Convert + Alignments - Common Problems MegaThread

Got questions or tips about the Conversion process? This is the place to discuss them.


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for discussing tips and understanding the process involved with Converting faces from your trained model.

If you are having issues with the Convert process not working as you would expect, then you should post in the Convert Support forum.

Please mark any answers that fixed your problems so others can find the solutions.

Locked
User avatar
Blackout
Posts: 2
Joined: Mon Jul 15, 2019 4:46 pm

Convert + Alignments - Common Problems MegaThread

Post by Blackout »

I am having problems trying to convert my project. When I try to convert to a video using FFMPG, it crashes complaining about not being able to find the file. When I convert using Opencv it only converts the face and not the whole scene. Any chance someone has, or can create a video tutorial of these processes please?

Code: Select all

07/20/2019 20:48:17 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000026_0.png'
07/20/2019 20:48:17 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000027_0.png'
07/20/2019 20:48:20 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000028_0.png'
07/20/2019 20:48:20 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000029_0.png'
07/20/2019 20:48:20 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000030_0.png'
07/20/2019 20:48:20 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000031_0.png'
07/20/2019 20:48:20 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000032_0.png'
07/20/2019 20:48:22 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000033_0.png'
07/20/2019 20:48:22 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000034_0.png'
07/20/2019 20:48:22 MainProcess     save_0          convert         save                      DEBUG    Writing GUI Preview image: 'D:\Faceswap\converted\.gui_preview.jpg'
07/20/2019 20:48:22 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000035_0.png'
07/20/2019 20:48:22 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000036_0.png'
07/20/2019 20:48:23 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000037_0.png'
07/20/2019 20:48:23 MainProcess     predict_faces_0 convert         predict_faces             VERBOSE  Found more than one face in an image! 'AOC 00_000038_0.png'
07/20/2019 20:48:23 MainProcess     predict_faces_0 convert         predict_faces             DEBUG    EOF Received
07/20/2019 20:48:23 MainProcess     predict_faces_0 convert         predict_faces             DEBUG    Putting EOF
07/20/2019 20:48:23 MainProcess     predict_faces_0 convert         predict_faces             DEBUG    Load queue complete
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 INFO     Muxing Audio...
07/20/2019 20:48:23 SpawnPoolWorker-4 MainThread      convert         process                   DEBUG    EOF Received
07/20/2019 20:48:23 SpawnPoolWorker-4 MainThread      convert         process                   DEBUG    Patch queue finished
07/20/2019 20:48:23 SpawnPoolWorker-4 MainThread      convert         process                   DEBUG    Putting EOF back to in_queue
07/20/2019 20:48:23 SpawnPoolWorker-4 MainThread      convert         process                   DEBUG    Completed convert process
07/20/2019 20:48:23 MainProcess     MainThread      convert         convert_images            DEBUG    Total process pools completed: 1 of 1
07/20/2019 20:48:23 MainProcess     MainThread      convert         convert_images            DEBUG    All processes completed. Joining Pool
07/20/2019 20:48:23 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Pooled Process: 'Converter.process'
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          video_file                DEBUG    D:\Faceswap\converted\AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          video_tmp_file            DEBUG    D:\Faceswap\converted\__tmp_AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          video_file                DEBUG    D:\Faceswap\converted\AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    Executing: C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    Muxing attempt: 1
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    ffmpy runtime error: `C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4` exited with status 1\n\nSTDOUT:\n\n\nSTDERR:\n
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    Muxing attempt: 2
07/20/2019 20:48:23 MainProcess     MainThread      multithreading  join                      DEBUG    Joined Pooled Process: 'Converter.process'
07/20/2019 20:48:23 MainProcess     MainThread      convert         convert_images            DEBUG    Putting EOF
07/20/2019 20:48:23 MainProcess     MainThread      convert         convert_images            DEBUG    Converted images
07/20/2019 20:48:23 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Threads: 'save'
07/20/2019 20:48:23 MainProcess     MainThread      multithreading  join                      DEBUG    Joining Thread: 'save_0'
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    ffmpy runtime error: `C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4` exited with status 1\n\nSTDOUT:\n\n\nSTDERR:\n
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    Muxing attempt: 3
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    ffmpy runtime error: `C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4` exited with status 1\n\nSTDOUT:\n\n\nSTDERR:\n
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    Muxing attempt: 4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    ffmpy runtime error: `C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4` exited with status 1\n\nSTDOUT:\n\n\nSTDERR:\n
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    Muxing attempt: 5
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 DEBUG    ffmpy runtime error: `C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4` exited with status 1\n\nSTDOUT:\n\n\nSTDERR:\n
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          mux_audio                 ERROR    There was a problem muxing audio. The output video has been created but you will need to mux audio yourself either with the EFFMpeg tool or an external application.
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          video_file                DEBUG    D:\Faceswap\converted\AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          video_tmp_file            DEBUG    D:\Faceswap\converted\__tmp_AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          ffmpeg          video_file                DEBUG    D:\Faceswap\converted\AOC_converted.mp4
07/20/2019 20:48:23 MainProcess     save_0          multithreading  run                       DEBUG    Error in thread (save_0): [WinError 2] The system cannot find the file specified: 'D:\\Faceswap\\converted\\__tmp_AOC_converted.mp4' -> 'D:\\Faceswap\\converted\\AOC_converted.mp4'
07/20/2019 20:48:23 MainProcess     MainThread      multithreading  join                      ERROR    Caught exception in thread: 'save_0'
Traceback (most recent call last):
  File "C:\Users\XXXXX\faceswap\plugins\convert\writer\ffmpeg.py", line 148, in mux_audio
    ffm.run()
  File "C:\Users\XXXXX\MiniConda3\envs\faceswap\lib\site-packages\ffmpy.py", line 105, in run
    raise FFRuntimeError(self.cmd, self.process.returncode, out[0], out[1])
ffmpy.FFRuntimeError: `C:\Users\XXXXX\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -hide_banner -nostats -v 0 -y -i D:\Faceswap\converted\__tmp_AOC_converted.mp4 -i D:\Faceswap\AOC.mp4 -map 0:0 -map 1:1 -c: copy D:\Faceswap\converted\AOC_converted.mp4` exited with status 1

