OSSForks/faceswap
1
0
Fork 0
mirror of https://github.com/zebrajr/faceswap.git synced 2025-12-06 12:20:27 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

locales: Train settings

Browse Source
This commit is contained in:
torzdf 2023-06-11 23:30:05 +01:00
parent a66214c58e
commit 02239d4183
5 changed files with 938 additions and 287 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
lib/config.py
View File

@ -3,6 +3,7 @@
Extends out :class:`configparser.ConfigParser` functionality by checking for default
configuration updates and returning data in it's correct format """
import gettext
import logging
import os
import sys
@ -16,6 +17,10 @@ from typing import Dict, List, Optional, Tuple, Union
from lib.utils import full_path_split
# LOCALES
_LANG = gettext.translation("lib.config", localedir="locales", fallback=True)
_ = _LANG.gettext
# Can't type OrderedDict fully on Python 3.8 or lower
if sys.version_info < (3, 9):
OrderedDictSectionType = OrderedDict
@ -282,7 +287,9 @@ class FaceswapConfig():
logger.error(err)
raise ValueError(err)
return configfile
dirname = os.path.dirname(sys.modules[self.__module__].__file__)
filepath = sys.modules[self.__module__].__file__
assert filepath is not None
dirname = os.path.dirname(filepath)
folder, fname = os.path.split(dirname)
retval = os.path.join(os.path.dirname(folder), "config", f"{fname}.ini")
logger.debug("Config File location: '%s'", retval)
@ -383,23 +390,23 @@ class FaceswapConfig():
""" Add extra helptext info from parameters """
helptext += "\n"
if not fixed:
helptext += "\nThis option can be updated for existing models.\n"
helptext += _("\nThis option can be updated for existing models.\n")
if datatype == list:
helptext += ("\nIf selecting multiple options then each option should be separated "
helptext += _("\nIf selecting multiple options then each option should be separated "
"by a space or a comma (e.g. item1, item2, item3)\n")
if choices and choices != "colorchooser":
helptext += f"\nChoose from: {choices}"
helptext += _("\nChoose from: {}").format(choices)
elif datatype == bool:
helptext += "\nChoose from: True, False"
helptext += _("\nChoose from: True, False")
elif datatype == int:
assert min_max is not None
cmin, cmax = min_max
helptext += f"\nSelect an integer between {cmin} and {cmax}"
helptext += _("\nSelect an integer between {} and {}").format(cmin, cmax)
elif datatype == float:
assert min_max is not None
cmin, cmax = min_max
helptext += f"\nSelect a decimal number between {cmin} and {cmax}"
helptext += f"\n[Default: {default}]"
helptext += _("\nSelect a decimal number between {} and {}").format(cmin, cmax)
helptext += _("\n[Default: {}]").format(default)
return helptext
def _check_exists(self) -> bool:

61
locales/lib.config.pot Normal file
View File

@ -0,0 +1,61 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR THE PACKAGE'S COPYRIGHT HOLDER
# This file is distributed under the same license as the PACKAGE package.
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-06-11 23:28+0100\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <LL@li.org>\n"
"Language: \n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=CHARSET\n"
"Content-Transfer-Encoding: 8bit\n"
#: lib/config.py:393
msgid ""
"\n"
"This option can be updated for existing models.\n"
msgstr ""
#: lib/config.py:395
msgid ""
"\n"
"If selecting multiple options then each option should be separated by a "
"space or a comma (e.g. item1, item2, item3)\n"
msgstr ""
#: lib/config.py:398
msgid ""
"\n"
"Choose from: {}"
msgstr ""
#: lib/config.py:400
msgid ""
"\n"
"Choose from: True, False"
msgstr ""
#: lib/config.py:404
msgid ""
"\n"
"Select an integer between {} and {}"
msgstr ""
#: lib/config.py:408
msgid ""
"\n"
"Select a decimal number between {} and {}"
msgstr ""
#: lib/config.py:409
msgid ""
"\n"
"[Default: {}]"
msgstr ""

552
locales/plugins.train._config.pot Normal file
View File

@ -0,0 +1,552 @@
# SOME DESCRIPTIVE TITLE.
# Copyright (C) YEAR THE PACKAGE'S COPYRIGHT HOLDER
# This file is distributed under the same license as the PACKAGE package.
# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
#
#, fuzzy
msgid ""
msgstr ""
"Project-Id-Version: PACKAGE VERSION\n"
"Report-Msgid-Bugs-To: \n"
"POT-Creation-Date: 2023-06-11 23:20+0100\n"
"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
"Language-Team: LANGUAGE <LL@li.org>\n"
"Language: \n"
"MIME-Version: 1.0\n"
"Content-Type: text/plain; charset=CHARSET\n"
"Content-Transfer-Encoding: 8bit\n"
#: plugins/train/_config.py:17
msgid ""
"\n"
"NB: Unless specifically stated, values changed here will only take effect "
"when creating a new model."
