Hello,
I have followed carefully the tutorials, everything went fine until I attempted to start the training.
When starting to train, I get the following error :
Code: Select all
05/31/2020 16:55:35 CRITICAL An unexpected crash has occurred. Crash report written to '/Users/antoine/faceswap/crash_report.2020.05.31.165532655615.log'. You MUST provide this file if seeking assistance. Please verify you are running the latest version of faceswap before reporting
Detailed logs provided below seem to point to the optimizers.py file.
I have tried various settings/models in the GUI, still the same result. Also, I am running the software on Mac OS, which seemed to be possible according to the faceswap home page.
Can anyone help me? I am trying to create a Deepfake as a birthday present but I am not python fluent and can't grasp this error. Thanks!
Code: Select all
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Non-trainable params: 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base name DEBUG model name: 'original'
05/31/2020 16:50:32 MainProcess _training_0 _base log_summary VERBOSE [Original B Summary]:
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Model: "model_5"
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Layer (type) Output Shape Param #
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE =================================================================
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE face_in (InputLayer) (None, 64, 64, 3) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE encoder (Model) (None, 8, 8, 512) 69662976
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE decoder_b (Model) (None, 64, 64, 3) 6199747
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE =================================================================
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Total params: 75,862,723
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Trainable params: 75,862,723
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Non-trainable params: 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base log_summary VERBOSE Decoder_B:
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Model: "decoder_b"
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Layer (type) Output Shape Param #
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE =================================================================
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE input_2 (InputLayer) (None, 8, 8, 512) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_8_1_conv2d (Conv2D) (None, 8, 8, 1024) 4719616
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_8_1_leakyrelu (Leaky (None, 8, 8, 1024) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_8_1_pixelshuffler (P (None, 16, 16, 256) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_16_1_conv2d (Conv2D) (None, 16, 16, 512) 1180160
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_16_1_leakyrelu (Leak (None, 16, 16, 512) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_16_1_pixelshuffler ( (None, 32, 32, 128) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_32_1_conv2d (Conv2D) (None, 32, 32, 256) 295168
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_32_1_leakyrelu (Leak (None, 32, 32, 256) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_32_1_pixelshuffler ( (None, 64, 64, 64) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE face_out (Conv2D) (None, 64, 64, 3) 4803
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE =================================================================
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Total params: 6,199,747
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Trainable params: 6,199,747
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Non-trainable params: 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base log_summary VERBOSE Encoder:
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Model: "encoder"
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Layer (type) Output Shape Param #
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE =================================================================
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE input_3 (InputLayer) (None, 64, 64, 3) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_64_0_conv2d (Conv2D) (None, 32, 32, 128) 9728
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_64_0_leakyrelu (LeakyRe (None, 32, 32, 128) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_32_0_conv2d (Conv2D) (None, 16, 16, 256) 819456
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_32_0_leakyrelu (LeakyRe (None, 16, 16, 256) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_16_0_conv2d (Conv2D) (None, 8, 8, 512) 3277312
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_16_0_leakyrelu (LeakyRe (None, 8, 8, 512) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_8_0_conv2d (Conv2D) (None, 4, 4, 1024) 13108224
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE conv_8_0_leakyrelu (LeakyReL (None, 4, 4, 1024) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE flatten_1 (Flatten) (None, 16384) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE dense_1 (Dense) (None, 1024) 16778240
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE dense_2 (Dense) (None, 16384) 16793600
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE reshape_1 (Reshape) (None, 4, 4, 1024) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_4_0_conv2d (Conv2D) (None, 4, 4, 2048) 18876416
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_4_0_leakyrelu (Leaky (None, 4, 4, 2048) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE upscale_4_0_pixelshuffler (P (None, 8, 8, 512) 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE =================================================================
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Total params: 69,662,976
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Trainable params: 69,662,976
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE Non-trainable params: 0
05/31/2020 16:50:32 MainProcess _training_0 _base <lambda> VERBOSE _________________________________________________________________
05/31/2020 16:50:32 MainProcess _training_0 _base compile_predictors DEBUG Compiling Predictors
05/31/2020 16:50:32 MainProcess _training_0 _base get_optimizer DEBUG Optimizer kwargs: {'lr': 5e-05, 'beta_1': 0.5, 'beta_2': 0.999}
05/31/2020 16:50:32 MainProcess _training_0 multithreading run DEBUG Error in thread (_training_0): __init__() takes from 1 to 5 positional arguments but 6 were given
05/31/2020 16:50:33 MainProcess MainThread train _monitor DEBUG Thread error detected
05/31/2020 16:50:33 MainProcess MainThread train _monitor DEBUG Closed Monitor
05/31/2020 16:50:33 MainProcess MainThread train _end_thread DEBUG Ending Training thread
05/31/2020 16:50:33 MainProcess MainThread train _end_thread CRITICAL Error caught! Exiting...