STDOUT:


STDERR:


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\XXXXX\faceswap\lib\cli.py", line 122, in execute_script
    process.process()
  File "C:\Users\XXXXX\faceswap\scripts\convert.py", line 104, in process
    self.disk_io.save_thread.join()
  File "C:\Users\XXXXX\faceswap\lib\multithreading.py", line 460, in join
    raise thread.err[1].with_traceback(thread.err[2])
  File "C:\Users\XXXXX\faceswap\lib\multithreading.py", line 391, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Users\XXXXX\faceswap\scripts\convert.py", line 421, in save
    self.writer.close()
  File "C:\Users\XXXXX\faceswap\plugins\convert\writer\ffmpeg.py", line 126, in close
    self.mux_audio()
  File "C:\Users\XXXXX\faceswap\plugins\convert\writer\ffmpeg.py", line 156, in mux_audio
    os.rename(self.video_tmp_file, self.video_file)
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'D:\\Faceswap\\converted\\__tmp_AOC_converted.mp4' -> 'D:\\Faceswap\\converted\\AOC_converted.mp4'

============ System Information ============
encoding:            cp1252
git_branch:          master
git_commits:         5da91b7 Add .ico back for legacy windows installs. 09c3215 Update README.md. 5f73418 Update icons. 0a82e51 Bugflx: Correct input variable to res_block. ae259e9 Add .mpg file extension support
gpu_cuda:            9.0
gpu_cudnn:           No global version found. Check Conda packages for Conda cuDNN
gpu_devices:         GPU_0: GeForce GTX 1050 Ti
gpu_devices_active:  GPU_0
gpu_driver:          431.36
gpu_vram:            GPU_0: 4096MB
os_machine:          AMD64
os_platform:         Windows-10-10.0.18362-SP0
os_release:          10
py_command:          C:\Users\XXXXX\faceswap\faceswap.py convert -i D:/Faceswap/faces/SofiaBoutella -o D:/Faceswap/converted -l 0.4 -m D:/Faceswap/models/AOC_SofiaBoutella2 -a D:/Faceswap/faces/AOC -ref D:/Faceswap/AOC.mp4 -c avg-color -sc sharpen -M dfl_full -w ffmpeg -osc 100 -j 0 -g 1 -s -L INFO -gui
py_conda_version:    conda 4.7.9
py_implementation:   CPython
py_version:          3.6.8
py_virtual_env:      True
sys_cores:           4
sys_processor:       Intel64 Family 6 Model 60 Stepping 3, GenuineIntel
sys_ram:             Total: 8085MB, Available: 1452MB, Used: 6632MB, Free: 1452MB

=============== Pip Packages ===============
absl-py==0.7.1
astor==0.7.1
certifi==2019.6.16
cloudpickle==1.2.1
cycler==0.10.0
cytoolz==0.10.0
dask==2.1.0
decorator==4.4.0
fastcluster==1.1.25
ffmpy==0.2.2
gast==0.2.2
grpcio==1.16.1
h5py==2.9.0
imageio==2.5.0
imageio-ffmpeg==0.3.0
joblib==0.13.2
Keras==2.2.4
Keras-Applications==1.0.8
Keras-Preprocessing==1.1.0
kiwisolver==1.1.0
Markdown==3.1.1
matplotlib==2.2.2
mkl-fft==1.0.12
mkl-random==1.0.2
mkl-service==2.0.2
mock==3.0.5
networkx==2.3
numpy==1.16.2
nvidia-ml-py3==7.352.0
olefile==0.46
pathlib==1.0.1
Pillow==6.1.0
protobuf==3.8.0
psutil==5.6.3
pyparsing==2.4.0
pyreadline==2.1
python-dateutil==2.8.0
pytz==2019.1
PyWavelets==1.0.3
pywin32==223
PyYAML==5.1.1
scikit-image==0.15.0
scikit-learn==0.21.2
scipy==1.2.1
six==1.12.0
tensorboard==1.13.1
tensorflow==1.13.1
tensorflow-estimator==1.13.0
termcolor==1.1.0
toolz==0.10.0
toposort==1.5
tornado==6.0.3
tqdm==4.32.1
Werkzeug==0.15.4
wincertstore==0.2