msgstr ""
#: plugins/train/_config.py:22
msgid ""
"Focal Frequency Loss. Analyzes the frequency spectrum of the images rather "
"than the images themselves. This loss function can be used on its own, but "
"the original paper found increased benefits when using it as a complementary "
"loss to another spacial loss function (e.g. MSE). Ref: Focal Frequency Loss "
"for Image Reconstruction and Synthesis https://arxiv.org/pdf/2012.12821.pdf "
"NB: This loss does not currently work on AMD cards."
msgstr ""
#: plugins/train/_config.py:29
msgid ""
"Nvidia FLIP. A perceptual loss measure that approximates the difference "
"perceived by humans as they alternate quickly (or flip) between two images. "
"Used on its own and this loss function creates a distinct grid on the "
"output. However it can be helpful when used as a complimentary loss "
"function. Ref: FLIP: A Difference Evaluator for Alternating Images: https://"
"research.nvidia.com/sites/default/files/node/3260/FLIP_Paper.pdf"
msgstr ""
#: plugins/train/_config.py:36
msgid ""
"Gradient Magnitude Similarity Deviation seeks to match the global standard "
"deviation of the pixel to pixel differences between two images. Similar in "
"approach to SSIM. Ref: Gradient Magnitude Similarity Deviation: An Highly "
"Efficient Perceptual Image Quality Index https://arxiv.org/ftp/arxiv/"
"papers/1308/1308.3052.pdf"
msgstr ""
#: plugins/train/_config.py:41
msgid ""
"The L_inf norm will reduce the largest individual pixel error in an image. "
"As each largest error is minimized sequentially, the overall error is "
"improved. This loss will be extremely focused on outliers."
msgstr ""
#: plugins/train/_config.py:45
msgid ""
"Laplacian Pyramid Loss. Attempts to improve results by focussing on edges "
"using Laplacian Pyramids. As this loss function gives priority to edges over "
"other low-frequency information, like color, it should not be used on its "
"own. The original implementation uses this loss as a complimentary function "
"to MSE. Ref: Optimizing the Latent Space of Generative Networks https://"
"arxiv.org/abs/1707.05776"
msgstr ""
#: plugins/train/_config.py:52
msgid ""
"LPIPS is a perceptual loss that uses the feature outputs of other pretrained "
"models as a loss metric. Be aware that this loss function will use more "
"VRAM. Used on its own and this loss will create a distinct moire pattern on "
"the output, however it can be helpful as a complimentary loss function. The "
"output of this function is strong, so depending on your chosen primary loss "
"function, you are unlikely going to want to set the weight above about 25%. "
"Ref: The Unreasonable Effectiveness of Deep Features as a Perceptual Metric "
"http://arxiv.org/abs/1801.03924\n"
"This variant uses the AlexNet backbone. A fairly light and old model which "
"performed best in the paper's original implementation.\n"
"NB: For AMD Users the final linear layer is not implemented."
msgstr ""
#: plugins/train/_config.py:62
msgid ""
"Same as lpips_alex, but using the SqueezeNet backbone. A more lightweight "
"version of AlexNet.\n"
"NB: For AMD Users the final linear layer is not implemented."
msgstr ""
#: plugins/train/_config.py:65
msgid ""
"Same as lpips_alex, but using the VGG16 backbone. A more heavyweight model.\n"
"NB: For AMD Users the final linear layer is not implemented."
msgstr ""
#: plugins/train/_config.py:68
msgid ""
"log(cosh(x)) acts similar to MSE for small errors and to MAE for large "
"errors. Like MSE, it is very stable and prevents overshoots when errors are "
"near zero. Like MAE, it is robust to outliers."
msgstr ""
#: plugins/train/_config.py:72
msgid ""
"Mean absolute error will guide reconstructions of each pixel towards its "
"median value in the training dataset. Robust to outliers but as a median, it "
"can potentially ignore some infrequent image types in the dataset."
