Hi!
I'm kind of new to the stuff, so excuse me for not understanding things.
- (Also worth mentioning. I have kinda old gaming laptop (Lenovo with NV GTX1050 4GB and i5-8300H Turbo 3,9)
What I did:
- 1. Installed FaceSwap app through original x64 installer. (Selected NVidia Support)
- 2. Extracted faces, etc.
- 3. Launched Training
- 4. GPU Usage 2%, Rate: 7 EG/s like it's a joke.
- 5. Installed (Globally) lastest cudatoolkit, lastest cudnn, & lastest compatible tensorflow (Bc FaceSwap didn't want to install them)
- 6. Reinstalled FaceSwap and Conda
- 7. Training. 2%. Same thing.
- 8. Uninstalled FaceSwap
- 9. Did a clear installation of FaceSwap by that guide: NB: It is imperative...
- 10. Training once again, all the same.
FaceSwap installation log:
01/08/2025 16:44:48 setup init INFO Installing cudatoolkit>=11.2,<11.3 cudnn>=8.1,<8.2
01/08/2025 16:44:50 setup call DEBUG Package: cudatoolkit>=11.2,<11.3 cudnn>=8.1,<8.2, returncode: 1
01/08/2025 16:44:50 setup _from_conda WARNING Couldn't install ['"cudatoolkit>=11.2,<11.3"', '"cudnn>=8.1,<8.2"'] with Conda. Please install this package manually
01/08/2025 16:47:10 setup init INFO Installing tensorflow>=2.10.0,<2.11.0
01/08/2025 16:47:12 setup _seen_line_log DEBUG Collecting tensorflow<2.11.0,>=2.10.0
01/08/2025 16:47:12 setup _seen_line_log DEBUG Obtaining dependency information for tensorflow<2.11.0,>=2.10.0 from https://files.pythonhosted.or
01/08/2025 16:47:12 setup _seen_line_log DEBUG g/packages/ad/87/f484e0b86687c97d2dfb081e03e948b796561fc8608b409a9366e3b4a663/tensorflow-2.10.1-cp31
01/08/2025 16:47:12 setup _seen_line_log DEBUG 0-cp310-win_amd64.whl.metadata
01/08/2025 16:47:12 setup _seen_line_log DEBUG Downloading tensorflow-2.10.1-cp310-cp310-win_amd64.whl.metadata (3.1 kB)
01/08/2025 16:48:00 setup call DEBUG Package: tensorflow>=2.10.0,<2.11.0, returncode: 0
FaceSwap System Info
============ System Information ============
backend: nvidia
encoding: cp1252
git_branch: master
git_commits: 41b61f9 Update README.md
gpu_cuda: 11.2
gpu_cudnn: No global version found. Check Conda packages for Conda cuDNN
gpu_devices: GPU_0: NVIDIA GeForce GTX 1050
gpu_devices_active: GPU_0
gpu_driver: 566.14
gpu_vram: GPU_0: 4096MB (3890MB free)
os_machine: AMD64
os_platform: Windows-10-10.0.19045-SP0
os_release: 10
py_command: C:\Users\ycxsb\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: 8
sys_processor: Intel64 Family 6 Model 158 Stepping 10, GenuineIntel
sys_ram: Total: 16258MB, Available: 4058MB, Used: 12201MB, Free: 4054MB
=============== Pip Packages ===============
absl-py==2.1.0
aiogram==2.14
aiohttp==3.8.5
aiomysql==0.2.0
aiosignal==1.3.1
altgraph==0.17.3
anyio==3.7.0
appdirs==1.4.4
APScheduler==3.10.4
astunparse==1.6.3
async-generator==1.10
async-timeout==4.0.2
asyncio==3.4.3
asyncpg @ git+https://github.com/MagicStack/asyncpg.g ... c33147b525
attrs==23.1.0
Babel==2.12.1
bcrypt==4.0.1
beautifulsoup4==4.12.2
blinker==1.6.2
Brotli==1.0.9
bs4==0.0.1
cachetools==5.3.1
certifi==2023.5.7
cffi==1.15.1
chardet==5.1.0
charset-normalizer==3.1.0
click==8.1.3
colorama==0.4.6
comtypes==1.2.0
contourpy==1.3.1
cryptography==41.0.1
cssselect==1.2.0
cycler==0.12.1
dill==0.3.7
dnspython==2.3.0
EasyProcess==1.1
entrypoint2==1.1
exceptiongroup==1.1.1
fake-useragent==1.1.3
fastcluster==1.2.6
ffmpy==0.5.0
Flask==2.3.2
flatbuffers==24.12.23
fonttools==4.55.3
frozenlist==1.4.0
future==0.18.3
gast==0.4.0
google-auth==2.23.0
google-auth-oauthlib==0.4.6
google-pasta==0.2.0