============== Conda Packages ==============
# packages in environment at C:\Users\XXXXX\MiniConda3\envs\faceswap:
#
# Name                    Version                   Build  Channel
_tflow_select             2.1.0                       gpu  
absl-py 0.7.1 py36_0
astor 0.7.1 py36_0
blas 1.0 mkl
ca-certificates 2019.5.15 0
certifi 2019.6.16 py36_0
cloudpickle 1.2.1 py_0
cudatoolkit 10.0.130 0
cudnn 7.6.0 cuda10.0_0
cycler 0.10.0 py36h009560c_0
cytoolz 0.10.0 py36he774522_0
dask-core 2.1.0 py_0
decorator 4.4.0 py36_1
fastcluster 1.1.25 py36h830ac7b_1000 conda-forge ffmpeg 4.1.3 h6538335_0 conda-forge ffmpy 0.2.2 pypi_0 pypi freetype 2.9.1 ha9979f8_1
gast 0.2.2 py36_0
grpcio 1.16.1 py36h351948d_1
h5py 2.9.0 py36h5e291fa_0
hdf5 1.10.4 h7ebc959_0
icc_rt 2019.0.0 h0cc432a_1
icu 58.2 ha66f8fd_1
imageio 2.5.0 py36_0
imageio-ffmpeg 0.3.0 py_0 conda-forge intel-openmp 2019.4 245
joblib 0.13.2 py36_0
jpeg 9c hfa6e2cd_1001 conda-forge keras 2.2.4 0
keras-applications 1.0.8 py_0
keras-base 2.2.4 py36_0
keras-preprocessing 1.1.0 py_1
kiwisolver 1.1.0 py36ha925a31_0
libblas 3.8.0 8_mkl conda-forge libcblas 3.8.0 8_mkl conda-forge liblapack 3.8.0 8_mkl conda-forge liblapacke 3.8.0 8_mkl conda-forge libmklml 2019.0.3 0
libpng 1.6.37 h7602738_0 conda-forge libprotobuf 3.8.0 h7bd577a_0
libtiff 4.0.10 h6512ee2_1003 conda-forge libwebp 1.0.2 hfa6e2cd_2 conda-forge lz4-c 1.8.3 he025d50_1001 conda-forge markdown 3.1.1 py36_0
matplotlib 2.2.2 py36had4c4a9_2
mkl 2019.4 245
mkl-service 2.0.2 py36he774522_0
mkl_fft 1.0.12 py36h14836fe_0
mkl_random 1.0.2 py36h343c172_0
mock 3.0.5 py36_0
networkx 2.3 py_0
numpy 1.16.2 py36h19fb1c0_0
numpy-base 1.16.2 py36hc3f5095_0
nvidia-ml-py3 7.352.0 pypi_0 pypi olefile 0.46 py36_0
opencv 4.1.0 py36hb4945ee_5 conda-forge openssl 1.1.1c he774522_1
pathlib 1.0.1 py36_1
pillow 6.1.0 py36hdc69c19_0
pip 19.1.1 py36_0
protobuf 3.8.0 py36h33f27b4_0
psutil 5.6.3 py36he774522_0
pyparsing 2.4.0 py_0
pyqt 5.9.2 py36h6538335_2
pyreadline 2.1 py36_1
python 3.6.8 h9f7ef89_7
python-dateutil 2.8.0 py36_0
pytz 2019.1 py_0
pywavelets 1.0.3 py36h8c2d366_1
pywin32 223 py36hfa6e2cd_1
pyyaml 5.1.1 py36he774522_0
qt 5.9.7 hc6833c9_1 conda-forge scikit-image 0.15.0 py36ha925a31_0
scikit-learn 0.21.2 py36h6288b17_0
scipy 1.2.1 py36h29ff71c_0
setuptools 41.0.1 py36_0
sip 4.19.8 py36h6538335_0
six 1.12.0 py36_0
sqlite 3.29.0 he774522_0
tensorboard 1.13.1 py36h33f27b4_0
tensorflow 1.13.1 gpu_py36h9006a92_0
tensorflow-base 1.13.1 gpu_py36h871c8ca_0
tensorflow-estimator 1.13.0 py_0
tensorflow-gpu 1.13.1 h0d30ee6_0
termcolor 1.1.0 py36_1
tk 8.6.8 hfa6e2cd_0
toolz 0.10.0 py_0
toposort 1.5 py_3 conda-forge tornado 6.0.3 py36he774522_0
tqdm 4.32.1 py_0
vc 14.1 h0510ff6_4
vs2015_runtime 14.15.26706 h3a45250_4
werkzeug 0.15.4 py_0
wheel 0.33.4 py36_0
wincertstore 0.2 py36h7fe50ca_0
xz 5.2.4 h2fa13f4_1001 conda-forge yaml 0.1.7 hc54c509_2
zlib 1.2.11 h2fa13f4_1005 conda-forge zstd 1.4.0 hd8a0e53_0 conda-forge
Last edited by torzdf on Sat Jul 20, 2019 3:02 pm, edited 1 time in total.
User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: Convert Can't find video/Only swaps faces

Post by torzdf »

You are pointing convert at the wrong thing.

The input should be the video you want to convert NOT your faces folder

My word is final

User avatar
Blackout
Posts: 2
Joined: Mon Jul 15, 2019 4:46 pm

Re: Convert Can't find video/Only swaps faces

Post by Blackout »

Yeah, I figured it out after posting.

Thanks.

User avatar
Makawes
Posts: 3
Joined: Tue Sep 17, 2019 2:46 pm

Avoid problem with multiple faces and false positives

Post by Makawes »

hi guys

When converting a video I sometimes encounter the problem of having multiple faces in one frame. Also sometimes I encounter false positives of faces in the alignment, which cause strange blurring of the whole image in the output after it has been converted.

So I noticed there is a tool to adjust the alignment (tools -> alignment) and I guess this is how you can solve the problem. Unfortunately there are a load of options to chose from. Which option would be suitable to remove faces I don't want to alter (filter faces) and which option would could be used to remove false positives, so I can avoid the blurring of the whole image for those frames? Or is there another solution for this problem?

Thanks for your answer in advance!

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Avoid problem with multiple faces and false positives

Post by bryanlyon »

There is already a guide for this https://faceswap.dev/forum/viewtopic.php?f=5&t=27#sort . Please check that guide for the solution. I'm also moving this into the Extract forum since this is an extract question, not directly related to convert.

Last edited by torzdf on Tue Sep 17, 2019 9:50 pm, edited 1 time in total.
Reason: Link to correct section of guide
User avatar
Makawes
Posts: 3
Joined: Tue Sep 17, 2019 2:46 pm

Re: Avoid problem with multiple faces and false positives

Post by Makawes »

Thanks for the link to the guide, this is very helpful. This worked very well for my test video, although I've encountered a different error when trying to manually adjust the alignment file.

It seems that the alignment tool somehow doesn't recognize the faces in the frames. When I select "Skip Mode: No Faces" it shows me every single frame that exists and it doesnt show any markings in the image frame itself (like the landmarks for example). If I select "Skip Mode: Has Faces" the tool directly skips to the last frame, as if there were no frames containing faces at all.

