)
+                fake_confidence = output[0, 1].item() * 100  # Fake confidence as a percentage
+                label = "Fake" if fake_confidence > 50 else "Real"
+                color = (0, 0, 255) if label == "Fake" else (0, 255, 0)
+
+                # Annotating confidence score with label
+                label_text = f"{label} ({fake_confidence:.2f}%)"
+
+            cv2.rectangle(frame, (x_min, y_min), (x_max, y_max), color, 2)
+            cv2.putText(frame, label_text, (x_min, y_min - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 1)
+
+        output_video.write(frame)
+
+    cap.release()
+    output_video.release()
+    return output_path
+
+def gradio_interface(video_file):
+    with NamedTemporaryFile(delete=False, suffix=".mp4") as temp_file:
+        temp_file.write(video_file.read())
+        temp_path = temp_file.name
+
+    output_path = process_video(temp_path)
+    return output_path
+
+# Gradio UI
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=gr.Video(label="Upload Video"),
+    outputs=gr.Video(label="Processed Video"),
+    title="Deepfake Detection",
+    description="Upload a video to detect deepfakes. The model will process faces and classify them as real or fake."
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+torch
+torchvision
+dlib
+opencv-python
+numpy
+imutils