Good day,
I am pretty new to all this but I have been having issues with training part at the moment. Currently averaging around 18-20EG/s while training. Unless I am mistaken, I'm pretty sure that is low for the card I am currently using. 4060ti (16GB). I have gone through the process of reinstalling via the method posted in the help section (basically fresh start) but still hasn't got above 20EG/s after numerous fresh installs. I made sure during the installation to select for "nvidia gpu" and now I'm at a loss, hopefully someone can point out what I have missed. Any help would be appreciated. Cheers!
(Below is the system output)
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: 16380MB (15339MB free)
os_machine: AMD64
os_platform: Windows-10-10.0.22631-SP0
os_release: 10
py_command: E:\FS\faceswap/faceswap.py gui
py_conda_version: conda 24.11.1
py_implementation: CPython
py_version: 3.10.16
py_virtual_env: True
sys_cores: 24
sys_processor: AMD64 Family 25 Model 97 Stepping 2, AuthenticAMD
sys_ram: Total: 31967MB, Available: 24081MB, Used: 7885MB, Free: 24081MB
=============== 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==1.69.0
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==3.2.1
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==1.6.1
scipy==1.15.1
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==1.17.2
============== Conda Packages ==============
# packages in environment at C:\Users\Nathan\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 2024.12.31 haa95532_0
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 1.69.0 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 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
pyasn1 0.6.1 pypi_0 pypi
pyasn1-modules 0.4.1 pypi_0 pypi
pyparsing 3.2.1 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 1.6.1 pypi_0 pypi
scipy 1.15.1 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 1.17.2 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
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: 30
mask_color: #ff0000
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