Do you know what could have gone wrong here? Is this an error caused by the extract process, when the alignment file is created or are some settings for the alignment tool wrong?

Really appreciate your help!

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Avoid problem with multiple faces and false positives

Post by bryanlyon »

The manual tool will only show already extracted and identified faces. Make sure that you're giving the right alignment file for the frames that you're using. Also make sure that you're using the frames and not the face images. If the problem still happens come give more information (Like the output of the "generate" button) so we can troubleshoot.

User avatar
nick22
Posts: 4
Joined: Thu Sep 26, 2019 4:34 pm
Answers: 1

Cannot Convert

Post by nick22 »

Hello I just finished training and Iam trying to convert a video and swap faces.

I get an error when I try doing it on command line

Here's the log file.

Code: Select all

09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'tune', datatype: '<class 'str'>', default: 'none', info: 'Change settings based upon the specifics of your input:\n	 none: Don't perform any additional tuning.\n	 film: [H.264 only] Use for high quality movie content; lowers deblocking.\n	 animation: [H.264 only] Good for cartoons; uses higher deblocking and more reference frames.\n	 grain: Preserves the grain structure in old, grainy film material.\n	 stillimage: [H.264 only] Good for slideshow-like content.\n	 fastdecode: Allows faster decoding by disabling certain filters.\n	 zerolatency: Good for fast encoding and low-latency streaming.', rounding: 'None', min_max: None, choices: ['none', 'film', 'animation', 'grain', 'stillimage', 'fastdecode', 'zerolatency'], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'profile', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Limit the output to a specific H.264 profile. Don't change this unless your target device only supports a certain profile.', rounding: 'None', min_max: None, choices: ['auto', 'baseline', 'main', 'high', 'high10', 'high422', 'high444'], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.ffmpeg', title: 'level', datatype: '<class 'str'>', default: 'auto', info: '[H.264 Only] Set the encoder level, Don't change this unless your target device only supports a certain level.', rounding: 'None', min_max: None, choices: ['auto', '1', '1b', '1.1', '1.2', '1.3', '2', '2.1', '2.2', '3', '3.1', '3.2', '4', '4.1', '4.2', '5', '5.1', '5.2', '6', '6.1', '6.2'], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.ffmpeg
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: gif_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.gif_defaults
09/27/2019 15:37:38 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.gif', info: 'Options for outputting converted frames to an animated gif.')
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'fps', datatype: '<class 'int'>', default: '25', info: 'Frames per Second.', rounding: '1', min_max: (1, 60), choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'loop', datatype: '<class 'int'>', default: '0', info: 'The number of iterations. Set to 0 to loop indefinitely.', rounding: '1', min_max: (0, 100), choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'palettesize', datatype: '<class 'str'>', default: '256', info: 'The number of colors to quantize the image to. Is rounded to the nearest power of two.', rounding: 'None', min_max: None, choices: ['2', '4', '8', '16', '32', '64', '128', '256'], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.gif', title: 'subrectangles', datatype: '<class 'bool'>', default: 'False', info: 'If True, will try and optimize the GIF by storing only the rectangular parts of each frame that change with respect to the previous.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.gif
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: opencv_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.opencv_defaults
09/27/2019 15:37:38 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.opencv', info: 'Options for outputting converted frames to a series of images using OpenCV\nOpenCV can be faster than other image writers, but lacks some configuration options and formats.')
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format', rounding: 'None', min_max: None, choices: ['bmp', 'jpg', 'jp2', 'png', 'ppm'], gui_radio: True, fixed: True, group: None)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.opencv', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all.', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.opencv
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Adding defaults: (filename: pillow_defaults.py, module_path: plugins.convert.writer, plugin_type: writer
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Importing defaults module: plugins.convert.writer.pillow_defaults
09/27/2019 15:37:38 MainProcess     MainThread      config          add_section               DEBUG    Add section: (title: 'writer.pillow', info: 'Options for outputting converted frames to a series of images using Pillow\nPillow is more feature rich than OpenCV but can be slower.')
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'format', datatype: '<class 'str'>', default: 'png', info: 'Image format to use:\n	 bmp: Windows bitmap\n	 gif: Graphics Interchange Format (NB: Not animated)\n	 jpg: JPEG format\n	 jp2: JPEG 2000 format\n	 png: Portable Network Graphics\n	 ppm: Portable Pixmap Format\n	 tif: Tag Image File Format', rounding: 'None', min_max: None, choices: ['bmp', 'gif', 'jpg', 'jp2', 'png', 'ppm', 'tif'], gui_radio: True, fixed: True, group: None)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'draw_transparent', datatype: '<class 'bool'>', default: 'False', info: 'Place the swapped face on a transparent layer rather than the original frame.\nNB: This is only compatible with images saved in png or tif format. If an incompatible format is selected then the image will be saved as a png.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'optimize', datatype: '<class 'bool'>', default: 'False', info: '[gif, jpg and png only] If enabled, indicates that the encoder should make an extra pass over the image in order to select optimal encoder settings.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'gif_interlace', datatype: '<class 'bool'>', default: 'True', info: '[gif only] Set whether to save the gif as interlaced or not.', rounding: 'None', min_max: None, choices: [], gui_radio: False, fixed: True, group: settings)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'jpg_quality', datatype: '<class 'int'>', default: '75', info: '[jpg only] Set the jpg quality. 1 is worst 95 is best. Higher quality leads to larger file sizes.', rounding: '1', min_max: (1, 95), choices: [], gui_radio: False, fixed: True, group: compression)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'png_compress_level', datatype: '<class 'int'>', default: '3', info: '[png only] ZLIB compression level, 1 gives best speed, 9 gives best compression, 0 gives no compression at all. When optimize option is set to True this has no effect (it is set to 9 regardless of a value passed).', rounding: '1', min_max: (0, 9), choices: [], gui_radio: False, fixed: True, group: compression)
09/27/2019 15:37:38 MainProcess     MainThread      config          add_item                  DEBUG    Add item: (section: 'writer.pillow', title: 'tif_compression', datatype: '<class 'str'>', default: 'tiff_deflate', info: '[tif only] The desired compression method for the file.', rounding: 'None', min_max: None, choices: ['none', 'tiff_ccitt', 'group3', 'group4', 'tiff_jpeg', 'tiff_adobe_deflate', 'tiff_thunderscan', 'tiff_deflate', 'tiff_sgilog', 'tiff_sgilog24', 'tiff_raw_16'], gui_radio: False, fixed: True, group: compression)
09/27/2019 15:37:38 MainProcess     MainThread      _config         load_module               DEBUG    Added defaults: writer.pillow
09/27/2019 15:37:38 MainProcess     MainThread      config          handle_config             DEBUG    Handling config
09/27/2019 15:37:38 MainProcess     MainThread      config          check_exists              DEBUG    Config file exists: 'C:\faceswap-master\config\convert.ini'
09/27/2019 15:37:38 MainProcess     MainThread      config          load_config               VERBOSE  Loading config: 'C:\faceswap-master\config\convert.ini'
09/27/2019 15:37:38 MainProcess     MainThread      config          validate_config           DEBUG    Validating config
09/27/2019 15:37:38 MainProcess     MainThread      config          check_config_change       DEBUG    Default config has not changed
09/27/2019 15:37:38 MainProcess     MainThread      config          check_config_choices      DEBUG    Checking config choices
