deepfake使用
作者：互联网
Github下载开源项目：https://github.com/deepfakes/faceswap
anaconda 创建环境：
conda create -n tf python=3.7
cd命令进入项目所在文件夹，进行安装
python setup.py
INFO Running without root/admin privileges
INFO The tool provides tips for installation
and installs required python packages
INFO Setup in Linux 5.13.0-30-generic
INFO Installed Python: 3.7.13 64bit
INFO Running in Conda
INFO Running in a Virtual Environment
INFO Encoding: UTF-8
INFO Installed pip: 21.2.2
INFO AMD Support: AMD GPU support is currently limited.
Nvidia Users MUST answer 'no' to this option.
Enable AMD Support? [y/N] no
INFO AMD Support Disabled
Enable Docker? [y/N] no
INFO Docker Disabled
Enable CUDA? [Y/n] y
INFO CUDA Enabled
INFO Skipping Cuda/cuDNN checks for Conda install
INFO Faceswap config written to: /home/bim/project-csc/faceswap-master/config/.faceswap
Please ensure your System Dependencies are met. Continue? [y/N] y
INFO Installing Required Python Packages. This may take some time...
INFO Installing tqdm>=4.64
INFO Installing psutil>=5.8.0
INFO Installing numpy>=1.18.0
INFO Installing opencv-python>=4.5.5.0
INFO "opencv-python>=4.5.5.0" not available in Conda. Installing with pip
INFO Installing opencv-python>=4.5.5.0
INFO Installing pillow>=8.3.1
INFO Installing scikit-learn>=1.0.2
INFO Installing fastcluster>=1.2.4
INFO Installing matplotlib>=3.5.1
INFO "matplotlib>=3.5.1" not available in Conda. Installing with pip
INFO Installing matplotlib>=3.5.1
INFO Installing imageio>=2.9.0
INFO Installing imageio-ffmpeg>=0.4.7
INFO Installing ffmpy==0.2.3
INFO ffmpy==0.2.3 not available in Conda. Installing with pip
INFO Installing ffmpy==0.2.3
INFO Installing nvidia-ml-py<11.515
INFO "nvidia-ml-py<11.515" not available in Conda. Installing with pip
INFO Installing nvidia-ml-py<11.515
INFO Installing typing-extensions
INFO Installing Cuda Toolkit
Solving environment: failed
PackagesNotFoundError: The following packages are not available from current channels:
- cudatoolkit=11.2
- __glibc[version='>=2.17,<3.0.a0']
- cudnn=8.1
- __glibc[version='>=2.17,<3.0.a0']
Current channels:
- https://conda.anaconda.org/conda-forge/linux-64
- https://conda.anaconda.org/conda-forge/noarch
- http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/linux-64
- http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/noarch
- http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/linux-64
- http://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/noarch
To search for alternate channels that may provide the conda package you're
looking for, navigate to
https://anaconda.org
and use the search bar at the top of the page.
WARNING Couldn't install Cuda Toolkit with Conda. Please install this package manually
INFO Installing tensorflow-gpu>=2.5.0,<2.9.0
Collecting tensorflow-gpu<2.9.0,>=2.5.0
Downloading tensorflow_gpu-2.8.1-cp37-cp37m-manylinux2010_x86_64.whl (497.9 MB)
|████████████████████████████████| 497.9 MB 11.9 MB/s
Requirement already satisfied: typing-extensions>=3.6.6 in /home/bim/anaconda3/envs/tf/lib/python3.7/site-packages (from tensorflow-gpu<2.9.0,>=2.5.0) (4.2.0)
Collecting google-pasta>=0.1.1
Downloading google_pasta-0.2.0-py3-none-any.whl (57 kB)
|████████████████████████████████| 57 kB 13.7 MB/s
Requirement already satisfied: numpy>=1.20 in /home/bim/anaconda3/envs/tf/lib/python3.7/site-packages (from tensorflow-gpu<2.9.0,>=2.5.0) (1.20.3)
Collecting gast>=0.2.1
