Convert + Alignments - Common Problems MegaThread
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.
- mikericer33
- Posts: 7
- Joined: Sun Mar 29, 2020 1:00 pm
- mikericer33
- Posts: 7
- Joined: Sun Mar 29, 2020 1:00 pm
Please make a convert guide !
Hi Guys
I can`t get my head around this convert thingy. I dont know where to put wich file or folder. I just wanted to convert after around 60000 iterations to check the quality. I was just getting "no alignment found for data_dst_003602.png, skipping" Unfortunatly with all the back and forth and messing with files to solve this i messed up my training also. So now i can start again with training. That sucks. Or maybe you can update the hints in the GUI to make it easier ... yeah i know i am not the brightest
Re: Please make a convert guide !
I think I know what you did.
so you train your model.
Then you want to apply that model to a video...
You (currently)have to extract the alignments for every frame in the video. Extract Every N = 1. That generated alignments file is the one you need to give to the convert process.
Then you need to clean that alignments file, about same as in the guide for extracting training sets but every frame (read the guide again).
Delete all the faces you don't want to try and convert, other actors, random pieces of wood the detector saw a face in, for example. Then delete faces (once again, as the guide shows you)and clean up the alignments file..
Beware , long videos make for lots of alignments and 1000's of extracted faces.
If the preview window looks OK, and Tools ->preview, THEN Ill make a couple 10-12 sec clips, and convert those to get a real good preview before I do the final.
I dunno what I'm doing
2X RTX 3090 : RTX 3080 : RTX: 2060 : 2x RTX 2080 Super : Ghetto 1060
Problem With Audio
So I just made a success of Convertion, I used ffmpeg tools build the vedio from pictures, but the video doesn't have audio (of course). Now I'm considering to use ffmpeg tools to solve this problem, but this is really a hassle, right? So what is the official solution about the audio problem, it does not seem to be written on the document.
Re: Problem With Audio
You can do this with the effmpeg tool and the "mux-audio" option.
input - Your converted video
reference video - The original video (which has the audio you want to put on to your convert)
My word is final
Which input/output directories for --swap-model?
Hi,
I have tried several options but I seem to miss something, so would be very grateful for clear answers.
When I add the option --swap-model to an otherwise fine working convert command,, it always throws errors.
So my questions are:
When I do
Code: Select all
convert -i dirA (images for A) -o dirB (images for B)
Then do I have to do:
A)Code: Select all
convert -i dirA (images for A) -o dirB (images for B) --swap-model
OR
B)Code: Select all
convert -i dirB (images for B) -o dirA (images for A) --swap-model
What does the following exception mean? Wrong model?
Code: Select all
ERROR Got Exception on main handler: line 484, in load\n network = load_model(...)
Re: Which input/output directories for --swap-model?
Ha, I just found and solved the problem:
The model was not the full path the model - I had to add the folder of the trainer (in this case: "/Original"), and then it worked.
This explains the thrown error by load_model() of course.
Thanks for your help anyway @[mention]torzdf[/mention]
CRITICAL An unexpected crash has occurred. when convert
Code: Select all
04/10/2020 00:22:19 MainProcess MainThread logger log_setup INFO Log level set to: INFO
04/10/2020 00:22:19 MainProcess MainThread cli execute_script DEBUG Executing: convert. PID: 24024
04/10/2020 00:22:21 MainProcess MainThread cli test_for_tf_version DEBUG Installed Tensorflow Version: 1.15
04/10/2020 00:22:22 MainProcess MainThread queue_manager __init__ DEBUG Initializing QueueManager
04/10/2020 00:22:22 MainProcess MainThread queue_manager __init__ DEBUG Initialized QueueManager