09/27/2019 15:37:38 MainProcess     MainThread      config          check_config_choices      DEBUG    Checked config choices
09/27/2019 15:37:38 MainProcess     MainThread      config          validate_config           DEBUG    Validated config
09/27/2019 15:37:38 MainProcess     MainThread      config          handle_config             DEBUG    Handled config
09/27/2019 15:37:38 MainProcess     MainThread      config          __init__                  DEBUG    Initialized: Config
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'format')
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'str'>, value: png)
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'draw_transparent')
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'bool'>, value: False)
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'jpg_quality')
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 75)
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Getting config item: (section: 'writer.opencv', option: 'png_compress_level')
09/27/2019 15:37:38 MainProcess     MainThread      config          get                       DEBUG    Returning item: (type: <class 'int'>, value: 3)
09/27/2019 15:37:38 MainProcess     MainThread      _base           __init__                  DEBUG    config: {'format': 'png', 'draw_transparent': False, 'jpg_quality': 75, 'png_compress_level': 3}
09/27/2019 15:37:38 MainProcess     MainThread      _base           __init__                  DEBUG    Initialized Writer
09/27/2019 15:37:38 MainProcess     MainThread      opencv          get_save_args             DEBUG    (16, 3)
09/27/2019 15:37:38 MainProcess     MainThread      convert         init_threads              DEBUG    Initializing DiskIO Threads
09/27/2019 15:37:38 MainProcess     MainThread      convert         add_queue                 DEBUG    Adding queue for task: 'load'
09/27/2019 15:37:38 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'convert_in'
09/27/2019 15:37:38 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'convert_in'
09/27/2019 15:37:38 MainProcess     MainThread      convert         add_queue                 DEBUG    Added queue for task: 'load'
09/27/2019 15:37:38 MainProcess     MainThread      convert         start_thread              DEBUG    Starting thread: 'load'
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initializing MultiThread: (target: 'load', thread_count: 1)
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initialized MultiThread: 'load'
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread(s): 'load'
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread 1 of 1: 'load_0'
09/27/2019 15:37:38 MainProcess     load_0          convert         load                      DEBUG    Load Images: Start
09/27/2019 15:37:38 MainProcess     load_0          fsmedia         load_video_frames         DEBUG    Input is video. Capturing frames
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  start                     DEBUG    Started all threads 'load': 1
09/27/2019 15:37:38 MainProcess     MainThread      convert         start_thread              DEBUG    Started thread: 'load'
09/27/2019 15:37:38 MainProcess     MainThread      convert         add_queue                 DEBUG    Adding queue for task: 'save'
09/27/2019 15:37:38 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'convert_out'
09/27/2019 15:37:38 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'convert_out'
09/27/2019 15:37:38 MainProcess     MainThread      convert         add_queue                 DEBUG    Added queue for task: 'save'
09/27/2019 15:37:38 MainProcess     MainThread      convert         start_thread              DEBUG    Starting thread: 'save'
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initializing MultiThread: (target: 'save', thread_count: 1)
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  __init__                  DEBUG    Initialized MultiThread: 'save'
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread(s): 'save'
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  start                     DEBUG    Starting thread 1 of 1: 'save_0'
09/27/2019 15:37:38 MainProcess     save_0          convert         save                      DEBUG    Save Images: Start
09/27/2019 15:37:38 MainProcess     save_0          convert         save                      DEBUG    Write preview for gui: False
09/27/2019 15:37:38 MainProcess     save_0          convert         total_count               DEBUG    573
09/27/2019 15:37:38 MainProcess     MainThread      multithreading  start                     DEBUG    Started all threads 'save': 1
09/27/2019 15:37:38 MainProcess     MainThread      convert         start_thread              DEBUG    Started thread: 'save'
09/27/2019 15:37:38 MainProcess     MainThread      convert         init_threads              DEBUG    Initialized DiskIO Threads
09/27/2019 15:37:38 MainProcess     MainThread      convert         __init__                  DEBUG    Initialized DiskIO
09/27/2019 15:37:38 MainProcess     MainThread      convert         queue_size                DEBUG    32
09/27/2019 15:37:38 MainProcess     MainThread      convert         __init__                  DEBUG    Initializing Predict: (args: Namespace(alignments_path=None, color_adjustment='avg-color', configfile=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.ScriptExecutor object at 0x000001B957900F60>>, gpus=1, input_aligned_dir=None, input_dir='C:\\faceswap-master\\video_teste\\teste.mp4', jobs=0, keep_unchanged=False, logfile=None, loglevel='INFO', mask_type='predicted', model_dir='C:\\faceswap\\saved_model_snapshot_100001_iters', nfilter=None, output_dir='C:\\faceswap-master\\aligned_faces\\converted', output_scale=100, redirect_gui=False, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='opencv'), queue_size: 32, in_queue: <queue.Queue object at 0x000001B97500B630>)
09/27/2019 15:37:38 MainProcess     MainThread      convert         get_batchsize             DEBUG    Getting batchsize
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       __init__                  DEBUG    Initializing GPUStats
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       initialize                DEBUG    OS is not macOS. Using pynvml
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       initialize                WARNING  There was an error reading from the Nvidia Machine Learning Library. Either you do not have an Nvidia GPU (in which case this warning can be ignored) or the most likely cause is incorrectly installed drivers. If this is the case, Please remove and reinstall your Nvidia drivers before reporting.Original Error: NVML Shared Library Not Found
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       get_driver                DEBUG    GPU Driver: No Nvidia driver found
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       get_devices               DEBUG    GPU Devices: []
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       get_vram                  DEBUG    GPU VRAM: []
09/27/2019 15:37:38 MainProcess     MainThread      gpu_stats       __init__                  WARNING  No GPU detected. Switching to CPU mode
09/27/2019 15:37:38 MainProcess     MainThread      convert         get_batchsize             DEBUG    Batchsize: 1
09/27/2019 15:37:38 MainProcess     MainThread      convert         get_batchsize             DEBUG    Got batchsize: 1
09/27/2019 15:37:38 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager getting: 'patch'
09/27/2019 15:37:38 MainProcess     MainThread      queue_manager   get_queue                 DEBUG    QueueManager got: 'patch'
09/27/2019 15:37:38 MainProcess     MainThread      convert         load_model                DEBUG    Loading Model
09/27/2019 15:37:38 MainProcess     MainThread      utils           get_folder                DEBUG    Requested path: 'C:\faceswap\saved_model_snapshot_100001_iters'
09/27/2019 15:37:38 MainProcess     MainThread      utils           get_folder                DEBUG    C:\faceswap\saved_model_snapshot_100001_iters does not exist
09/27/2019 15:37:38 MainProcess     MainThread      cli             execute_script            ERROR    C:\faceswap\saved_model_snapshot_100001_iters does not exist.
Traceback (most recent call last):
  File "C:\faceswap-master\lib\cli.py", line 127, in execute_script
    process = script(arguments)
  File "C:\faceswap-master\scripts\convert.py", line 47, in __init__
    self.predictor = Predict(self.disk_io.load_queue, self.queue_size, arguments)
  File "C:\faceswap-master\scripts\convert.py", line 425, in __init__
    self.model = self.load_model()
  File "C:\faceswap-master\scripts\convert.py", line 477, in load_model
    raise FaceswapError("{} does not exist.".format(self.args.model_dir))
lib.utils.FaceswapError: C:\faceswap\saved_model_snapshot_100001_iters does not exist.