05/31/2020 16:50:33 MainProcess MainThread multithreading join DEBUG Joining Threads: '_training'
05/31/2020 16:50:33 MainProcess MainThread multithreading join DEBUG Joining Thread: '_training_0'
05/31/2020 16:50:33 MainProcess MainThread multithreading join ERROR Caught exception in thread: '_training_0'
Traceback (most recent call last):
File "/Users/antoine/faceswap/lib/cli/launcher.py", line 155, in execute_script
process.process()
File "/Users/antoine/faceswap/scripts/train.py", line 161, in process
self._end_thread(thread, err)
File "/Users/antoine/faceswap/scripts/train.py", line 201, in _end_thread
thread.join()
File "/Users/antoine/faceswap/lib/multithreading.py", line 121, in join
raise thread.err[1].with_traceback(thread.err[2])
File "/Users/antoine/faceswap/lib/multithreading.py", line 37, in run
self._target(*self._args, **self._kwargs)
File "/Users/antoine/faceswap/scripts/train.py", line 226, in _training
raise err
File "/Users/antoine/faceswap/scripts/train.py", line 214, in _training
model = self._load_model()
File "/Users/antoine/faceswap/scripts/train.py", line 255, in _load_model
predict=False)
File "/Users/antoine/faceswap/plugins/train/model/original.py", line 25, in __init__
super().__init__(*args, **kwargs)
File "/Users/antoine/faceswap/plugins/train/model/_base.py", line 125, in __init__
self.build()
File "/Users/antoine/faceswap/plugins/train/model/_base.py", line 259, in build
self.compile_predictors(initialize=True)
File "/Users/antoine/faceswap/plugins/train/model/_base.py", line 364, in compile_predictors
optimizer = self.get_optimizer(lr=learning_rate, beta_1=0.5, beta_2=0.999)
File "/Users/antoine/faceswap/plugins/train/model/_base.py", line 387, in get_optimizer
return Adam(**opt_kwargs, cpu_mode=self.vram_savings.optimizer_savings)
File "/Users/antoine/faceswap/lib/model/optimizers.py", line 58, in __init__
super().__init__(lr, beta_1, beta_2, epsilon, decay)
TypeError: __init__() takes from 1 to 5 positional arguments but 6 were given
============ System Information ============
encoding: UTF-8
git_branch: master
git_commits: ac40b0f Remove subpixel upscaling option (#1024)
gpu_cuda: Unsupported OS. Check Conda packages for Conda Cuda
gpu_cudnn: Unsupported OS. Check Conda packages for Conda cuDNN
gpu_devices:
gpu_devices_active:
gpu_driver: 0
gpu_vram:
os_machine: x86_64
os_platform: Darwin-19.3.0-x86_64-i386-64bit
os_release: 19.3.0
