Update app.py

app.py

@@ -2,8 +2,6 @@ import gradio as gr
 import cv2
 import numpy as np
 import tensorflow as tf
-import tensorflow_addons
-
 from facenet_pytorch import MTCNN
 from PIL import Image
 import moviepy.editor as mp
@@ -13,61 +11,43 @@ import zipfile
 # Load face detector
 mtcnn = MTCNN(margin=14, keep_all=True, factor=0.7, device='cpu')
 
-#Face Detection function, Reference: (Timesler, 2020); Source link: https://www.kaggle.com/timesler/facial-recognition-model-in-pytorch
+# Face Detection function
 class DetectionPipeline:
-    """Pipeline class for detecting faces in the frames of a video file."""
-
     def __init__(self, detector, n_frames=None, batch_size=60, resize=None):
-        """Constructor for DetectionPipeline class.
-        """
         self.detector = detector
         self.n_frames = n_frames
         self.batch_size = batch_size
         self.resize = resize
 
     def __call__(self, filename):
-        """Load frames from an MP4 video and detect faces.
-
-        Arguments:
-            filename {str} -- Path to video.
-        """
-        # Create video reader and find length
         v_cap = cv2.VideoCapture(filename)
         v_len = int(v_cap.get(cv2.CAP_PROP_FRAME_COUNT))
 
-        # Pick 'n_frames' evenly spaced frames to sample
         if self.n_frames is None:
             sample = np.arange(0, v_len)
         else:
             sample = np.linspace(0, v_len - 1, self.n_frames).astype(int)
 
-        # Loop through frames
         faces = []
         frames = []
         for j in range(v_len):
             success = v_cap.grab()
             if j in sample:
-                # Load frame
                 success, frame = v_cap.retrieve()
                 if not success:
                     continue
                 frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-                # frame = Image.fromarray(frame)
 
-                # Resize frame to desired size
                 if self.resize is not None:
-                    frame = frame.resize([int(d * self.resize) for d in frame.size])
+                    frame = cv2.resize(frame, (int(frame.shape[1] * self.resize), int(frame.shape[0] * self.resize)))
+
                 frames.append(frame)
 
-                # When batch is full, detect faces and reset frame list
                 if len(frames) % self.batch_size == 0 or j == sample[-1]:
-
-                    boxes, probs = self.detector.detect(frames)
-
+                    boxes, _ = self.detector.detect(frames)
                     for i in range(len(frames)):
-
                         if boxes[i] is None:
-                            faces.append(face2)     #append previous face frame if no face is detected
+                            faces.append(face2)
                             continue
 
                         box = boxes[i][0].astype(int)
@@ -75,11 +55,10 @@ class DetectionPipeline:
                         face = frame[box[1]:box[3], box[0]:box[2]]
 
                         if not face.any():
-                            faces.append(face2)     #append previous face frame if no face is detected
+                            faces.append(face2)
                             continue
 
                         face2 = cv2.resize(face, (224, 224))
-
                         faces.append(face2)
 
                     frames = []
@@ -88,14 +67,11 @@ class DetectionPipeline:
 
         return faces
 
-
-detection_pipeline = DetectionPipeline(detector=mtcnn,n_frames=20, batch_size=60)
+detection_pipeline = DetectionPipeline(detector=mtcnn, n_frames=20, batch_size=60)
 
 model = tf.keras.models.load_model("p1")
 
-
 def deepfakespredict(input_video):
-
     faces = detection_pipeline(input_video)
 
     total = 0
@@ -103,22 +79,21 @@ def deepfakespredict(input_video):
     fake = 0
 
     for face in faces:
-
-        face2 = face/255
+        face2 = face / 255
         pred = model.predict(np.expand_dims(face2, axis=0))[0]
-        total+=1
+        total += 1
 
         pred2 = pred[1]
 
         if pred2 > 0.5:
-          fake+=1
+            fake += 1
         else:
-          real+=1
+            real += 1
 
-    fake_ratio = fake/total
+    fake_ratio = fake / total
 
-    text =""
-    text2 = "Deepfakes Confidence: " + str(fake_ratio*100) + "%"
+    text = ""
+    text2 = "Deepfakes Confidence: " + str(fake_ratio * 100) + "%"
 
     if fake_ratio >= 0.5:
         text = "The video is FAKE."
@@ -126,27 +101,25 @@ def deepfakespredict(input_video):
         text = "The video is REAL."
 
     face_frames = []
-    
+
     for face in faces:
         face_frame = Image.fromarray(face.astype('uint8'), 'RGB')
         face_frames.append(face_frame)
-        
-    face_frames[0].save('results.gif', save_all=True, append_images=face_frames[1:], duration = 250, loop = 100 )
+
+    face_frames[0].save('results.gif', save_all=True, append_images=face_frames[1:], duration=250, loop=100)
     clip = mp.VideoFileClip("results.gif")
     clip.write_videofile("video.mp4")
 
     return text, text2, "video.mp4"
 
-
-
-title="Group 2- EfficientNetV2 based Deepfake Video Detector"
-description='''Please upload videos responsibly and await the results in a gif. The approach in place includes breaking down the video into several frames followed by collecting
+title = "Group 2- EfficientNetV2 based Deepfake Video Detector"
+description = '''Please upload videos responsibly and await the results in a gif. The approach in place includes breaking down the video into several frames followed by collecting
 the frames that contain a face. Once these frames are collected the trained model attempts to predict if the face is fake or real and contribute to a deepfake confidence. This confidence level eventually 
 determines if the video can be considered a fake or not.'''
-            
+
 gr.Interface(deepfakespredict,
-                     inputs = ["video"],
-                     outputs=["text","text", gr.Video(label="Detected face sequence")],
-                     title=title,
-                     description=description
-                     ).launch()
+             inputs=["video"],
+             outputs=["text", "text", gr.Video(label="Detected face sequence")],
+             title=title,
+             description=description
+             ).launch()