============ System Information ============
encoding:            cp1252
git_branch:          Not Found
git_commits:         Not Found
gpu_cuda:            10.0
gpu_cudnn:           7.4.2
gpu_devices:         
gpu_devices_active:
gpu_driver: No Nvidia driver found gpu_vram:
os_machine: AMD64 os_platform: Windows-10-10.0.17763-SP0 os_release: 10 py_command: faceswap.py convert -i /faceswap-master/video_teste/teste.mp4 -o /faceswap-master/aligned_faces/converted -m /faceswap/saved_model_snapshot_100001_iters py_conda_version: N/A py_implementation: CPython py_version: 3.6.6 py_virtual_env: True sys_cores: 12 sys_processor: Intel64 Family 6 Model 158 Stepping 10, GenuineIntel sys_ram: Total: 32571MB, Available: 26478MB, Used: 6093MB, Free: 26478MB =============== Pip Packages =============== absl-py==0.8.0 astor==0.8.0 cycler==0.10.0 decorator==4.4.0 fastcluster==1.1.25 ffmpy==0.2.2 gast==0.3.2 google-pasta==0.1.7 grpcio==1.23.0 h5py==2.9.0 imageio==2.5.0 imageio-ffmpeg==0.3.0 joblib==0.13.2 Keras==2.2.4 Keras-Applications==1.0.8 Keras-Preprocessing==1.1.0 kiwisolver==1.1.0 Markdown==3.1.1 matplotlib==2.2.2 networkx==2.3 numpy==1.16.2 opencv-python==4.1.1.26 pathlib==1.0.1 Pillow==6.1.0 protobuf==3.9.2 psutil==5.6.3 pynvml==8.0.3 pyparsing==2.4.2 python-dateutil==2.8.0 pytz==2019.2 PyWavelets==1.0.3 pywin32==225 PyYAML==5.1.2 scikit-image==0.15.0 scikit-learn==0.21.3 scipy==1.3.1 six==1.12.0 tensorboard==1.14.0 tensorflow-estimator==1.14.0 tensorflow-gpu==1.14.0 termcolor==1.1.0 toposort==1.5 tqdm==4.36.1 Werkzeug==0.16.0 wrapt==1.11.2 ================= Configs ================== --------- .faceswap --------- backend: nvidia --------- convert.ini --------- [color.color_transfer] clip: True preserve_paper: True [color.manual_balance] colorspace: HSV balance_1: 0.0 balance_2: 0.0 balance_3: 0.0 contrast: 0.0 brightness: 0.0 [color.match_hist] threshold: 99.0 [mask.box_blend] type: gaussian distance: 11.0 radius: 5.0 passes: 1 [mask.mask_blend] type: normalized radius: 3.0 passes: 4 erosion: 0.0 [scaling.sharpen] method: unsharp_mask amount: 150 radius: 0.3 threshold: 5.0 [writer.ffmpeg] container: mp4 codec: libx264 crf: 23 preset: medium tune: none profile: auto level: auto [writer.gif] fps: 25 loop: 0 palettesize: 256 subrectangles: False [writer.opencv] format: png draw_transparent: False jpg_quality: 75 png_compress_level: 3 [writer.pillow] format: png draw_transparent: False optimize: False gif_interlace: True jpg_quality: 75 png_compress_level: 3 tif_compression: tiff_deflate --------- extract.ini --------- [align.fan] batch-size: 8 [detect.cv2_dnn] confidence: 50 [detect.mtcnn] minsize: 20 threshold_1: 0.6 threshold_2: 0.7 threshold_3: 0.7 scalefactor: 0.709 batch-size: 8 [detect.s3fd] confidence: 50 batch-size: 8 --------- gui.ini --------- [global] fullscreen: False tab: extract options_panel_width: 30 console_panel_height: 20 font: default font_size: 9 --------- train.ini --------- [global] coverage: 68.75 mask_type: none mask_blur: False icnr_init: False conv_aware_init: False subpixel_upscaling: False reflect_padding: False penalized_mask_loss: True loss_function: mae learning_rate: 5e-05 [model.dfl_h128] lowmem: False [model.dfl_sae] input_size: 128 clipnorm: True architecture: df autoencoder_dims: 0 encoder_dims: 42 decoder_dims: 21 multiscale_decoder: False [model.original] lowmem: False [model.realface] input_size: 64 output_size: 128 dense_nodes: 1536 complexity_encoder: 128 complexity_decoder: 512 [model.unbalanced] input_size: 128 lowmem: False clipnorm: True nodes: 1024 complexity_encoder: 128 complexity_decoder_a: 384 complexity_decoder_b: 512 [model.villain] lowmem: False [trainer.original] preview_images: 14 zoom_amount: 5 rotation_range: 10 shift_range: 5 flip_chance: 50 color_lightness: 30 color_ab: 8 color_clahe_chance: 50 color_clahe_max_size: 4