msgstr ""
#: plugins/train/_config.py:76
msgid ""
"Mean squared error will guide reconstructions of each pixel towards its "
"average value in the training dataset. As an avg, it will be susceptible to "
"outliers and typically produces slightly blurrier results. Ref: Multi-Scale "
"Structural Similarity for Image Quality Assessment https://www.cns.nyu.edu/"
"pub/eero/wang03b.pdf"
msgstr ""
#: plugins/train/_config.py:81
msgid ""
"Multiscale Structural Similarity Index Metric is similar to SSIM except that "
"it performs the calculations along multiple scales of the input image."
msgstr ""
#: plugins/train/_config.py:84
msgid ""
"Smooth_L1 is a modification of the MAE loss to correct two of its "
"disadvantages. This loss has improved stability and guidance for small "
"errors. Ref: A General and Adaptive Robust Loss Function https://arxiv.org/"
"pdf/1701.03077.pdf"
msgstr ""
#: plugins/train/_config.py:88
msgid ""
"Structural Similarity Index Metric is a perception-based loss that considers "
"changes in texture, luminance, contrast, and local spatial statistics of an "
"image. Potentially delivers more realistic looking images. Ref: Image "
"Quality Assessment: From Error Visibility to Structural Similarity http://"
"www.cns.nyu.edu/pub/eero/wang03-reprint.pdf"
msgstr ""
#: plugins/train/_config.py:93
msgid ""
"Instead of minimizing the difference between the absolute value of each "
"pixel in two reference images, compute the pixel to pixel spatial difference "
"in each image and then minimize that difference between two images. Allows "
"for large color shifts, but maintains the structure of the image."
msgstr ""
#: plugins/train/_config.py:97
msgid "Do not use an additional loss function."
msgstr ""
#: plugins/train/_config.py:117
msgid "Options that apply to all models"
msgstr ""
#: plugins/train/_config.py:126 plugins/train/_config.py:150
msgid "face"
msgstr ""
#: plugins/train/_config.py:128
msgid ""
"How to center the training image. The extracted images are centered on the "
"middle of the skull based on the face's estimated pose. A subsection of "
"these images are used for training. The centering used dictates how this "
"subsection will be cropped from the aligned images.\n"
"\tface: Centers the training image on the center of the face, adjusting for "
"pitch and yaw.\n"
"\thead: Centers the training image on the center of the head, adjusting for "
"pitch and yaw. NB: You should only select head centering if you intend to "
"include the full head (including hair) in the final swap. This may give "
"mixed results. Additionally, it is only worth choosing head centering if you "
"are training with a mask that includes the hair (e.g. BiSeNet-FP-Head).\n"
"\tlegacy: The 'original' extraction technique. Centers the training image "
"near the tip of the nose with no adjustment. Can result in the edges of the "
"face appearing outside of the training area."
msgstr ""
#: plugins/train/_config.py:152
msgid ""
"How much of the extracted image to train on. A lower coverage will limit the "
"model's scope to a zoomed-in central area while higher amounts can include "
"the entire face. A trade-off exists between lower amounts given more detail "
"versus higher amounts avoiding noticeable swap transitions. For 'Face' "
"centering you will want to leave this above 75%. For Head centering you will "
"most likely want to set this to 100%. Sensible values for 'Legacy' centering "
"are:\n"
"\t62.5% spans from eyebrow to eyebrow.\n"
"\t75.0% spans from temple to temple.\n"
"\t87.5% spans from ear to ear.\n"
"\t100.0% is a mugshot."
msgstr ""
#: plugins/train/_config.py:168 plugins/train/_config.py:179
msgid "initialization"
msgstr ""
#: plugins/train/_config.py:170
msgid ""
"Use ICNR to tile the default initializer in a repeating pattern. This "
"strategy is designed for pairing with sub-pixel / pixel shuffler to reduce "
"the 'checkerboard effect' in image reconstruction. \n"
"\t https://arxiv.org/ftp/arxiv/papers/1707/1707.02937.pdf"
msgstr ""
#: plugins/train/_config.py:181
msgid ""
"Use Convolution Aware Initialization for convolutional layers. This can help "
"eradicate the vanishing and exploding gradient problem as well as lead to "
"higher accuracy, lower loss and faster convergence.\n"
"NB:\n"
"\t This can use more VRAM when creating a new model so you may want to lower "
"the batch size for the first run. The batch size can be raised again when "
"reloading the model. \n"
"\t Multi-GPU is not supported for this option, so you should start the model "
"on a single GPU. Once training has started, you can stop training, enable "
"multi-GPU and resume.\n"
"\t Building the model will likely take several minutes as the calculations "
"for this initialization technique are expensive. This will only impact "
"starting a new model."