py_command: /Users/antoine/faceswap/faceswap.py train -A /Users/antoine/Desktop/faceswap-WORKSPACE/camille -ala /Users/antoine/Desktop/faceswap-WORKSPACE/camille_alignments.fsa -B /Users/antoine/Desktop/faceswap-WORKSPACE/nadal -alb /Users/antoine/Desktop/faceswap-WORKSPACE/nadal_alignments.fsa -m /Users/antoine/Desktop/faceswap-WORKSPACE/model -t original -bs 64 -it 1000000 -s 100 -ss 25000 -tia /Users/antoine/Desktop/faceswap-WORKSPACE/timelapse/input-camille -tib /Users/antoine/Desktop/faceswap-WORKSPACE/timelapse/input-nadal -to /Users/antoine/Desktop/faceswap-WORKSPACE/timelapse/output -ps 50 -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: i386
sys_ram: Total: 8192MB, Available: 2145MB, Used: 3892MB, Free: 28MB
=============== Pip Packages ===============
absl-py==0.9.0
astor==0.8.1
astunparse==1.6.3
cachetools==4.1.0
certifi==2020.4.5.1
chardet==3.0.4
cycler==0.10.0
fastcluster==1.1.26
ffmpy==0.2.2
gast==0.2.2
google-auth==1.16.0
google-auth-oauthlib==0.4.1
google-pasta==0.2.0
grpcio==1.29.0
h5py==2.10.0
idna==2.9
imageio==2.8.0
imageio-ffmpeg==0.4.2
importlib-metadata==1.6.0
Keras==2.3.1
Keras-Applications==1.0.8
Keras-Preprocessing==1.1.2
kiwisolver==1.2.0
Markdown==3.2.2
matplotlib==3.2.1
numpy==1.18.4
nvidia-ml-py3==7.352.1
oauthlib==3.1.0
opencv-python==4.1.2.30
opt-einsum==3.2.1
Pillow==7.1.2
protobuf==3.12.2
psutil==5.7.0
pyasn1==0.4.8
pyasn1-modules==0.2.8
pynvx==1.0.0
pyparsing==2.4.7
python-dateutil==2.8.1
PyYAML==5.3.1
requests==2.23.0
requests-oauthlib==1.3.0
rsa==4.0
scipy==1.4.1
six==1.15.0
tensorboard==1.15.0
tensorboard-plugin-wit==1.6.0.post3
tensorflow==1.15.0
tensorflow-estimator==1.15.1
termcolor==1.1.0
tqdm==4.46.0
urllib3==1.25.9
Werkzeug==1.0.1
wrapt==1.12.1
zipp==3.1.0
============== Conda Packages ==============
# packages in environment at /Users/antoine/opt/anaconda3/envs/faceswap:
#
# Name Version Build Channel
absl-py 0.9.0 pypi_0 pypi
astor 0.8.1 pypi_0 pypi
astunparse 1.6.3 pypi_0 pypi
ca-certificates 2020.1.1 0
cachetools 4.1.0 pypi_0 pypi
certifi 2020.4.5.1 py37_0
chardet 3.0.4 pypi_0 pypi
cycler 0.10.0 pypi_0 pypi
fastcluster 1.1.26 pypi_0 pypi
gast 0.2.2 pypi_0 pypi
google-auth 1.16.0 pypi_0 pypi
google-auth-oauthlib 0.4.1 pypi_0 pypi
google-pasta 0.2.0 pypi_0 pypi
grpcio 1.29.0 pypi_0 pypi
h5py 2.10.0 pypi_0 pypi
idna 2.9 pypi_0 pypi
imageio 2.8.0 pypi_0 pypi
imageio-ffmpeg 0.4.2 pypi_0 pypi
importlib-metadata 1.6.0 pypi_0 pypi
keras 2.3.1 pypi_0 pypi
keras-applications 1.0.8 pypi_0 pypi
keras-preprocessing 1.1.2 pypi_0 pypi
kiwisolver 1.2.0 pypi_0 pypi
libcxx 10.0.0 1
libedit 3.1.20181209 hb402a30_0
libffi 3.3 h0a44026_1
markdown 3.2.2 pypi_0 pypi
matplotlib 3.2.1 pypi_0 pypi
ncurses 6.2 h0a44026_1
numpy 1.18.4 pypi_0 pypi
oauthlib 3.1.0 pypi_0 pypi
openssl 1.1.1g h1de35cc_0
opt-einsum 3.2.1 pypi_0 pypi
pillow 7.1.2 pypi_0 pypi
pip 20.0.2 py37_3
protobuf 3.12.2 pypi_0 pypi
psutil 5.7.0 pypi_0 pypi
pyasn1 0.4.8 pypi_0 pypi
pyasn1-modules 0.2.8 pypi_0 pypi
pyparsing 2.4.7 pypi_0 pypi
python 3.7.7 hf48f09d_4