grpcio==1.69.0
gspread==5.11.1
h11==0.14.0
h2==4.1.0
h5py==3.12.1
hpack==4.0.0
httpcore==0.17.2
httplib2==0.22.0
httpx==0.24.1
hyperframe==6.0.1
idna==3.4
imageio==2.36.1
imageio-ffmpeg==0.5.1
impacket==0.10.0
importlib-metadata==6.7.0
itsdangerous==2.1.2
Jinja2==3.1.2
joblib==1.4.2
keras==2.10.0
Keras-Preprocessing==1.1.2
keyboard==0.13.5
kiwisolver==1.4.8
ldap3==2.9.1
ldapdomaindump==0.9.4
libclang==18.1.1
lxml==4.9.2
Markdown==3.7
MarkupSafe==2.1.3
matplotlib==3.10.0
mouse==0.7.1
MouseInfo==0.1.3
mpmath==1.3.0
mss==9.0.1
multidict==6.0.4
multiprocess==0.70.15
mutagen==1.46.0
nextcord==2.5.0
numexpr==2.10.2
numpy==1.26.4
nvidia-ml-py==12.560.30
oauth2client==4.1.3
oauthlib==3.2.2
opencv-python==4.10.0.84
opt_einsum==3.4.0
outcome==1.2.0
packaging==24.2
paramiko==3.2.0
parse==1.19.1
pefile==2023.2.7
Pillow==9.5.0
protobuf==3.19.6
psutil==6.1.1
psycopg2==2.9.7
pyasn1==0.5.0
pyasn1-modules==0.3.0
PyAutoGUI==0.9.54
pycparser==2.21
pycryptodome==3.11.0
pycryptodomex==3.18.0
pyee==8.2.2
pygame==2.4.0
PyGetWindow==0.0.9
pyinstaller-hooks-contrib==2023.3
PyMsgBox==1.0.9
PyMySQL==1.1.0
PyNaCl==1.5.0
pynput==1.7.6
pyOpenSSL==23.2.0
pyparsing==3.1.1
pyperclip==1.8.2
pyppeteer==1.0.2
PyQt5==5.15.9
PyQt5-Qt5==5.15.2
PyQt5-sip==12.12.1
pyquery==2.0.0
PyRect==0.2.0
pyscreenshot==3.1
PyScreeze==0.1.29
pyserial==3.5
PySocks==1.7.1
pystyle==2.9
python-dateutil==2.9.0.post0
python-nmap==0.7.1
python-telegram-bot==20.5
pytweening==1.0.7
pytz==2023.3.post1
pywin32==306
pywin32-ctypes==0.2.1
pywinauto==0.6.8
pywinpty @ file:///C:/ci_310/pywinpty_1644230983541/work/target/wheels/pywinpty-2.0.2-cp310-none-win_amd64.whl
redis==4.6.0
requests==2.31.0
requests-html==0.10.0
requests-oauthlib==1.3.1
rsa==4.9
scapy==2.4.5
scikit-learn==1.6.0
scipy==1.15.0
selenium==4.10.0
six==1.16.0
sniffio==1.3.0
socksio==1.0.0
sortedcontainers==2.4.0
soupsieve==2.4.1
spotipy==2.23.0
sqlmap==1.7.6
telepot==12.7
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
trio==0.22.0
trio-websocket==0.10.3
typing_extensions==4.12.2
tzdata==2023.3
tzlocal==5.0.1
urllib3==1.26.16
uvicorn==0.22.0
w3lib==2.1.1
WaveLinkCord==2.5.1
websockets==10.4
Werkzeug==2.3.6
wrapt==1.17.0
wsproto==1.2.0
yarl==1.8.2
youtube-dl==2021.12.17
yt-dlp==2023.7.6
zipp==3.15.0
============== Conda Packages ==============
packages in environment at C:\ProgramData\anaconda3\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
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-oauthlib 0.4.6 pypi_0 pypi
google-pasta 0.2.0 pypi_0 pypi
grpcio 1.69.0 pypi_0 pypi
h5py 3.12.1 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
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
opencv-python 4.10.0.84 pypi_0 pypi
openssl 3.4.0 ha4e3fda_1 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
python 3.10.16 h37870fc_1_cpython conda-forge
python-dateutil 2.9.0.post0 pypi_0 pypi
pywinpty 2.0.2 py310h5da7b33_0
scikit-learn 1.6.0 pypi_0 pypi
scipy 1.15.0 pypi_0 pypi
setuptools 75.1.0 py310haa95532_0
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
vc 14.40 haa95532_2
vc14_runtime 14.42.34433 he29a5d6_23 conda-forge
vs2015_runtime 14.42.34433 hdffcdeb_23 conda-forge
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-forge
================= 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.mask_blend]
type: normalized
kernel_size: 3
passes: 4
threshold: 4
erosion: 0.0
erosion_top: 0.0
erosion_bottom: 0.0
erosion_left: 0.0
erosion_right: 0.0
[scaling.sharpen]
method: none