msgstr ""
#: plugins/train/_config.py:198 plugins/train/_config.py:223
#: plugins/train/_config.py:238 plugins/train/_config.py:265
msgid "optimizer"
msgstr ""
#: plugins/train/_config.py:202
msgid ""
"The optimizer to use.\n"
"\t adabelief - Adapting Stepsizes by the Belief in Observed Gradients. An "
"optimizer with the aim to converge faster, generalize better and remain more "
"stable. (https://arxiv.org/abs/2010.07468). NB: Epsilon for AdaBelief needs "
"to be set to a smaller value than other Optimizers. Generally setting the "
"'Epsilon Exponent' to around '-16' should work.\n"
"\t adam - Adaptive Moment Optimization. A stochastic gradient descent method "
"that is based on adaptive estimation of first-order and second-order "
"moments.\n"
"\t nadam - Adaptive Moment Optimization with Nesterov Momentum. Much like "
"Adam but uses a different formula for calculating momentum.\n"
"\t rms-prop - Root Mean Square Propagation. Maintains a moving (discounted) "
"average of the square of the gradients. Divides the gradient by the root of "
"this average."
msgstr ""
#: plugins/train/_config.py:225
msgid ""
"Learning rate - how fast your network will learn (how large are the "
"modifications to the model weights after one batch of training). Values that "
"are too large might result in model crashes and the inability of the model "
"to find the best solution. Values that are too small might be unable to "
"escape from dead-ends and find the best global minimum."
msgstr ""
#: plugins/train/_config.py:240
msgid ""
"The epsilon adds a small constant to weight updates to attempt to avoid "
"'divide by zero' errors. Unless you are using the AdaBelief Optimizer, then "
"Generally this option should be left at default value, For AdaBelief, "
"setting this to around '-16' should work.\n"
"In all instances if you are getting 'NaN' loss values, and have been unable "
"to resolve the issue any other way (for example, increasing batch size, or "
"lowering learning rate), then raising the epsilon can lead to a more stable "
"model. It may, however, come at the cost of slower training and a less "
"accurate final result.\n"
"NB: The value given here is the 'exponent' to the epsilon. For example, "
"choosing '-7' will set the epsilon to 1e-7. Choosing '-3' will set the "
"epsilon to 0.001 (1e-3)."
msgstr ""
#: plugins/train/_config.py:258
msgid ""
"[Not PlaidML] Apply AutoClipping to the gradients. AutoClip analyzes the "
"gradient weights and adjusts the normalization value dynamically to fit the "
"data. Can help prevent NaNs and improve model optimization at the expense of "
"VRAM. Ref: AutoClip: Adaptive Gradient Clipping for Source Separation "
"Networks https://arxiv.org/abs/2007.14469"
msgstr ""
#: plugins/train/_config.py:271 plugins/train/_config.py:283
#: plugins/train/_config.py:297 plugins/train/_config.py:314
msgid "network"
msgstr ""
#: plugins/train/_config.py:273
msgid ""
"Use reflection padding rather than zero padding with convolutions. Each "
"convolution must pad the image boundaries to maintain the proper sizing. "
"More complex padding schemes can reduce artifacts at the border of the "
"image.\n"
"\t http://www-cs.engr.ccny.cuny.edu/~wolberg/cs470/hw/hw2_pad.txt"
msgstr ""
#: plugins/train/_config.py:286
msgid ""
"[Nvidia Only]. Enable the Tensorflow GPU 'allow_growth' configuration "
"option. This option prevents Tensorflow from allocating all of the GPU VRAM "
"at launch but can lead to higher VRAM fragmentation and slower performance. "
"Should only be enabled if you are receiving errors regarding 'cuDNN fails to "
"initialize' when commencing training."
msgstr ""
#: plugins/train/_config.py:299
msgid ""
"[Not PlaidML], NVIDIA GPUs can run operations in float16 faster than in "
"float32. Mixed precision allows you to use a mix of float16 with float32, to "
"get the performance benefits from float16 and the numeric stability benefits "
"from float32.\n"
"\n"
"This is untested on DirectML backend, but will run on most Nvidia models. it "
"will only speed up training on more recent GPUs. Those with compute "
"capability 7.0 or higher will see the greatest performance benefit from "
"mixed precision because they have Tensor Cores. Older GPUs offer no math "
"performance benefit for using mixed precision, however memory and bandwidth "
"savings can enable some speedups. Generally RTX GPUs and later will offer "
"the most benefit."