Downloading gast-0.5.3-py3-none-any.whl (19 kB)
Collecting astunparse>=1.6.0
Downloading astunparse-1.6.3-py2.py3-none-any.whl (12 kB)
Collecting flatbuffers>=1.12
Downloading flatbuffers-2.0-py2.py3-none-any.whl (26 kB)
Collecting libclang>=9.0.1
Downloading libclang-14.0.1-py2.py3-none-manylinux1_x86_64.whl (14.5 MB)
|████████████████████████████████| 14.5 MB 8.2 MB/s
Collecting grpcio<2.0,>=1.24.3
Downloading grpcio-1.46.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.4 MB)
|████████████████████████████████| 4.4 MB 11.4 MB/s
Collecting tensorboard<2.9,>=2.8
Downloading tensorboard-2.8.0-py3-none-any.whl (5.8 MB)
|████████████████████████████████| 5.8 MB 9.0 MB/s
Collecting tensorflow-estimator<2.9,>=2.8
Downloading tensorflow_estimator-2.8.0-py2.py3-none-any.whl (462 kB)
|████████████████████████████████| 462 kB 11.4 MB/s
Collecting h5py>=2.9.0
Downloading h5py-3.6.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (4.1 MB)
|████████████████████████████████| 4.1 MB 11.1 MB/s
Requirement already satisfied: setuptools in /home/bim/anaconda3/envs/tf/lib/python3.7/site-packages (from tensorflow-gpu<2.9.0,>=2.5.0) (61.2.0)
Collecting termcolor>=1.1.0
Downloading termcolor-1.1.0.tar.gz (3.9 kB)
Collecting keras<2.9,>=2.8.0rc0
Downloading keras-2.8.0-py2.py3-none-any.whl (1.4 MB)
|████████████████████████████████| 1.4 MB 11.4 MB/s
Collecting keras-preprocessing>=1.1.1
Downloading Keras_Preprocessing-1.1.2-py2.py3-none-any.whl (42 kB)
|████████████████████████████████| 42 kB 14.1 MB/s
Collecting protobuf>=3.9.2
Downloading protobuf-3.20.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl (1.0 MB)
|████████████████████████████████| 1.0 MB 11.3 MB/s
Collecting opt-einsum>=2.3.2
Downloading opt_einsum-3.3.0-py3-none-any.whl (65 kB)
|████████████████████████████████| 65 kB 13.4 MB/s
Collecting tensorflow-io-gcs-filesystem>=0.23.1
Downloading tensorflow_io_gcs_filesystem-0.26.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (2.4 MB)
|████████████████████████████████| 2.4 MB 11.1 MB/s
Collecting absl-py>=0.4.0
Downloading absl_py-1.0.0-py3-none-any.whl (126 kB)
|████████████████████████████████| 126 kB 12.0 MB/s
Requirement already satisfied: six>=1.12.0 in /home/bim/anaconda3/envs/tf/lib/python3.7/site-packages (from tensorflow-gpu<2.9.0,>=2.5.0) (1.16.0)
Collecting wrapt>=1.11.0
Downloading wrapt-1.14.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (75 kB)
|████████████████████████████████| 75 kB 13.0 MB/s
Requirement already satisfied: wheel<1.0,>=0.23.0 in /home/bim/anaconda3/envs/tf/lib/python3.7/site-packages (from astunparse>=1.6.0->tensorflow-gpu<2.9.0,>=2.5.0) (0.37.1)
Collecting cached-property
Downloading cached_property-1.5.2-py2.py3-none-any.whl (7.6 kB)
Collecting tensorboard-data-server<0.7.0,>=0.6.0
Downloading tensorboard_data_server-0.6.1-py3-none-manylinux2010_x86_64.whl (4.9 MB)
|████████████████████████████████| 4.9 MB 11.3 MB/s
Collecting google-auth-oauthlib<0.5,>=0.4.1
Downloading google_auth_oauthlib-0.4.6-py2.py3-none-any.whl (18 kB)
Collecting tensorboard-plugin-wit>=1.6.0
Downloading tensorboard_plugin_wit-1.8.1-py3-none-any.whl (781 kB)
|████████████████████████████████| 781 kB 12.0 MB/s
Collecting requests<3,>=2.21.0
Downloading requests-2.27.1-py2.py3-none-any.whl (63 kB)
|████████████████████████████████| 63 kB 13.2 MB/s
Collecting markdown>=2.6.8
Downloading Markdown-3.3.7-py3-none-any.whl (97 kB)