04/10/2020 00:22:22 MainProcess MainThread convert __init__ DEBUG Initializing Convert: (args: Namespace(alignments_path='D:\\CARAS\\OUTPUT\\Training_snapshot_50001_iters\\dfl_h128_state.json', allow_growth=False, colab=False, color_adjustment='avg-color', configfile=None, filter=None, frame_ranges=None, func=<bound method ScriptExecutor.execute_script of <lib.cli.ScriptExecutor object at 0x000001BC896849C8>>, gpus=1, input_aligned_dir=None, input_dir='D:\\CARAS\\Starlord.mp4', jobs=0, keep_unchanged=False, logfile=None, loglevel='INFO', mask_type='predicted', model_dir='D:\\CARAS\\OUTPUT\\Training_snapshot_75001_iters\\dfl_h128_logs\\a', nfilter=None, on_the_fly=False, output_dir='D:\\', output_scale=100, redirect_gui=True, ref_threshold=0.4, reference_video=None, scaling='none', singleprocess=False, swap_model=False, trainer=None, writer='ffmpeg'))
04/10/2020 00:22:22 MainProcess MainThread image __init__ DEBUG Initializing ImagesLoader: (path: D:\CARAS\Starlord.mp4, queue_size: 8, fast_count: True, skip_list: None, count: None)
04/10/2020 00:22:22 MainProcess MainThread image __init__ DEBUG Initializing ImagesLoader: (path: D:\CARAS\Starlord.mp4, queue_size: 8, args: None)
04/10/2020 00:22:22 MainProcess MainThread queue_manager get_queue DEBUG QueueManager getting: 'ImagesLoader'
04/10/2020 00:22:22 MainProcess MainThread queue_manager add_queue DEBUG QueueManager adding: (name: 'ImagesLoader', maxsize: 8)
04/10/2020 00:22:22 MainProcess MainThread queue_manager add_queue DEBUG QueueManager added: (name: 'ImagesLoader')
04/10/2020 00:22:22 MainProcess MainThread queue_manager get_queue DEBUG QueueManager got: 'ImagesLoader'
04/10/2020 00:22:22 MainProcess MainThread image _check_for_video DEBUG Input 'D:\CARAS\Starlord.mp4' is_video: True
04/10/2020 00:22:22 MainProcess MainThread image _get_fps DEBUG 60.0
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG filename: D:\CARAS\Starlord.mp4, fast: True
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG FFMPEG Command: 'C:\Users\cvisu\MiniConda3\envs\faceswap\Library\bin\ffmpeg.exe -i D:\CARAS\Starlord.mp4 -map 0:v:0 -c copy -f null -'
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG Duration line: Duration: 00:00:52.69, start: 0.000000, bitrate: 10116 kb/s
04/10/2020 00:22:22 MainProcess MainThread utils convert_to_secs DEBUG from time: ('00', '00', '52.69')
04/10/2020 00:22:22 MainProcess MainThread utils convert_to_secs DEBUG to secs: 52.69
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG duration: 52
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG frame line: frame= 3158 fps=0.0 q=-1.0 Lsize=N/A time=00:00:52.60 bitrate=N/A speed=1.51e+03x
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG Initializing tqdm
04/10/2020 00:22:22 MainProcess MainThread utils convert_to_secs DEBUG from time: ('00', '00', '52.60')
04/10/2020 00:22:22 MainProcess MainThread utils convert_to_secs DEBUG to secs: 52.6
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG frames: 3158, vid_time: 52
04/10/2020 00:22:22 MainProcess MainThread image count_frames DEBUG Return code: 0, frames: 3158
04/10/2020 00:22:22 MainProcess MainThread image _get_count_and_filelist DEBUG count: 3158
04/10/2020 00:22:22 MainProcess MainThread fsmedia __init__ DEBUG Initializing Alignments: (is_extract: False, input_is_video: True)
04/10/2020 00:22:22 MainProcess MainThread fsmedia _set_folder_filename DEBUG Alignments File provided: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.json'
04/10/2020 00:22:22 MainProcess MainThread fsmedia _set_folder_filename DEBUG Setting Alignments: (folder: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters' filename: 'dfl_h128_state.json')
04/10/2020 00:22:22 MainProcess MainThread alignments __init__ DEBUG Initializing Alignments: (folder: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters', filename: 'dfl_h128_state.json')
04/10/2020 00:22:22 MainProcess MainThread serializer get_serializer DEBUG <lib.serializer._PickleSerializer object at 0x000001BC927C2F08>
04/10/2020 00:22:22 MainProcess MainThread serializer get_serializer DEBUG <lib.serializer._CompressedSerializer object at 0x000001BC927C90C8>
04/10/2020 00:22:22 MainProcess MainThread alignments _get_location DEBUG Getting location: (folder: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters', filename: 'dfl_h128_state.json')
04/10/2020 00:22:22 MainProcess MainThread alignments _update_file_format INFO Reformatting legacy alignments file...