I have a NVIDIA GPU and I just finished a 24 hour train.

I also tried using the GUI to convert but the network did not detect any of the aligned faces from the video I had extracted.

What should I do?

User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Cannot Convert

Post by bryanlyon »

lib.utils.FaceswapError: C:\faceswap\saved_model_snapshot_100001_iters does not exist.

Don't try to use the snapshot for convert, use the standard model folder, the same one you used while training.

User avatar
Makawes
Posts: 3
Joined: Tue Sep 17, 2019 2:46 pm

Re: Avoid problem with multiple faces and false positives

Post by Makawes »

Thanks for your reply. Actually my mistake was that I swapped the folders for extracted faces and the source frames. I just tried it again and now it works as it should. Thanks again.

User avatar
winter0s
Posts: 2
Joined: Mon Oct 28, 2019 10:35 pm

Convert not swapping faces for every frame of input video.

Post by winter0s »

Hey guys,

A Faceswap rookie here! So, I followed extraction and training guides posted here and ended up with a trained model which turned out to be decent. I used every 6th image for training. When I convert, Faceswap swaps every 6 frame to Face B. What's the point of training with reduced face set then? Should I just train with all the frames from Face A? Or Am I doing it wrong? Any help will be much appreciated :)

Here is my convert setup -

Image

And here is the result-

Code: Select all

Loading...
Setting Faceswap backend to NVIDIA
10/28/2019 17:47:38 INFO     Log level set to: INFO
10/28/2019 17:47:40 INFO     Input Video: D:\_FL\InputA\t_video6334477867065278594.mp4
10/28/2019 17:47:40 INFO     Output Directory: D:\_FL\OUTPUT
10/28/2019 17:47:40 INFO     Reformatting legacy alignments file...
10/28/2019 17:47:40 INFO     Old location: 'D:\_FL\InputA\t_video6334477867065278594_alignments.json', New location: 'D:\_FL\InputA\t_video6334477867065278594_alignments.fsa'
10/28/2019 17:47:40 INFO     Reading alignments from: 'D:\_FL\InputA\t_video6334477867065278594_alignments.fsa'
10/28/2019 17:47:40 INFO     Loading Writer from Ffmpeg plugin...

10/28/2019 17:47:41 INFO     Using configuration saved in state file
10/28/2019 17:47:41 WARNING  From C:\Users\******\MiniConda3\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.\n
10/28/2019 17:47:41 WARNING  From C:\Users\******\MiniConda3\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.\n
10/28/2019 17:47:41 WARNING  From C:\Users\******\MiniConda3\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.\n
10/28/2019 17:47:41 WARNING  From C:\Users\******\MiniConda3\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:174: The name tf.get_default_session is deprecated. Please use tf.compat.v1.get_default_session instead.\n
10/28/2019 17:47:41 WARNING  From C:\Users\******\MiniConda3\envs\faceswap\lib\site-packages\keras\backend\tensorflow_backend.py:181: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.\n
10/28/2019 17:47:45 INFO     Loaded model from disk: 'D:\_FL\model'
10/28/2019 17:47:45 WARNING  From C:\Users\******\MiniConda3\envs\faceswap\lib\site-packages\keras\optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.\n
10/28/2019 17:47:45 INFO     Loading Mask from Box_Blend plugin...
10/28/2019 17:47:45 INFO     Loading Mask from Mask_Blend plugin...
10/28/2019 17:47:45 WARNING  Predicted selected, but the model was not trained with a mask. Switching to 'dfl_full'
10/28/2019 17:47:45 INFO     Loading Color from Avg_Color plugin...
10/28/2019 17:47:51 INFO     Outputting to: 'D:\_FL\OUTPUT\t_video6334477867065278594_converted.mp4'