|████████████████████████████████| 97 kB 13.2 MB/s
Collecting werkzeug>=0.11.15
Downloading Werkzeug-2.1.2-py3-none-any.whl (224 kB)
|████████████████████████████████| 224 kB 11.1 MB/s
Collecting google-auth<3,>=1.6.3
Downloading google_auth-2.6.6-py2.py3-none-any.whl (156 kB)
|████████████████████████████████| 156 kB 11.1 MB/s
Collecting cachetools<6.0,>=2.0.0
Downloading cachetools-5.1.0-py3-none-any.whl (9.2 kB)
Collecting pyasn1-modules>=0.2.1
Downloading pyasn1_modules-0.2.8-py2.py3-none-any.whl (155 kB)
|████████████████████████████████| 155 kB 11.1 MB/s
Collecting rsa<5,>=3.1.4
Downloading rsa-4.8-py3-none-any.whl (39 kB)
Collecting requests-oauthlib>=0.7.0
Downloading requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)
Collecting importlib-metadata>=4.4
Downloading importlib_metadata-4.11.3-py3-none-any.whl (18 kB)
Collecting zipp>=0.5
Downloading zipp-3.8.0-py3-none-any.whl (5.4 kB)
Collecting pyasn1<0.5.0,>=0.4.6
Downloading pyasn1-0.4.8-py2.py3-none-any.whl (77 kB)
|████████████████████████████████| 77 kB 12.5 MB/s
Collecting charset-normalizer~=2.0.0
Downloading charset_normalizer-2.0.12-py3-none-any.whl (39 kB)
Collecting urllib3<1.27,>=1.21.1
Downloading urllib3-1.26.9-py2.py3-none-any.whl (138 kB)
|████████████████████████████████| 138 kB 11.2 MB/s
Requirement already satisfied: certifi>=2017.4.17 in /home/bim/anaconda3/envs/tf/lib/python3.7/site-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow-gpu<2.9.0,>=2.5.0) (2022.5.18.1)
Collecting idna<4,>=2.5
Downloading idna-3.3-py3-none-any.whl (61 kB)
|████████████████████████████████| 61 kB 13.0 MB/s
Collecting oauthlib>=3.0.0
Downloading oauthlib-3.2.0-py3-none-any.whl (151 kB)
|████████████████████████████████| 151 kB 11.3 MB/s
Building wheels for collected packages: termcolor
Building wheel for termcolor (setup.py) ... done
Created wheel for termcolor: filename=termcolor-1.1.0-py3-none-any.whl size=4848 sha256=f0c42830bca3d8858668bb7252a993b9e4c39385d50c72f3340856926d4f5f9e
Stored in directory: /tmp/pip-ephem-wheel-cache-h10wtvcm/wheels/3f/e3/ec/8a8336ff196023622fbcb36de0c5a5c218cbb24111d1d4c7f2
Successfully built termcolor
Installing collected packages: urllib3, pyasn1, idna, charset-normalizer, zipp, rsa, requests, pyasn1-modules, oauthlib, cachetools, requests-oauthlib, importlib-metadata, google-auth, werkzeug, tensorboard-plugin-wit, tensorboard-data-server, protobuf, markdown, grpcio, google-auth-oauthlib, cached-property, absl-py, wrapt, termcolor, tensorflow-io-gcs-filesystem, tensorflow-estimator, tensorboard, opt-einsum, libclang, keras-preprocessing, keras, h5py, google-pasta, gast, flatbuffers, astunparse, tensorflow-gpu
Successfully installed absl-py-1.0.0 astunparse-1.6.3 cached-property-1.5.2 cachetools-5.1.0 charset-normalizer-2.0.12 flatbuffers-2.0 gast-0.5.3 google-auth-2.6.6 google-auth-oauthlib-0.4.6 google-pasta-0.2.0 grpcio-1.46.1 h5py-3.6.0 idna-3.3 importlib-metadata-4.11.3 keras-2.8.0 keras-preprocessing-1.1.2 libclang-14.0.1 markdown-3.3.7 oauthlib-3.2.0 opt-einsum-3.3.0 protobuf-3.20.1 pyasn1-0.4.8 pyasn1-modules-0.2.8 requests-2.27.1 requests-oauthlib-1.3.1 rsa-4.8 tensorboard-2.8.0 tensorboard-data-server-0.6.1 tensorboard-plugin-wit-1.8.1 tensorflow-estimator-2.8.0 tensorflow-gpu-2.8.1 tensorflow-io-gcs-filesystem-0.26.0 termcolor-1.1.0 urllib3-1.26.9 werkzeug-2.1.2 wrapt-1.14.1 zipp-3.8.0
INFO All python3 dependencies are met.
You are good to go.