python-dateutil 2.8.1 pypi_0 pypi
pyyaml 5.3.1 pypi_0 pypi
readline 8.0 h1de35cc_0
requests 2.23.0 pypi_0 pypi
requests-oauthlib 1.3.0 pypi_0 pypi
rsa 4.0 pypi_0 pypi
scipy 1.4.1 pypi_0 pypi
setuptools 46.4.0 py37_0
six 1.15.0 pypi_0 pypi
sqlite 3.31.1 h5c1f38d_1
tensorboard 1.15.0 pypi_0 pypi
tensorboard-plugin-wit 1.6.0.post3 pypi_0 pypi
tensorflow 1.15.0 pypi_0 pypi
tensorflow-estimator 1.15.1 pypi_0 pypi
termcolor 1.1.0 pypi_0 pypi
tk 8.6.8 ha441bb4_0
tqdm 4.46.0 pypi_0 pypi
urllib3 1.25.9 pypi_0 pypi
werkzeug 1.0.1 pypi_0 pypi
wheel 0.34.2 py37_0
wrapt 1.12.1 pypi_0 pypi
xz 5.2.5 h1de35cc_0
zipp 3.1.0 pypi_0 pypi
zlib 1.2.11 h1de35cc_3
================= Configs ==================
--------- convert.ini ---------
[color.color_transfer]
clip: True
preserve_paper: True
[color.match_hist]
threshold: 99.0
[color.manual_balance]
colorspace: HSV
balance_1: 0.0
balance_2: 0.0
balance_3: 0.0
contrast: 0.0
brightness: 0.0
[writer.pillow]
format: png
draw_transparent: False
optimize: False
gif_interlace: True
jpg_quality: 75
png_compress_level: 3
tif_compression: tiff_deflate
[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
[mask.mask_blend]
type: normalized
kernel_size: 3
passes: 4
threshold: 4
erosion: 0.0
[mask.box_blend]
type: gaussian
distance: 11.0
radius: 5.0
passes: 1
[scaling.sharpen]
method: unsharp_mask
amount: 150
radius: 0.3
threshold: 5.0
--------- 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
--------- .faceswap ---------
backend: cpu
--------- extract.ini ---------
[global]
allow_growth: False
[detect.mtcnn]
minsize: 20
threshold_1: 0.6
threshold_2: 0.7
threshold_3: 0.7
scalefactor: 0.709
batch-size: 8
[detect.cv2_dnn]
confidence: 50
[detect.s3fd]
confidence: 70
batch-size: 4
[align.fan]
batch-size: 12
[mask.unet_dfl]
batch-size: 8
[mask.vgg_obstructed]
batch-size: 2
[mask.vgg_clear]
batch-size: 6
--------- train.ini ---------
[global]
coverage: 80.0
mask_type: none
mask_blur_kernel: 3
mask_threshold: 4
learn_mask: False
icnr_init: False
conv_aware_init: False
reflect_padding: False
penalized_mask_loss: True
loss_function: mae
learning_rate: 5e-05
[model.realface]
input_size: 64
output_size: 128
dense_nodes: 1536
complexity_encoder: 128
complexity_decoder: 512
[model.dfl_sae]
input_size: 128
clipnorm: True
architecture: df
autoencoder_dims: 0
encoder_dims: 42
decoder_dims: 21
multiscale_decoder: False
[model.unbalanced]
input_size: 128
lowmem: False
clipnorm: True
nodes: 1024
complexity_encoder: 128
complexity_decoder_a: 384
complexity_decoder_b: 512
[model.dlight]
features: best
details: good
output_size: 256
[model.villain]
lowmem: False
[model.original]
lowmem: False
[model.dfl_h128]
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