msgstr ""
#: plugins/train/_config.py:316
msgid ""
"If a 'NaN' is generated in the model, this means that the model has "
"corrupted and the model is likely to start deteriorating from this point on. "
"Enabling NaN protection will stop training immediately in the event of a "
"NaN. The last save will not contain the NaN, so you may still be able to "
"rescue your model."
msgstr ""
#: plugins/train/_config.py:329
msgid "convert"
msgstr ""
#: plugins/train/_config.py:331
msgid ""
"[GPU Only]. The number of faces to feed through the model at once when "
"running the Convert process.\n"
"\n"
"NB: Increasing this figure is unlikely to improve convert speed, however, if "
"you are getting Out of Memory errors, then you may want to reduce the batch "
"size."
msgstr ""
#: plugins/train/_config.py:350
msgid ""
"Loss configuration options\n"
"Loss is the mechanism by which a Neural Network judges how well it thinks "
"that it is recreating a face."
msgstr ""
#: plugins/train/_config.py:357 plugins/train/_config.py:369
#: plugins/train/_config.py:382 plugins/train/_config.py:402
#: plugins/train/_config.py:414 plugins/train/_config.py:434
#: plugins/train/_config.py:446 plugins/train/_config.py:466
#: plugins/train/_config.py:482 plugins/train/_config.py:498
#: plugins/train/_config.py:515
msgid "loss"
msgstr ""
#: plugins/train/_config.py:361
msgid "The loss function to use."
msgstr ""
#: plugins/train/_config.py:373
msgid ""
"The second loss function to use. If using a structural based loss (such as "
"SSIM, MS-SSIM or GMSD) it is common to add an L1 regularization(MAE) or L2 "
"regularization (MSE) function. You can adjust the weighting of this loss "
"function with the loss_weight_2 option."
msgstr ""
#: plugins/train/_config.py:388
msgid ""
"The amount of weight to apply to the second loss function.\n"
"\n"
"\n"
"\n"
"The value given here is as a percentage denoting how much the selected "
"function should contribute to the overall loss cost of the model. For "
"example:\n"
"\t 100 - The loss calculated for the second loss function will be applied at "
"its full amount towards the overall loss score. \n"
"\t 25 - The loss calculated for the second loss function will be reduced by "
"a quarter prior to adding to the overall loss score. \n"
"\t 400 - The loss calculated for the second loss function will be mulitplied "
"4 times prior to adding to the overall loss score. \n"
"\t 0 - Disables the second loss function altogether."
msgstr ""
#: plugins/train/_config.py:406
msgid ""
"The third loss function to use. You can adjust the weighting of this loss "
"function with the loss_weight_3 option."
msgstr ""
#: plugins/train/_config.py:420
msgid ""
"The amount of weight to apply to the third loss function.\n"
"\n"
"\n"
"\n"
"The value given here is as a percentage denoting how much the selected "
"function should contribute to the overall loss cost of the model. For "
"example:\n"
"\t 100 - The loss calculated for the third loss function will be applied at "
"its full amount towards the overall loss score. \n"
"\t 25 - The loss calculated for the third loss function will be reduced by a "
"quarter prior to adding to the overall loss score. \n"
"\t 400 - The loss calculated for the third loss function will be mulitplied "
"4 times prior to adding to the overall loss score. \n"
"\t 0 - Disables the third loss function altogether."
msgstr ""
#: plugins/train/_config.py:438
msgid ""
"The fourth loss function to use. You can adjust the weighting of this loss "
"function with the loss_weight_3 option."
msgstr ""
#: plugins/train/_config.py:452
msgid ""
"The amount of weight to apply to the fourth loss function.\n"
"\n"
"\n"
"\n"
"The value given here is as a percentage denoting how much the selected "
"function should contribute to the overall loss cost of the model. For "
"example:\n"
"\t 100 - The loss calculated for the fourth loss function will be applied at "
"its full amount towards the overall loss score. \n"
"\t 25 - The loss calculated for the fourth loss function will be reduced by "
"a quarter prior to adding to the overall loss score. \n"
"\t 400 - The loss calculated for the fourth loss function will be mulitplied "
"4 times prior to adding to the overall loss score. \n"
"\t 0 - Disables the fourth loss function altogether."