04/10/2020 00:22:22 MainProcess MainThread alignments _update_file_format INFO Old location: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.json', New location: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa'
04/10/2020 00:22:22 MainProcess MainThread serializer get_serializer_from_filename DEBUG filename: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.json'
04/10/2020 00:22:22 MainProcess MainThread serializer get_serializer_from_filename DEBUG extension: '.json'
04/10/2020 00:22:22 MainProcess MainThread serializer get_serializer_from_filename DEBUG <lib.serializer._JSONSerializer object at 0x000001BC927C2D08>
04/10/2020 00:22:22 MainProcess MainThread serializer load DEBUG filename: D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.json
04/10/2020 00:22:22 MainProcess MainThread serializer load DEBUG stored data type: <class 'bytes'>
04/10/2020 00:22:22 MainProcess MainThread serializer unmarshal DEBUG data type: <class 'bytes'>
04/10/2020 00:22:22 MainProcess MainThread serializer unmarshal DEBUG returned data type: <class 'dict'>
04/10/2020 00:22:22 MainProcess MainThread serializer load DEBUG data type: <class 'dict'>
04/10/2020 00:22:22 MainProcess MainThread serializer save DEBUG filename: D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa, data type: <class 'dict'>
04/10/2020 00:22:22 MainProcess MainThread serializer _check_extension DEBUG Original filename: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa', final filename: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa'
04/10/2020 00:22:22 MainProcess MainThread serializer marshal DEBUG data type: <class 'dict'>
04/10/2020 00:22:22 MainProcess MainThread serializer marshal DEBUG returned data type: <class 'bytes'>
04/10/2020 00:22:22 MainProcess MainThread alignments _get_location DEBUG Updated legacy alignments. New filename: 'dfl_h128_state.fsa'
04/10/2020 00:22:22 MainProcess MainThread alignments _get_location DEBUG File extension set from serializer: 'fsa'
04/10/2020 00:22:22 MainProcess MainThread alignments _get_location VERBOSE Alignments filepath: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa'
04/10/2020 00:22:22 MainProcess MainThread alignments _load DEBUG Loading alignments
04/10/2020 00:22:22 MainProcess MainThread alignments _load INFO Reading alignments from: 'D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa'
04/10/2020 00:22:22 MainProcess MainThread serializer load DEBUG filename: D:\CARAS\OUTPUT\Training_snapshot_50001_iters\dfl_h128_state.fsa
04/10/2020 00:22:22 MainProcess MainThread serializer load DEBUG stored data type: <class 'bytes'>
04/10/2020 00:22:22 MainProcess MainThread serializer unmarshal DEBUG data type: <class 'bytes'>
04/10/2020 00:22:22 MainProcess MainThread serializer unmarshal DEBUG returned data type: <class 'dict'>
04/10/2020 00:22:22 MainProcess MainThread serializer load DEBUG data type: <class 'dict'>
04/10/2020 00:22:22 MainProcess MainThread alignments _load DEBUG Loaded alignments
04/10/2020 00:22:22 MainProcess MainThread alignments _has_legacy_structure DEBUG legacy structure: False
04/10/2020 00:22:22 MainProcess MainThread alignments _has_legacy_landmarksxy DEBUG checking legacy landmarksXY
Traceback (most recent call last):
File "D:\Users\cvisu\faceswap\lib\cli.py", line 127, in execute_script
process = script(arguments)
File "D:\Users\cvisu\faceswap\scripts\convert.py", line 56, in __init__
