代码解析—part1 数据准备—CVPR2023—Implicit Identity Leakage: The Stumbling Block to Improving Deepfake

原创

已于 2024-05-23 15:17:00 修改 · 852 阅读

18 ·

CC 4.0 BY-SA版权

文章标签：

#学习 #人工智能 #视觉检测 #AIGC

于 2024-05-13 00:05:13 首次发布

论文讲解请看：https://blog.youkuaiyun.com/JustWantToLearn/article/details/138758033
代码链接：https://github.com/megvii-research/CADDM
在这里，我们简要描述算法流程，着重分析模型搭建细节，以及为什么要这样搭建。
part 1：数据集准备本文
part 2: 数据集加载，包含 Multi-scale Facial Swap(MFS) 模块：https://blog.youkuaiyun.com/JustWantToLearn/article/details/139092687
part 3：训练过程，ADM模块 https://blog.youkuaiyun.com/JustWantToLearn/article/details/139116455

环境准备

linux
Python 3 >= 3.6
Pytorch >= 1.6.0
OpenCV >= 4.4.0
Scipy >= 1.4.1
NumPy >= 1.19.5

在安装dlib库的时候卡了很久，先安装cmake，再去安装dlib。如果不成功，直接源码安装

git clone https://github.com/davisking/dlib.git
cd dlib
mkdir build
cd build
cmake ..
cmake --build . --config Release
cmake --build . --config Release --target install
cd ..
python setup.py install

数据准备提取ff++数据集的ldm

1、下载FF++数据集

根据链接https://github.com/ondyari/FaceForensics/tree/master提示下载
放入特定文件夹中

.
└── data
    └── FaceForensics++
        ├── original_sequences
        │   └── youtube
        │       └── raw
        │           └── videos
        │               └── *.mp4
        ├── manipulated_sequences
        │   ├── Deepfakes
        │       └── raw
        │           └── videos
        │               └── *.mp4
        │   ├── Face2Face
        │		...
        │   ├── FaceSwap
        │		...
        │   ├── NeuralTextures
        │		...
        │   ├── FaceShifter
        │		...

2、提取ldm

 python lib/extract_frames_ldm_ff++.py

2.1 定义路径，函数

#extract_frames_ldm_ff++.py
#!/usr/bin/env python3
from glob import glob
import os
import cv2
from tqdm import tqdm
import numpy as np
import dlib
import json
import argparse
from imutils import face_utils

#定义路径
VIDEO_PATH = "./CADDM/data/FaceForensics++"
SAVE_IMGS_PATH = "./test_images"
#下载好的形状预测模型
PREDICTOR_PATH = "./CADDM/lib/shape_predictor_81_face_landmarks.dat"
DATASETS = {
   
   'Original', 'FaceSwap', 'FaceShifter', 'Face2Face', 'Deepfakes', 'NeuralTextures'}
COMPRESSION = {
   
   'raw'}
NUM_FRAMES = 1
IMG_META_DICT = dict()

def parse_labels(video_path):
    label = None
    if "original" in video_path:
        label = 0
    else:
        label = 1
    return label

def parse_source_save_path(save_path):
    source_save_path = None
    if "original" in save_path:
        source_save_path = save_path
    else:
        img_meta = save_path.split('/')
        source_target_index