Read the FAQs and search the forum before posting a new topic.
This forum is for reporting errors with the Training process. If you want to get tips, or better understand the Training process, then you should look in the Training Discussion forum.
Please mark any answers that fixed your problems so others can find the solutions.
While training it uses my cpu and not using my gpu, or it is using my gpu but it's not fast so am i expecting too much? how can I avoid this?
My pc specs are;
NVIDIA RTX 4070 LAPTOP 8GB VRAM
32GB RAM
12TH GEN INTEL I7-12650H 16 CPUs 2.3ghz
I'm a beginner, I would appreciate any help and tips about faceswap:)
Hello, was wondering if anyone can check my issue. I've applied the steps mentioned in the FAQ and check as well as old threads with the same issue but it seems Faceswap just doesn't seem to use my GPU during extraction and training. I tried running deepfacelab separately to compare and the SAEHD training batch file there uses my GPU just fine. Any idea on this one?
Update faceswap: I tried manually installing 11.2 since I got the warning below but doesn't seem to do anything. Altho nvidia-smi says I have CUDA 12.7.
Code: Select all
12/29/2024 22:01:04 INFO Checking for updates...
12/29/2024 22:01:06 INFO Faceswap is up to date.
12/29/2024 22:01:06 INFO Updating dependencies...
12/29/2024 22:01:06 INFO Setup in Windows 10
12/29/2024 22:01:06 INFO Installed Python: 3.10.16 64bit
12/29/2024 22:01:06 INFO Running in Conda
12/29/2024 22:01:06 INFO Running in a Virtual Environment
12/29/2024 22:01:06 INFO Encoding: cp1252
12/29/2024 22:01:06 INFO Installed pip: 24.2
12/29/2024 22:01:06 INFO Adding conda required package 'zlib-wapi' for backend 'nvidia')
12/29/2024 22:01:06 INFO Adding conda required package '['cudatoolkit>=11.2,<11.3', 'cudnn>=8.1,<8.2']' for backend 'nvidia')
12/29/2024 22:01:08 INFO Installing Required Python Packages. This may take some time...
12/29/2024 22:01:08 INFO Installing Required Conda Packages. This may take some time...
12/29/2024 22:01:08 INFO Installing cudatoolkit>=11.2,<11.3 cudnn>=8.1,<8.2
12/29/2024 22:01:11 WARNING Couldn't install ['"cudatoolkit>=11.2,<11.3"', '"cudnn>=8.1,<8.2"'] with Conda. Please install this package manually
12/29/2024 22:01:11 INFO Dependencies updatedSystem info:
Code: Select all
============ System Information ============
backend: nvidia
encoding: cp1252
git_branch: master
git_commits: 41b61f9 Update README.md
gpu_cuda: No global version found. Check Conda packages for Conda Cuda
gpu_cudnn: No global version found. Check Conda packages for Conda cuDNN
gpu_devices: GPU_0: NVIDIA GeForce RTX 4060 Ti
gpu_devices_active: GPU_0
gpu_driver: 566.36
gpu_vram: GPU_0: 8188MB (7336MB free)
os_machine: AMD64
os_platform: Windows-10-10.0.22631-SP0
os_release: 10
py_command: C:\faceswap/faceswap.py gui
py_conda_version: conda 24.11.2
py_implementation: CPython
py_version: 3.10.16
py_virtual_env: True
sys_cores: 16
sys_processor: Intel64 Family 6 Model 183 Stepping 1, GenuineIntel
sys_ram: Total: 32603MB, Available: 23875MB, Used: 8727MB, Free: 23878MB
=============== Pip Packages ===============
absl-py==2.1.0
astunparse==1.6.3
cachetools==5.5.0
certifi==2024.12.14
charset-normalizer==3.4.1
colorama==0.4.6
contourpy==1.3.1
cycler==0.12.1
fastcluster==1.2.6
ffmpy==0.5.0
flatbuffers==24.12.23
fonttools==4.55.3
gast==0.4.0
google-auth==2.37.0
google-auth-oauthlib==0.4.6
google-pasta==0.2.0
grpcio==1.68.1
h5py==3.12.1
idna==3.10
imageio==2.36.1
imageio-ffmpeg==0.5.1
joblib==1.4.2
keras==2.10.0
Keras-Preprocessing==1.1.2
kiwisolver==1.4.8
libclang==18.1.1
Markdown==3.7
MarkupSafe==3.0.2
matplotlib==3.10.0
numexpr==2.10.2
numpy==1.26.4
nvidia-ml-py==12.560.30
oauthlib==3.2.2
opencv-python==4.10.0.84
opt_einsum==3.4.0
packaging==24.2
Pillow==9.5.0
protobuf==3.19.6
psutil==6.1.1