Enter: 'python faceswap.py -h' to see the options
'python faceswap.py gui' to launch the GUI
建立原始图像文件夹source，下设两个文件夹分别储存被替换人物图像和替换人物图像，可以用视频
人像抓取（从视频）：
python faceswap.py extract -i /home/bim/project-csc/faceswap-master/source/chaoyue -o /home/bim/project-csc/faceswap-master/source/xiaopang/
开始训练：
python faceswap.py train -A ./face/chaoyue -B ./face/xiaopang -m ./model/
训练过程：
Setting Faceswap backend to NVIDIA 05/20/2022 18:57:30 INFO Log level set to: INFO 05/20/2022 18:57:31 INFO Model A Directory: '/home/bim/project-csc/faceswap-master/face/chaoyue' (354 images) 05/20/2022 18:57:31 INFO Model B Directory: '/home/bim/project-csc/faceswap-master/face/xiaopang' (302 images) 05/20/2022 18:57:31 INFO Training data directory: /home/bim/project-csc/faceswap-master/model 05/20/2022 18:57:31 INFO =================================================== 05/20/2022 18:57:31 INFO Starting 05/20/2022 18:57:31 INFO Press 'ENTER' to save and quit 05/20/2022 18:57:31 INFO Press 'S' to save model weights immediately 05/20/2022 18:57:31 INFO =================================================== 05/20/2022 18:57:32 INFO Loading data, this may take a while... 05/20/2022 18:57:32 INFO Loading Model from Original plugin... 05/20/2022 18:57:32 INFO No existing state file found. Generating. 05/20/2022 18:57:35 INFO Loading Trainer from Original plugin... [18:57:48] [#00001] Loss A: 0.29092, Loss B: 0.25283 05/20/2022 18:57:48 INFO [Saved models] - Average loss since last save: face_a: 0.29092, face_b: 0.25283 [18:58:31] [#00250] Loss A: 0.08387, Loss B: 0.12929 05/20/2022 18:58:31 INFO [Saved models] - Average loss since last save: face_a: 0.12682, face_b: 0.16347 [18:59:11] [#00500] Loss A: 0.08441, Loss B: 0.11587 05/20/2022 18:59:12 INFO [Saved models] - Average loss since last save: face_a: 0.08083, face_b: 0.11646 [18:59:52] [#00750] Loss A: 0.06658, Loss B: 0.09254 05/20/2022 18:59:53 INFO [Saved models] - Average loss since last save: face_a: 0.06893, face_b: 0.10239 [19:00:33] [#01000] Loss A: 0.05453, Loss B: 0.07997 05/20/2022 19:00:34 INFO [Saved models] - Average loss since last save: face_a: 0.06153, face_b: 0.09495 [19:01:15] [#01250] Loss A: 0.05931, Loss B: 0.10159 05/20/2022 19:01:16 INFO [Saved models] - Average loss since last save: face_a: 0.05717, face_b: 0.08923 [19:01:58] [#01500] Loss A: 0.05073, Loss B: 0.08939 05/20/2022 19:01:58 INFO [Saved models] - Average loss since last save: face_a: 0.05318, face_b: 0.08536 [19:02:40] [#01750] Loss A: 0.04741, Loss B: 0.07891 05/20/2022 19:02:41 INFO [Saved models] - Average loss since last save: face_a: 0.05014, face_b: 0.08195 [19:03:23] [#02000] Loss A: 0.05117, Loss B: 0.07520 05/20/2022 19:03:24 INFO [Saved models] - Average loss since last save: face_a: 0.04778, face_b: 0.08011 [19:04:05] [#02250] Loss A: 0.04463, Loss B: 0.08217 05/20/2022 19:04:06 INFO [Saved models] - Average loss since last save: face_a: 0.04666, face_b: 0.07742 [19:04:47] [#02500] Loss A: 0.04054, Loss B: 0.08013 05/20/2022 19:04:48 INFO [Saved models] - Average loss since last save: face_a: 0.04453, face_b: 0.07574 [19:05:29] [#02750] Loss A: 0.03798, Loss B: 0.07508 05/20/2022 19:05:30 INFO [Saved models] - Average loss since last save: face_a: 0.04322, face_b: 0.07385 [19:06:11] [#03000] Loss A: 0.04088, Loss B: 0.06374 05/20/2022 19:06:12 INFO [Saved models] - Average loss since last save: face_a: 0.04156, face_b: 0.07255 [19:06:54] [#03250] Loss A: 0.04008, Loss B: 0.06920 05/20/2022 19:06:54 INFO [Saved models] - Average loss since last save: face_a: 0.04128, face_b: 0.07075 [19:07:36] [#03500] Loss A: 0.03971, Loss B: 0.07669 