10/28/2019 17:48:12 INFO     Muxing Audio...
10/28/2019 17:48:12 ERROR    There was a problem muxing audio. The output video has been created but you will need to mux audio yourself either with the EFFMpeg tool or an external application.
10/28/2019 17:48:12 INFO     -------------------------
10/28/2019 17:48:12 INFO     Images found:        727
10/28/2019 17:48:12 INFO     Faces detected:      144
10/28/2019 17:48:12 INFO     -------------------------
10/28/2019 17:48:12 INFO     Process Succesfully Completed. Shutting Down...
Process exited.
User avatar
bryanlyon
Site Admin
Posts: 793
Joined: Fri Jul 12, 2019 12:49 am
Answers: 44
Location: San Francisco
Has thanked: 4 times
Been thanked: 218 times
Contact:

Re: Convert not swapping faces for every frame of input video.

Post by bryanlyon »

When you convert you need to use the full alignments file that you would have made from following the extract guide, not the subset file you made in the same guide.

You don't have to train with the same files you are converting with.

User avatar
winter0s
Posts: 2
Joined: Mon Oct 28, 2019 10:35 pm

Re: Convert not swapping faces for every frame of input video.

Post by winter0s »

Thanks! I will give that a shot.

User avatar
bador
Posts: 2
Joined: Wed Oct 30, 2019 2:23 pm

Blurry face when converting (first time)

Post by bador »

Hi, this is my first time to try Faceswap. I downloaded 2 youtube videos where the people talk and the camera is mostly in front to make it easier. I followed the guides for extraction and training and have a couple of thousand imaged extracted that the software trained with around 50k iterations. It came down to around 0,03 error margin.

Now I try to use the "Convert" tab without any guide and it makes the face swap, but not a good swap and very very blurry. It aslo changes faces of other people but that's a smaller problem. Any tips?

Here is an example. The glasses are starting to get there barely and no details.

EDIT: My guess is that I trained too little. 50k iterations, but it took only a few hours with gtx 1070 + core i5 cpu. I read in the guide it can take more, like 1-7 days.

User avatar
kilroythethird
Posts: 20
Joined: Fri Jul 12, 2019 11:35 pm
Answers: 1
Has thanked: 2 times
Been thanked: 10 times

Re: Blurry face when converting (first time)

Post by kilroythethird »

Yes, 50k iterations is highly likely to few.
How long you need to train depends on the model, the batchsize and your dataset.

Also it looks like one of your datasets has glasses. This is really hard to get right (probably not possible with satisfactory results atm to be honest).

To remove unwanted faces follow the "sorting" and "Clean the Alignments File" section in: viewtopic.php?f=5&t=27#sort

that amd guy

User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: Blurry face when converting (first time)

Post by torzdf »

It also looks like you haven't generated an alignments file for the source video, so it's using the vastly inferior on-the-fly detector for converting.

My word is final

User avatar
bador
Posts: 2
Joined: Wed Oct 30, 2019 2:23 pm

Re: Blurry face when converting (first time)

Post by bador »

Thank you for the replies. I have alignment files (if I use them correctly) and now have 90k iterations and around 0.025 loss on both.
I took Snowden with glasses as a model, but as you said it might be hard to get the glasses right. I will try later with other models instead.

Starting to look a bit better now with 90k iterations at least:

VS original guy:

I will try the guide to sort and clean to get rid of other peoples faces changing later as well.

User avatar
rokh
Posts: 2
Joined: Sat Nov 09, 2019 8:40 pm

How to convert after training

Post by rokh »

OK so I trained the models, using extracted frames one set (A) for source Video and another set (B) for the swap. Training took longer than expected (over 20 hrs.) and I had to terminate early and then tried again, and again I had to terminate after several hours. 1th question: Is it OK to use the data from a terminated early training or do you have to have a completely finished training which could take days?
So I went ahead and used the early terminated training data to try to convert my project. So I put in my input directory path and my output directory path and specified my model directory (which again contained logs from the early terminated training) and I used all the default settings except I changed the Writer to Ffmpeg and I checked the box next to Swap model. The resulted converted video was the original video with the faces blured and the second try was even worse.
Unfortunately there isn't a thoroughly explained Convert process explanation on the forum like the other processes such as extraction and training which are clearly explained in their own chapters. And it also puzzles me what happens to my B folder containing the pictures that I like to replace the originals with because during conversion I don't see a file path for those and I am just guessing that the Model directory would lead the program to that file.
Having said all that my 2nd question is: "what exactly am I not doing right?"

User avatar
mymooo3
Posts: 3
Joined: Tue Nov 12, 2019 3:51 am

How to replace an specific person's face from clip with many people??

Post by mymooo3 »

Hello. I was working on a faceswap and was replacing a person's face (B) into a clip but there are quite many faces involved.

I extracted and removed the unwanted faces and left only the face (A) that I wanted to replace.

After converting, all of the faces involved in the clip were also replaced by the face B (but untrained so its like unfinished and glitchy) But the face A was properly trained and replaced to my satisfactory.

How can I convert it without the other faces getting affected? Theres a scene in a clip where two of them in one shot

Thank you

User avatar
torzdf
Posts: 2649
Joined: Fri Jul 12, 2019 12:53 am
Answers: 159
Has thanked: 128 times
Been thanked: 622 times

Re: How to replace an specific person's face from clip with many people??

Post by torzdf »

You need to clean the alignments file. Whilst you have removed the faces, they still exist in the Alignments file. See here:
viewtopic.php?f=5&t=27#clean

My word is final

Locked