msgstr ""
#: plugins/train/_config.py:471
msgid ""
"The loss function to use when learning a mask.\n"
"\t MAE - Mean absolute error will guide reconstructions of each pixel "
"towards its median value in the training dataset. Robust to outliers but as "
"a median, it can potentially ignore some infrequent image types in the "
"dataset.\n"
"\t MSE - Mean squared error will guide reconstructions of each pixel towards "
"its average value in the training dataset. As an average, it will be "
"susceptible to outliers and typically produces slightly blurrier results."
msgstr ""
#: plugins/train/_config.py:488
msgid ""
"The amount of priority to give to the eyes.\n"
"\n"
"The value given here is as a multiplier of the main loss score. For "
"example:\n"
"\t 1 - The eyes will receive the same priority as the rest of the face. \n"
"\t 10 - The eyes will be given a score 10 times higher than the rest of the "
"face.\n"
"\n"
"NB: Penalized Mask Loss must be enable to use this option."
msgstr ""
#: plugins/train/_config.py:504
msgid ""
"The amount of priority to give to the mouth.\n"
"\n"
"The value given here is as a multiplier of the main loss score. For "
"Example:\n"
"\t 1 - The mouth will receive the same priority as the rest of the face. \n"
"\t 10 - The mouth will be given a score 10 times higher than the rest of the "
"face.\n"
"\n"
"NB: Penalized Mask Loss must be enable to use this option."
msgstr ""
#: plugins/train/_config.py:517
msgid ""
"Image loss function is weighted by mask presence. For areas of the image "
"without the facial mask, reconstruction errors will be ignored while the "
"masked face area is prioritized. May increase overall quality by focusing "
"attention on the core face area."
msgstr ""
#: plugins/train/_config.py:528 plugins/train/_config.py:570
#: plugins/train/_config.py:584 plugins/train/_config.py:593
msgid "mask"
msgstr ""
#: plugins/train/_config.py:531
msgid ""
"The mask to be used for training. If you have selected 'Learn Mask' or "
"'Penalized Mask Loss' you must select a value other than 'none'. The "
"required mask should have been selected as part of the Extract process. If "
"it does not exist in the alignments file then it will be generated prior to "
"training commencing.\n"
"\tnone: Don't use a mask.\n"
"\tbisenet-fp_face: Relatively lightweight NN based mask that provides more "
"refined control over the area to be masked (configurable in mask settings). "
"Use this version of bisenet-fp if your model is trained with 'face' or "
"'legacy' centering.\n"
"\tbisenet-fp_head: Relatively lightweight NN based mask that provides more "
"refined control over the area to be masked (configurable in mask settings). "
"Use this version of bisenet-fp if your model is trained with 'head' "
"centering.\n"
"\tcomponents: Mask designed to provide facial segmentation based on the "
"positioning of landmark locations. A convex hull is constructed around the "
"exterior of the landmarks to create a mask.\n"
"\tcustom_face: Custom user created, face centered mask.\n"
"\tcustom_head: Custom user created, head centered mask.\n"
"\textended: Mask designed to provide facial segmentation based on the "
"positioning of landmark locations. A convex hull is constructed around the "
"exterior of the landmarks and the mask is extended upwards onto the "
"forehead.\n"
"\tvgg-clear: Mask designed to provide smart segmentation of mostly frontal "
"faces clear of obstructions. Profile faces and obstructions may result in "
"sub-par performance.\n"
"\tvgg-obstructed: Mask designed to provide smart segmentation of mostly "
"frontal faces. The mask model has been specifically trained to recognize "
"some facial obstructions (hands and eyeglasses). Profile faces may result in "
"sub-par performance.\n"
"\tunet-dfl: Mask designed to provide smart segmentation of mostly frontal "
"faces. The mask model has been trained by community members and will need "
"testing for further description. Profile faces may result in sub-par "
"performance."
msgstr ""
#: plugins/train/_config.py:572
msgid ""
"Apply gaussian blur to the mask input. This has the effect of smoothing the "
"edges of the mask, which can help with poorly calculated masks and give less "
"of a hard edge to the predicted mask. The size is in pixels (calculated from "
"a 128px mask). Set to 0 to not apply gaussian blur. This value should be "
"odd, if an even number is passed in then it will be rounded to the next odd "
"number."