pyasn1==0.6.1
pyasn1_modules==0.4.1
pyparsing==3.2.0
python-dateutil==2.9.0.post0
pywin32==308
pywinpty @ file:///C:/ci_310/pywinpty_1644230983541/work/target/wheels/pywinpty-2.0.2-cp310-none-win_amd64.whl
requests==2.32.3
requests-oauthlib==2.0.0
rsa==4.9
scikit-learn==1.6.0
scipy==1.14.1
six==1.17.0
tensorboard==2.10.1
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
tensorflow==2.10.1
tensorflow-estimator==2.10.0
tensorflow-io-gcs-filesystem==0.31.0
termcolor==2.5.0
threadpoolctl==3.5.0
tqdm==4.67.1
typing_extensions==4.12.2
urllib3==2.3.0
Werkzeug==3.1.3
wrapt==1.17.0
============== Conda Packages ==============
# packages in environment at C:\Users\Admin\MiniConda3\envs\faceswap:
#
# Name Version Build Channel
absl-py 2.1.0 pypi_0 pypi
astunparse 1.6.3 pypi_0 pypi
bzip2 1.0.8 h2bbff1b_6
ca-certificates 2024.12.14 h56e8100_0 conda-forge
cachetools 5.5.0 pypi_0 pypi
certifi 2024.12.14 pypi_0 pypi
charset-normalizer 3.4.1 pypi_0 pypi
colorama 0.4.6 pypi_0 pypi
contourpy 1.3.1 pypi_0 pypi
cycler 0.12.1 pypi_0 pypi
fastcluster 1.2.6 pypi_0 pypi
ffmpy 0.5.0 pypi_0 pypi
flatbuffers 24.12.23 pypi_0 pypi
fonttools 4.55.3 pypi_0 pypi
gast 0.4.0 pypi_0 pypi
git 2.45.2 haa95532_1
google-auth 2.37.0 pypi_0 pypi
google-auth-oauthlib 0.4.6 pypi_0 pypi
google-pasta 0.2.0 pypi_0 pypi
grpcio 1.68.1 pypi_0 pypi
h5py 3.12.1 pypi_0 pypi
idna 3.10 pypi_0 pypi
imageio 2.36.1 pypi_0 pypi
imageio-ffmpeg 0.5.1 pypi_0 pypi
joblib 1.4.2 pypi_0 pypi
keras 2.10.0 pypi_0 pypi
keras-preprocessing 1.1.2 pypi_0 pypi
kiwisolver 1.4.8 pypi_0 pypi
libclang 18.1.1 pypi_0 pypi
libffi 3.4.4 hd77b12b_1
liblzma 5.6.3 h2466b09_1 conda-forge
libsqlite 3.47.2 h67fdade_0 conda-forge
libzlib 1.3.1 h2466b09_2 conda-forge
libzlib-wapi 1.3.1 h2466b09_2 conda-forge
markdown 3.7 pypi_0 pypi
markupsafe 3.0.2 pypi_0 pypi
matplotlib 3.10.0 pypi_0 pypi
numexpr 2.10.2 pypi_0 pypi
numpy 1.26.4 pypi_0 pypi
nvidia-ml-py 12.560.30 pypi_0 pypi
oauthlib 3.2.2 pypi_0 pypi
opencv-python 4.10.0.84 pypi_0 pypi
openssl 3.4.0 h2466b09_0 conda-forge
opt-einsum 3.4.0 pypi_0 pypi
packaging 24.2 pypi_0 pypi
pillow 9.5.0 pypi_0 pypi
pip 24.2 py310haa95532_0
protobuf 3.19.6 pypi_0 pypi
psutil 6.1.1 pypi_0 pypi
pyasn1 0.6.1 pypi_0 pypi
pyasn1-modules 0.4.1 pypi_0 pypi
pyparsing 3.2.0 pypi_0 pypi
python 3.10.16 h37870fc_1_cpython conda-forge
python-dateutil 2.9.0.post0 pypi_0 pypi
pywin32 308 pypi_0 pypi
pywinpty 2.0.2 py310h5da7b33_0
requests 2.32.3 pypi_0 pypi
requests-oauthlib 2.0.0 pypi_0 pypi
rsa 4.9 pypi_0 pypi
scikit-learn 1.6.0 pypi_0 pypi
scipy 1.14.1 pypi_0 pypi
setuptools 75.1.0 py310haa95532_0
six 1.17.0 pypi_0 pypi
sqlite 3.45.3 h2bbff1b_0
tensorboard 2.10.1 pypi_0 pypi
tensorboard-data-server 0.6.1 pypi_0 pypi
tensorboard-plugin-wit 1.8.1 pypi_0 pypi
tensorflow 2.10.1 pypi_0 pypi
tensorflow-estimator 2.10.0 pypi_0 pypi
tensorflow-io-gcs-filesystem 0.31.0 pypi_0 pypi
termcolor 2.5.0 pypi_0 pypi
threadpoolctl 3.5.0 pypi_0 pypi
tk 8.6.13 h5226925_1 conda-forge
tqdm 4.67.1 pypi_0 pypi
typing-extensions 4.12.2 pypi_0 pypi
tzdata 2024b h04d1e81_0
ucrt 10.0.22621.0 h57928b3_1 conda-forge
urllib3 2.3.0 pypi_0 pypi
vc 14.40 haa95532_2
vc14_runtime 14.42.34433 he29a5d6_23 conda-forge
vs2015_runtime 14.42.34433 hdffcdeb_23 conda-forge
werkzeug 3.1.3 pypi_0 pypi
wheel 0.44.0 py310haa95532_0
winpty 0.4.3 4
wrapt 1.17.0 pypi_0 pypi
xz 5.4.6 h8cc25b3_1
zlib 1.3.1 h2466b09_2 conda-forge
zlib-wapi 1.3.1 h2466b09_2 conda-forgedxdiag:
Code: Select all
------------------
System Information
------------------
Time of this report: 12/29/2024, 22:03:44
Machine name: DESKTOP-R36PH5T
Machine Id: {D36039C2-3229-4052-B488-4BA83077E3B4}
Operating System: Windows 11 Pro 64-bit (10.0, Build 22631) (22621.ni_release.220506-1250)
Language: English (Regional Setting: English)
System Manufacturer: Gigabyte Technology Co., Ltd.
