File size: 5,406 Bytes
f518cc5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
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
import os
import zipfile
# local_zip = "FINAL-EFFICIENTNETV2-B0.zip"
# zip_ref = zipfile.ZipFile(local_zip, 'r')
# zip_ref.extractall('FINAL-EFFICIENTNETV2-B0')
# zip_ref.close()
# 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
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.
Keyword Arguments:
n_frames {int} -- Total number of frames to load. These will be evenly spaced
throughout the video. If not specified (i.e., None), all frames will be loaded.
(default: {None})
batch_size {int} -- Batch size to use with MTCNN face detector. (default: {32})
resize {float} -- Fraction by which to resize frames from original prior to face
detection. A value less than 1 results in downsampling and a value greater than
1 result in upsampling. (default: {None})
"""
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])
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)
for i in range(len(frames)):
if boxes[i] is None:
faces.append(face2) #append previous face frame if no face is detected
continue
box = boxes[i][0].astype(int)
frame = frames[i]
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
continue
face2 = cv2.resize(face, (224, 224))
faces.append(face2)
frames = []
v_cap.release()
return faces
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
real = 0
fake = 0
for face in faces:
face2 = face/255
pred = model.predict(np.expand_dims(face2, axis=0))[0]
total+=1
pred2 = pred[1]
if pred2 > 0.5:
fake+=1
else:
real+=1
fake_ratio = fake/total
text =""
text2 = "Deepfakes Confidence: " + str(fake_ratio*100) + "%"
if fake_ratio >= 0.5:
text = "The video is FAKE."
else:
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 )
clip = mp.VideoFileClip("results.gif")
clip.write_videofile("video.mp4")
return text, text2, "video.mp4"
title="EfficientNetV2 Deepfakes Video Detector"
examples = [
['Video1-fake-1-ff.mp4'],
['Video6-real-1-ff.mp4'],
['Video3-fake-3-ff.mp4'],
['Video8-real-3-ff.mp4'],
['real-1.mp4'],
['fake-1.mp4'],
]
gr.Interface(deepfakespredict,
inputs = ["video"],
outputs=["text","text", gr.Video(label="Detected face sequence")],
title=title,
examples=examples
).launch() |