msgstr ""
#: plugins/train/_config.py:586
msgid ""
"Sets pixels that are near white to white and near black to black. Set to 0 "
"for off."
msgstr ""
#: plugins/train/_config.py:595
msgid ""
"Dedicate a portion of the model to learning how to duplicate the input mask. "
"Increases VRAM usage in exchange for learning a quick ability to try to "
"replicate more complex mask models."
msgstr ""

2
plugins/extract/_config.py
View File

@ -11,7 +11,7 @@ from lib.config import FaceswapConfig
_LANG = gettext.translation("plugins.extract._config", localedir="locales", fallback=True)
_ = _LANG.gettext
logger = logging.getLogger(__name__) # pylint: disable=invalid-name
logger = logging.getLogger(__name__)
class Config(FaceswapConfig):

265
plugins/train/_config.py
View File

@ -1,46 +1,54 @@
#!/usr/bin/env python3
""" Default configurations for models """
import gettext
import logging
import os
from lib.config import FaceswapConfig
from plugins.plugin_loader import PluginLoader
logger = logging.getLogger(__name__) # pylint: disable=invalid-name
# LOCALES
_LANG = gettext.translation("plugins.train._config", localedir="locales", fallback=True)
_ = _LANG.gettext
ADDITIONAL_INFO = ("\nNB: Unless specifically stated, values changed here will only take effect "
logger = logging.getLogger(__name__)
ADDITIONAL_INFO = _("\nNB: Unless specifically stated, values changed here will only take effect "
"when creating a new model.")
_LOSS_HELP = dict(
ffl="Focal Frequency Loss. Analyzes the frequency spectrum of the images rather than the "
_LOSS_HELP = {
"ffl": _(
"Focal Frequency Loss. Analyzes the frequency spectrum of the images rather than the "
"images themselves. This loss function can be used on its own, but the original paper "
"found increased benefits when using it as a complementary loss to another spacial loss "
"function (e.g. MSE). Ref: Focal Frequency Loss for Image Reconstruction and Synthesis "
"https://arxiv.org/pdf/2012.12821.pdf NB: This loss does not currently work on AMD cards.",
flip="Nvidia FLIP. A perceptual loss measure that approximates the difference perceived by "
"https://arxiv.org/pdf/2012.12821.pdf NB: This loss does not currently work on AMD "
"cards."),
"flip": _(
"Nvidia FLIP. A perceptual loss measure that approximates the difference perceived by "
"humans as they alternate quickly (or flip) between two images. Used on its own and this "
"loss function creates a distinct grid on the output. However it can be helpful when "
"used as a complimentary loss function. Ref: FLIP: A Difference Evaluator for "
"Alternating Images: "
"https://research.nvidia.com/sites/default/files/node/3260/FLIP_Paper.pdf",
gmsd=(
"https://research.nvidia.com/sites/default/files/node/3260/FLIP_Paper.pdf"),
"gmsd": _(
"Gradient Magnitude Similarity Deviation seeks to match the global standard deviation of "
"the pixel to pixel differences between two images. Similar in approach to SSIM. Ref: "
"Gradient Magnitude Similarity Deviation: An Highly Efficient Perceptual Image Quality "
"Index https://arxiv.org/ftp/arxiv/papers/1308/1308.3052.pdf"),
l_inf_norm=(
"l_inf_norm": _(
"The L_inf norm will reduce the largest individual pixel error in an image. As "
"each largest error is minimized sequentially, the overall error is improved. This loss "
"will be extremely focused on outliers."),
laploss=(
"laploss": _(
"Laplacian Pyramid Loss. Attempts to improve results by focussing on edges using "
"Laplacian Pyramids. As this loss function gives priority to edges over other low-"
"frequency information, like color, it should not be used on its own. The original "
"implementation uses this loss as a complimentary function to MSE. "
"Ref: Optimizing the Latent Space of Generative Networks "
"https://arxiv.org/abs/1707.05776"),
lpips_alex=(
"lpips_alex": _(
"LPIPS is a perceptual loss that uses the feature outputs of other pretrained models as a "
"loss metric. Be aware that this loss function will use more VRAM. Used on its own and "
"this loss will create a distinct moire pattern on the output, however it can be helpful "
@ -50,42 +58,43 @@ _LOSS_HELP = dict(
"Metric http://arxiv.org/abs/1801.03924\nThis variant uses the AlexNet backbone. A fairly "
"light and old model which performed best in the paper's original implementation.\nNB: "
"For AMD Users the final linear layer is not implemented."),