self._alignments = Alignments(self._args, False, self._images.is_video)
File "D:\Users\cvisu\faceswap\scripts\fsmedia.py", line 71, in __init__
super().__init__(folder, filename=filename)
File "D:\Users\cvisu\faceswap\lib\alignments.py", line 42, in __init__
self._update_legacy()
File "D:\Users\cvisu\faceswap\lib\alignments.py", line 500, in _update_legacy
if self._has_legacy_landmarksxy():
File "D:\Users\cvisu\faceswap\lib\alignments.py", line 599, in _has_legacy_landmarksxy
for val in self._data.values()
File "D:\Users\cvisu\faceswap\lib\alignments.py", line 600, in <genexpr>
for alignment in val["faces"]
TypeError: string indices must be integers
============ System Information ============
encoding: cp1252
git_branch: master
git_commits: 9461c59 Bugfixes and minor updates: - Remove preview option from effmpeg tool - Remove json filetypes from GUI for alignments files - Capture and raise empty timelapse folder errors - Move convert to use centralized ImagesLoader. f126dc4 Documentation Update. 10115de Update .gitignore. 8bc00d6 Documentation update. 8412941 Update Travis Test for Masker
gpu_cuda: 10.2
gpu_cudnn: No global version found. Check Conda packages for Conda cuDNN
gpu_devices: GPU_0: GeForce GTX 1050
gpu_devices_active: GPU_0
gpu_driver: 445.75
gpu_vram: GPU_0: 4096MB
os_machine: AMD64
os_platform: Windows-10-10.0.18362-SP0
os_release: 10
py_command: D:\Users\cvisu\faceswap\faceswap.py convert -i D:/CARAS/Starlord.mp4 -o D:/ -al D:/CARAS/OUTPUT/Training_snapshot_50001_iters/dfl_h128_state.json -m D:/CARAS/OUTPUT/Training_snapshot_75001_iters/dfl_h128_logs/a -c avg-color -M predicted -sc none -w ffmpeg -osc 100 -l 0.4 -j 0 -g 1 -L INFO -gui
py_conda_version: conda 4.8.3
py_implementation: CPython
py_version: 3.7.7
py_virtual_env: True
sys_cores: 8
sys_processor: Intel64 Family 6 Model 158 Stepping 9, GenuineIntel
sys_ram: Total: 16269MB, Available: 10524MB, Used: 5744MB, Free: 10524MB
=============== Pip Packages ===============
absl-py==0.9.0
asn1crypto==1.3.0
astor==0.8.0
blinker==1.4
cachetools==3.1.1
certifi==2019.11.28
cffi==1.14.0
chardet==3.0.4
click==7.1.1
cloudpickle==1.3.0
cryptography==2.8
cycler==0.10.0
cytoolz==0.10.1
dask==2.13.0
decorator==4.4.2
fastcluster==1.1.26
ffmpy==0.2.2
gast==0.2.2
google-auth==1.11.2
google-auth-oauthlib==0.4.1
google-pasta==0.2.0
grpcio==1.27.2
h5py==2.9.0
idna==2.9
imageio==2.6.1
imageio-ffmpeg==0.4.1
joblib==0.14.1
Keras==2.2.4
Keras-Applications==1.0.8
Keras-Preprocessing==1.1.0
kiwisolver==1.1.0
Markdown==3.1.1
matplotlib==3.1.3
mkl-fft==1.0.15
mkl-random==1.1.0
mkl-service==2.3.0
networkx==2.4
numpy==1.17.4
nvidia-ml-py3==7.352.1
oauthlib==3.1.0
olefile==0.46
opencv-python==4.1.2.30
opt-einsum==3.1.0
pathlib==1.0.1
Pillow==6.2.1
protobuf==3.11.4
psutil==5.7.0
pyasn1==0.4.8
pyasn1-modules==0.2.7
pycparser==2.20
PyJWT==1.7.1
pyOpenSSL==19.1.0
pyparsing==2.4.6
pyreadline==2.1
PySocks==1.7.1
python-dateutil==2.8.1
pytz==2019.3
PyWavelets==1.1.1
pywin32==227
PyYAML==5.3.1
requests==2.23.0
requests-oauthlib==1.3.0
rsa==4.0
scikit-image==0.16.2
scikit-learn==0.22.1
scipy==1.4.1
six==1.14.0
tensorboard==2.1.0
tensorflow==1.15.0
tensorflow-estimator==1.15.1
termcolor==1.1.0
toolz==0.10.0
toposort==1.5
tornado==6.0.4
tqdm==4.44.1
urllib3==1.25.8
Werkzeug==0.16.1
win-inet-pton==1.1.0
wincertstore==0.2
wrapt==1.12.1
============== Conda Packages ==============
# packages in environment at C:\Users\cvisu\MiniConda3\envs\faceswap:
#
# Name Version Build Channel
_tflow_select 2.1.0 gpu