amount: 150
radius: 0.3
threshold: 5.0
[writer.ffmpeg]
container: mp4
codec: libx264
crf: 23
preset: medium
tune: none
profile: auto
level: auto
skip_mux: False
[writer.gif]
fps: 25
loop: 0
palettesize: 256
subrectangles: False
[writer.opencv]
format: png
draw_transparent: False
separate_mask: False
jpg_quality: 75
png_compress_level: 3
[writer.patch]
start_index: 0
index_offset: 0
number_padding: 6
include_filename: True
face_index_location: before
origin: bottom-left
empty_frames: blank
json_output: False
separate_mask: False
bit_depth: 16
format: png
png_compress_level: 3
tiff_compression_method: lzw
[writer.pillow]
format: png
draw_transparent: False
separate_mask: False
optimize: False
gif_interlace: True
jpg_quality: 75
png_compress_level: 3
tif_compression: tiff_deflate
--------- extract.ini ---------
[global]
allow_growth: False
aligner_min_scale: 0.07
aligner_max_scale: 2.0
aligner_distance: 22.5
aligner_roll: 45.0
aligner_features: True
filter_refeed: True
save_filtered: False
realign_refeeds: True
filter_realign: True
[align.external]
file_name: import.json
origin: top-left
4_point_centering: head
[align.fan]
batch-size: 12
[detect.cv2_dnn]
confidence: 50
[detect.external]
file_name: import.json
origin: top-left
[detect.mtcnn]
minsize: 20
scalefactor: 0.709
batch-size: 8
cpu: True
threshold_1: 0.6
threshold_2: 0.7
threshold_3: 0.7
[detect.s3fd]
confidence: 70
batch-size: 4
[mask.bisenet_fp]
batch-size: 8
cpu: False
weights: faceswap
include_ears: False
include_hair: False
include_glasses: True
[mask.custom]
batch-size: 8
centering: face
fill: False
[mask.unet_dfl]
batch-size: 8
[mask.vgg_clear]
batch-size: 6
[mask.vgg_obstructed]
batch-size: 2
[recognition.vgg_face2]
batch-size: 16
cpu: False
--------- 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: prompt
timeout: 120
auto_load_model_stats: True
--------- train.ini ---------
[global]
centering: face
coverage: 87.5
icnr_init: False
conv_aware_init: False
optimizer: adam
learning_rate: 5e-05
epsilon_exponent: -7
save_optimizer: exit
lr_finder_iterations: 1000
lr_finder_mode: set
lr_finder_strength: default
autoclip: False
reflect_padding: False
allow_growth: False
mixed_precision: False
nan_protection: True
convert_batchsize: 16
[global.loss]
loss_function: ssim
loss_function_2: mse
loss_weight_2: 100
loss_function_3: None
loss_weight_3: 0
loss_function_4: None
loss_weight_4: 0
mask_loss_function: mse
eye_multiplier: 3
mouth_multiplier: 2
penalized_mask_loss: True
mask_type: extended
mask_dilation: 0.0
mask_blur_kernel: 3
mask_threshold: 4
learn_mask: False
[model.dfaker]
output_size: 128
[model.dfl_h128]
lowmem: False
[model.dfl_sae]
input_size: 128
architecture: df
autoencoder_dims: 0
encoder_dims: 42
decoder_dims: 21
multiscale_decoder: False
[model.dlight]
features: best
details: good
output_size: 256
[model.original]
lowmem: False
[model.phaze_a]
output_size: 128
shared_fc: None
enable_gblock: True
split_fc: True
split_gblock: False
split_decoders: False
enc_architecture: fs_original
enc_scaling: 7
enc_load_weights: True
bottleneck_type: dense
bottleneck_norm: None
bottleneck_size: 1024
bottleneck_in_encoder: True
fc_depth: 1
fc_min_filters: 1024
fc_max_filters: 1024
fc_dimensions: 4
fc_filter_slope: -0.5
fc_dropout: 0.0
fc_upsampler: upsample2d
fc_upsamples: 1
fc_upsample_filters: 512
fc_gblock_depth: 3
fc_gblock_min_nodes: 512
fc_gblock_max_nodes: 512
fc_gblock_filter_slope: -0.5
fc_gblock_dropout: 0.0
dec_upscale_method: subpixel