05/20/2022 19:07:36 INFO [Saved models] - Average loss since last save: face_a: 0.03975, face_b: 0.06984 [19:08:18] [#03750] Loss A: 0.04245, Loss B: 0.06629 05/20/2022 19:08:19 INFO [Saved models] - Average loss since last save: face_a: 0.03923, face_b: 0.06923 [19:09:00] [#04000] Loss A: 0.04397, Loss B: 0.06900 05/20/2022 19:09:01 INFO [Saved models] - Average loss since last save: face_a: 0.03823, face_b: 0.06784 [19:09:42] [#04250] Loss A: 0.03289, Loss B: 0.06148 05/20/2022 19:09:42 INFO [Saved models] - Average loss since last save: face_a: 0.03736, face_b: 0.06743 [19:10:25] [#04500] Loss A: 0.03530, Loss B: 0.07094 05/20/2022 19:10:25 INFO [Saved models] - Average loss since last save: face_a: 0.03702, face_b: 0.06596 [19:11:07] [#04750] Loss A: 0.03651, Loss B: 0.06341 05/20/2022 19:11:08 INFO [Saved models] - Average loss since last save: face_a: 0.03644, face_b: 0.06522 [19:11:49] [#05000] Loss A: 0.02978, Loss B: 0.05741 05/20/2022 19:11:50 INFO [Saved models] - Average loss since last save: face_a: 0.03594, face_b: 0.06486 [19:12:31] [#05250] Loss A: 0.03091, Loss B: 0.06061 05/20/2022 19:12:32 INFO [Saved models] - Average loss since last save: face_a: 0.03553, face_b: 0.06409 [19:13:13] [#05500] Loss A: 0.03453, Loss B: 0.06567 05/20/2022 19:13:14 INFO [Saved models] - Average loss since last save: face_a: 0.03487, face_b: 0.06315 [19:13:55] [#05750] Loss A: 0.03094, Loss B: 0.06266 05/20/2022 19:13:56 INFO [Saved models] - Average loss since last save: face_a: 0.03468, face_b: 0.06292 [19:14:38] [#06000] Loss A: 0.03007, Loss B: 0.05961 05/20/2022 19:14:38 INFO [Saved models] - Average loss since last save: face_a: 0.03437, face_b: 0.06176 [19:15:19] [#06250] Loss A: 0.03887, Loss B: 0.06390 05/20/2022 19:15:20 INFO [Saved models] - Average loss since last save: face_a: 0.03335, face_b: 0.06121 [19:16:02] [#06500] Loss A: 0.03204, Loss B: 0.06094 05/20/2022 19:16:04 INFO [Saved models] - Average loss since last save: face_a: 0.03344, face_b: 0.06102 [19:16:45] [#06750] Loss A: 0.03290, Loss B: 0.05749 05/20/2022 19:16:45 INFO [Saved models] - Average loss since last save: face_a: 0.03324, face_b: 0.06002 [19:17:27] [#07000] Loss A: 0.03356, Loss B: 0.05954 05/20/2022 19:17:29 INFO [Saved models] - Average loss since last save: face_a: 0.03313, face_b: 0.06050 [19:18:10] [#07250] Loss A: 0.02756, Loss B: 0.05608 05/20/2022 19:18:10 INFO [Saved models] - Average loss since last save: face_a: 0.03261, face_b: 0.05931 [19:18:51] [#07500] Loss A: 0.03412, Loss B: 0.05743 05/20/2022 19:18:52 INFO [Saved models] - Average loss since last save: face_a: 0.03206, face_b: 0.05913 [19:19:34] [#07750] Loss A: 0.02854, Loss B: 0.05528 05/20/2022 19:19:35 INFO [Saved models] - Average loss since last save: face_a: 0.03212, face_b: 0.05822 [19:20:16] [#08000] Loss A: 0.03306, Loss B: 0.06277 05/20/2022 19:20:17 INFO [Saved models] - Average loss since last save: face_a: 0.03167, face_b: 0.05836 [19:20:58] [#08250] Loss A: 0.02742, Loss B: 0.05388 05/20/2022 19:20:59 INFO [Saved models] - Average loss since last save: face_a: 0.03128, face_b: 0.05754 [19:21:41] [#08500] Loss A: 0.02840, Loss B: 0.05149 05/20/2022 19:21:42 INFO [Saved models] - Average loss since last save: face_a: 0.03093, face_b: 0.05766
enter结束训练，模型存放在./model
视频转图像
ffmpeg -i ./source/chaoyue/s1.mp4 ./convert/before/video-%d.png
对原始视频的图像逐帧替换
python faceswap.py convert -i ./convert/before/ -o ./convert/after/ -m ./model/
图像合成视频
ffmpeg -i video-%d.png -c:v libx264 -vf "fps=25,format=yuv420p" out.mp4
标签：INFO,Loss,20,05,19,face,使用,deepfake 来源： https://www.cnblogs.com/chensongchun/p/16293840.html