absl-py 0.9.0 py37_0
asn1crypto 1.3.0 py37_0
astor 0.8.0 py37_0
blas 1.0 mkl
blinker 1.4 py37_0
ca-certificates 2020.1.1 0
cachetools 3.1.1 py_0
certifi 2019.11.28 py37_1
cffi 1.14.0 py37h7a1dbc1_0
chardet 3.0.4 py37_1003
click 7.1.1 py_0
cloudpickle 1.3.0 py_0
cryptography 2.8 py37h7a1dbc1_0
cudatoolkit 10.0.130 0
cudnn 7.6.5 cuda10.0_0
cycler 0.10.0 py37_0
cytoolz 0.10.1 py37he774522_0
dask-core 2.13.0 py_0
decorator 4.4.2 py_0
fastcluster 1.1.26 py37he350917_0 conda-forge
ffmpeg 4.2 h6538335_0 conda-forge
ffmpy 0.2.2 pypi_0 pypi
freetype 2.9.1 ha9979f8_1
gast 0.2.2 py37_0
git 2.23.0 h6bb4b03_0
google-auth 1.11.2 py_0
google-auth-oauthlib 0.4.1 py_2
google-pasta 0.2.0 py_0
grpcio 1.27.2 py37h351948d_0
h5py 2.9.0 py37h5e291fa_0
hdf5 1.10.4 h7ebc959_0
icc_rt 2019.0.0 h0cc432a_1
icu 58.2 ha66f8fd_1
idna 2.9 py_1
imageio 2.6.1 py37_0
imageio-ffmpeg 0.4.1 py_0 conda-forge
intel-openmp 2020.0 166
joblib 0.14.1 py_0
jpeg 9b hb83a4c4_2
keras 2.2.4 0
keras-applications 1.0.8 py_0
keras-base 2.2.4 py37_0
keras-preprocessing 1.1.0 py_1
kiwisolver 1.1.0 py37ha925a31_0
libpng 1.6.37 h2a8f88b_0
libprotobuf 3.11.4 h7bd577a_0
libtiff 4.1.0 h56a325e_0
markdown 3.1.1 py37_0
matplotlib 3.1.1 py37hc8f65d3_0
matplotlib-base 3.1.3 py37h64f37c6_0
mkl 2020.0 166
mkl-service 2.3.0 py37hb782905_0
mkl_fft 1.0.15 py37h14836fe_0
mkl_random 1.1.0 py37h675688f_0
networkx 2.4 py_0
numpy 1.17.4 py37h4320e6b_0
numpy-base 1.17.4 py37hc3f5095_0
nvidia-ml-py3 7.352.1 pypi_0 pypi
oauthlib 3.1.0 py_0
olefile 0.46 py37_0
opencv-python 4.1.2.30 pypi_0 pypi
openssl 1.1.1f he774522_0
opt_einsum 3.1.0 py_0
pathlib 1.0.1 py37_1
pillow 6.2.1 py37hdc69c19_0
pip 20.0.2 py37_1
protobuf 3.11.4 py37h33f27b4_0
psutil 5.7.0 py37he774522_0
pyasn1 0.4.8 py_0
pyasn1-modules 0.2.7 py_0
pycparser 2.20 py_0
pyjwt 1.7.1 py37_0
pyopenssl 19.1.0 py37_0
pyparsing 2.4.6 py_0
pyqt 5.9.2 py37h6538335_2
pyreadline 2.1 py37_1
pysocks 1.7.1 py37_0
python 3.7.7 h60c2a47_0_cpython
python-dateutil 2.8.1 py_0
python_abi 3.7 1_cp37m conda-forge
pytz 2019.3 py_0
pywavelets 1.1.1 py37he774522_0
pywin32 227 py37he774522_1
pyyaml 5.3.1 py37he774522_0
qt 5.9.7 vc14h73c81de_0
requests 2.23.0 py37_0
requests-oauthlib 1.3.0 py_0
rsa 4.0 py_0
scikit-image 0.16.2 py37h47e9c7a_0
scikit-learn 0.22.1 py37h6288b17_0
scipy 1.4.1 py37h9439919_0
setuptools 46.1.3 py37_0
sip 4.19.8 py37h6538335_0
six 1.14.0 py37_0
sqlite 3.31.1 he774522_0
tensorboard 2.1.0 py3_0
tensorflow 1.15.0 gpu_py37hc3743a6_0
tensorflow-base 1.15.0 gpu_py37h1afeea4_0
tensorflow-estimator 1.15.1 pyh2649769_0
tensorflow-gpu 1.15.0 h0d30ee6_0
termcolor 1.1.0 py37_1
tk 8.6.8 hfa6e2cd_0
toolz 0.10.0 py_0
toposort 1.5 py_3 conda-forge
tornado 6.0.4 py37he774522_1
tqdm 4.44.1 py_0
urllib3 1.25.8 py37_0
vc 14.1 h0510ff6_4
vs2015_runtime 14.16.27012 hf0eaf9b_1
werkzeug 0.16.1 py_0
wheel 0.34.2 py37_0
win_inet_pton 1.1.0 py37_0
wincertstore 0.2 py37_0
wrapt 1.12.1 py37he774522_1
xz 5.2.4 h2fa13f4_4
yaml 0.1.7 hc54c509_2
zlib 1.2.11 h62dcd97_3
zstd 1.3.7 h508b16e_0
================= 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
kernel_size: 3
passes: 4
threshold: 4
erosion: 0.0
[scaling.sharpen]
method: unsharp_mask
amount: 150
radius: 0.3
threshold: 5.0
[writer.ffmpeg]
container: mp4
codec: libx264
crf: 16
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 ---------
[global]
allow_growth: False
[align.fan]
batch-size: 12
[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: 70