dec_upscales_in_fc: 0
dec_norm: None
dec_min_filters: 64
dec_max_filters: 512
dec_slope_mode: full
dec_filter_slope: -0.45
dec_res_blocks: 1
dec_output_kernel: 5
dec_gaussian: True
dec_skip_last_residual: True
freeze_layers: keras_encoder
load_layers: encoder
fs_original_depth: 4
fs_original_min_filters: 128
fs_original_max_filters: 1024
fs_original_use_alt: False
mobilenet_width: 1.0
mobilenet_depth: 1
mobilenet_dropout: 0.001
mobilenet_minimalistic: 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
nodes: 1024
complexity_encoder: 128
complexity_decoder_a: 384
complexity_decoder_b: 512
[model.villain]
lowmem: False
[trainer.original]
preview_images: 14
mask_opacity: 40
mask_color: #00ffff
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
Training Launch Log
Loading...
Setting Faceswap backend to NVIDIA
01/08/2025 16:51:12 INFO Log level set to: VERBOSE
01/08/2025 16:51:19 INFO Model A Directory: 'F:\#Deepfacelabs\#deep-dst' (33069 images)
01/08/2025 16:51:19 INFO Model B Directory: 'F:\#Deepfacelabs\#deep-src' (30492 images)
01/08/2025 16:51:19 INFO Training data directory: F:\#_Deepfacelabs\#fs_model_dsh_1\dshm1
01/08/2025 16:51:19 INFO ===================================================
01/08/2025 16:51:19 INFO Starting
01/08/2025 16:51:19 INFO Using live preview
01/08/2025 16:51:19 INFO ===================================================
01/08/2025 16:51:19 INFO ---------------------------------------------------
01/08/2025 16:51:19 INFO Preview key bindings:
01/08/2025 16:51:19 INFO Zoom: +/-
01/08/2025 16:51:19 INFO Toggle Zoom Mode: i
01/08/2025 16:51:19 INFO Move: arrow keys
01/08/2025 16:51:19 INFO Save Preview: Ctrl+s
01/08/2025 16:51:19 INFO ---------------------------------------------------
01/08/2025 16:51:20 INFO Loading data, this may take a while...
01/08/2025 16:51:20 INFO Loading Model from Original plugin...
01/08/2025 16:51:20 VERBOSE Loading config: 'C:\Users\ycxsb\faceswap\config\train.ini'
01/08/2025 16:51:20 VERBOSE Loading config: 'C:\Users\ycxsb\faceswap\config\train.ini'
01/08/2025 16:51:20 INFO Using configuration saved in state file
2025-01-08 16:51:20.589331: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudnn64_8.dll'; dlerror: cudnn64_8.dll not found
2025-01-08 16:51:20.589907: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1934] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.
Skipping registering GPU devices...
2025-01-08 16:51:20.591510: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
01/08/2025 16:18:00 INFO Loaded model from disk: 'F:\#_Deepfacelabs\#fs_model_dsh_1\dshm1\original.h5'
01/08/2025 16:18:00 INFO Loading Trainer from Original plugin...
01/08/2025 16:18:00 VERBOSE Loading config: 'C:\Users\ycxsb\faceswap\config\train.ini'
01/08/2025 16:18:01 VERBOSE Enabled TensorBoard Logging
01/08/2025 16:18:14 INFO [Saved model] - Average loss since last save: face_a: 0.08411, face_b: 0.11751
01/08/2025 16:18:17 INFO [Preview Updated]
It says "Could not load dynamic library 'cudnn64_8.dll'; dlerror: cudnn64_8.dll not found", but as you can see, other libraries loaded just fine. And you can clearly see presence of "cudnn64_8.dll" library in CUDNN main folder. I've even added the folder to the path.
I did Cuda installations by following this guide: https://support.echoview.com/WebHelp/_I ... ibrary.htm
I guess I need a help in CUDNN 8.1 on my windows machine. Because faceswap can't see the dll i've installed on my own.
Thank you in advance.
<3