System Model: B760M DS3H AX
BIOS: F16 (type: UEFI)
Processor: Intel(R) Core(TM) i5-14400F (16 CPUs), ~2.5GHz
Memory: 32768MB RAM
Available OS Memory: 32604MB RAM
Page File: 10878MB used, 23773MB available
Windows Dir: C:\Windows
DirectX Version: DirectX 12
DX Setup Parameters: Not found
User DPI Setting: 96 DPI (100 percent)
System DPI Setting: 96 DPI (100 percent)
DWM DPI Scaling: Disabled
Miracast: Available, no HDCP
Microsoft Graphics Hybrid: Not Supported
DirectX Database Version: 1.6.4
DxDiag Version: 10.00.22621.3527 64bit Unicode
---------------
Display Devices
---------------
Card name: NVIDIA GeForce RTX 4060 Ti
Manufacturer: NVIDIA
Chip type: NVIDIA GeForce RTX 4060 Ti
DAC type: Integrated RAMDAC
Device Type: Full Device (POST)
Device Key: Enum\PCI\VEN_10DE&DEV_2803&SUBSYS_41061458&REV_A1
Device Status: 0180200A [DN_DRIVER_LOADED|DN_STARTED|DN_DISABLEABLE|DN_NT_ENUMERATOR|DN_NT_DRIVER]
Device Problem Code: No Problem
Driver Problem Code: Unknown
Display Memory: 24250 MB
Dedicated Memory: 7949 MB
Shared Memory: 16301 MB
I reinstalled the program several times. I uninstalled it according to the instructions, but there was no Python folder in the path C:\users\[your username]\AppData\Roaming
Did a fresh install via the installer, but GPU doesn't seem to be utilized at all when running, only CPU. What am I missing here?
After doing some digging, it appears that the installer failed to install cudatoolkit and cudnn. After installing manually through conda, everything looks fine, but the installer should probably be updated.
Hi, my PC is configured with an RTX 4070 and an Intel i7-13700. During installation, I selected the NVIDIA GPU option. However, when I started training, I noticed the following issues: the CPU usage is at 100%, while GPU usage remains between 0–3%. I also checked the backend monitor to confirm this.
I’ve tried reinstalling, but the problem still persists. Could you please advise me on how to fix this?
Thank you very much for your help!
(I’m from Taiwan, and my English may not be perfect — 
thank you for your understanding.)
Loading...
Setting Faceswap backend to NVIDIA
04/14/2025 00:16:22 INFO Log level set to: INFO
04/14/2025 00:16:25 INFO Model A Directory: 'D:\112\113\swap\a' (98 images)
04/14/2025 00:16:25 INFO Model B Directory: 'D:\112\113\swap\b' (116 images)
04/14/2025 00:16:25 WARNING At least one of your input folders contains fewer than 250 images. Results are likely to be poor.
04/14/2025 00:16:25 WARNING You need to provide a significant number of images to successfully train a Neural Network. Aim for between 500 - 5000 images per side.
04/14/2025 00:16:25 INFO Training data directory: D:\112\113\swap\c
04/14/2025 00:16:25 INFO ===================================================
04/14/2025 00:16:25 INFO Starting
04/14/2025 00:16:25 INFO ===================================================
04/14/2025 00:16:26 INFO Loading data, this may take a while...
04/14/2025 00:16:26 INFO Loading Model from Original plugin...
04/14/2025 00:16:26 INFO No existing state file found. Generating.
04/14/2025 00:16:26 INFO Storing Mixed Precision compatible layers. Please ignore any following warnings about using mixed precision.
04/14/2025 00:16:26 WARNING Mixed precision compatibility check (mixed_float16): WARNING
The dtype policy mixed_float16 may run slowly because this machine does not have a GPU. Only Nvidia GPUs with compute capability of at least 7.0 run quickly with mixed_float16.
If you will use compatible GPU(s) not attached to this host, e.g. by running a multi-worker model, you can ignore this warning. This message will only be logged once
This was a regression caused by an updated in how MiniConda handles requirements.
If you re-install faceswap, it should now work.
If you still have issues please provide the newest faceswap_setup.log from your faceswap folder
My word is final