batch-size: 4
[mask.unet_dfl]
batch-size: 8
[mask.vgg_clear]
batch-size: 6
[mask.vgg_obstructed]
batch-size: 2
--------- gui.ini ---------
[global]
fullscreen: False
tab: extract
options_panel_width: 30
console_panel_height: 20
icon_size: 14
font: default
font_size: 9
autosave_last_session: always
timeout: 120
auto_load_model_stats: True
--------- train.ini ---------
[global]
coverage: 75.0
mask_type: none
mask_blur_kernel: 3
mask_threshold: 4
learn_mask: 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: True
[model.dfl_sae]
input_size: 128
clipnorm: True
architecture: df
autoencoder_dims: 0
encoder_dims: 42
decoder_dims: 21
multiscale_decoder: False
[model.dlight]
features: best
details: fast
output_size: 256
[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 get this error when I am going to convert. I'm noob whith phyton and need help. ¿What can i do?
Thank You So Much.
- bryanlyon
- Site Admin
- Posts: 793
- Joined: Fri Jul 12, 2019 12:49 am
- Location: San Francisco
- Has thanked: 4 times
- Been thanked: 218 times
- Contact:
Re: CRITICAL An unexpected crash has occurred. when convert
py_command: D:\Users\cvisu\faceswap\faceswap.py convert -i D:/CARAS/Starlord.mp4 -o D:/ -al D:/CARAS/OUTPUT/Training_snapshot_50001_iters/dfl_h128_state.json -m D:/CARAS/OUTPUT/Training_snapshot_75001_iters/dfl_h128_logs/a -c avg-color -M predicted -sc none -w ffmpeg -osc 100 -l 0.4 -j 0 -g 1 -L INFO -gui
Several problems here:
1: You're using the wrong file for "alignments". That should be the .fsa created during the extract process on the video you're swapping into.
2: You're using the wrong folder for "Model". It should be the same folder as you trained to -- Presumably D:/CARAS/OUTPUT/Training .
Convert Skips PNGs
Hi I first of all say thank you and tell tham I am delighted with this program its simply awesome. !!!!!
I have a problem when I try to convert I receive this msg after training....Could you please let me know what I am doing wrong?
No alignment found hd_000003.png, skipping
C:\Users\GR\MiniConda3\envs\faceswap\python.exe C:\Users\GR\faceswap\faceswap.py convert -i C:/Users/GR/faceswap/WILL/video-hd.mp4 -o C:/Users/GR/faceswap/WILL/vid1 -al C:/Users/GR/faceswap/WILL/TRAINING/Alignment.fsa -m C:/Users/GR/faceswap/WILL/MODEL1 -c avg-color -M extended -sc none -w ffmpeg -osc 100 -l 0.4 -j 0 -g 1 -L INFO
Many thanks in advance!!
Re: Convert Skips PNGs
OK so I have to do a full aligment of the Video. Wth all frames or ok with an Interval?
When I do Sort, rename and Clean thats for Training only. Right?
Then for convert original alignment (keeps the original as a back up I think)and original video and MODEL folder. Right?
Many thanks for prompt response!!!!!!!!!!! and Help!!
Re: Convert Skips PNGs
Has to be every frame.
The alignments file associated with the video for conversion tells the process where all the faces are in the video.
You will have to clean the alignments file, as otherwise it will swap ALL faces in the video (and false positives) regardless of who your subject is.
My word is final
Re: Convert Skips PNGs
[mention]torzdf[/mention]
Ive made a new test and now works great!!!
Great Job Guys!!! Great Job!!!! This program is Awesome!
no alignment found for
Hi there guys
Im getting a lot of no alignment found for 'image-name'.png skipping.
I've tried merging all aligments files I could still get that an the video is not converted.
Any ideas?