lpips_squeeze=(
"lpips_squeeze": _(
"Same as lpips_alex, but using the SqueezeNet backbone. A more lightweight "
"version of AlexNet.\nNB: For AMD Users the final linear layer is not implemented."),
lpips_vgg16="Same as lpips_alex, but using the VGG16 backbone. A more heavyweight model.\n"
"NB: For AMD Users the final linear layer is not implemented.",
logcosh=(
"lpips_vgg16": _(
"Same as lpips_alex, but using the VGG16 backbone. A more heavyweight model.\n"
"NB: For AMD Users the final linear layer is not implemented."),
"logcosh": _(
"log(cosh(x)) acts similar to MSE for small errors and to MAE for large errors. Like "
"MSE, it is very stable and prevents overshoots when errors are near zero. Like MAE, it "
"is robust to outliers."),
mae=(
"mae": _(
"Mean absolute error will guide reconstructions of each pixel towards its median value in "
"the training dataset. Robust to outliers but as a median, it can potentially ignore some "
"infrequent image types in the dataset."),
mse=(
"mse": _(
"Mean squared error will guide reconstructions of each pixel towards its average value in "
"the training dataset. As an avg, it will be susceptible to outliers and typically "
"produces slightly blurrier results. Ref: Multi-Scale Structural Similarity for Image "
"Quality Assessment https://www.cns.nyu.edu/pub/eero/wang03b.pdf"),
ms_ssim=(
"ms_ssim": _(
"Multiscale Structural Similarity Index Metric is similar to SSIM except that it "
"performs the calculations along multiple scales of the input image."),
smooth_loss=(
"smooth_loss": _(
"Smooth_L1 is a modification of the MAE loss to correct two of its disadvantages. "
"This loss has improved stability and guidance for small errors. Ref: A General and "
"Adaptive Robust Loss Function https://arxiv.org/pdf/1701.03077.pdf"),
ssim=(
"ssim": _(
"Structural Similarity Index Metric is a perception-based loss that considers changes in "
"texture, luminance, contrast, and local spatial statistics of an image. Potentially "
"delivers more realistic looking images. Ref: Image Quality Assessment: From Error "
"Visibility to Structural Similarity http://www.cns.nyu.edu/pub/eero/wang03-reprint.pdf"),
pixel_gradient_diff=(
"pixel_gradient_diff": _(
"Instead of minimizing the difference between the absolute value of each "
"pixel in two reference images, compute the pixel to pixel spatial difference in each "
"image and then minimize that difference between two images. Allows for large color "
"shifts, but maintains the structure of the image."),
none="Do not use an additional loss function.")
"none": _("Do not use an additional loss function.")}
_NON_PRIMARY_LOSS = ["flip", "lpips_alex", "lpips_squeeze", "lpips_vgg16", "none"]
@ -105,7 +114,7 @@ class Config(FaceswapConfig):
logger.debug("Setting global config")
section = "global"
self.add_section(section,
"Options that apply to all models" + ADDITIONAL_INFO)
_("Options that apply to all models") + ADDITIONAL_INFO)
self.add_item(
section=section,
title="centering",
@ -114,8 +123,9 @@ class Config(FaceswapConfig):
default="face",
choices=["face", "head", "legacy"],
fixed=True,
group="face",
info="How to center the training image. The extracted images are centered on the "
group=_("face"),
info=_(
"How to center the training image. The extracted images are centered on the "
"middle of the skull based on the face's estimated pose. A subsection of these "
"images are used for training. The centering used dictates how this subsection "
"will be cropped from the aligned images."
@ -128,7 +138,7 @@ class Config(FaceswapConfig):
"training with a mask that includes the hair (e.g. BiSeNet-FP-Head)."
"\n\tlegacy: The 'original' extraction technique. Centers the training image "
"near the tip of the nose with no adjustment. Can result in the edges of the "
"face appearing outside of the training area.")
"face appearing outside of the training area."))
self.add_item(
section=section,
title="coverage",
@ -137,8 +147,9 @@ class Config(FaceswapConfig):
min_max=(62.5, 100.0),
rounding=2,
fixed=True,
group="face",
info="How much of the extracted image to train on. A lower coverage will limit the "
group=_("face"),
info=_(
"How much of the extracted image to train on. A lower coverage will limit the "
"model's scope to a zoomed-in central area while higher amounts can include the "
"entire face. A trade-off exists between lower amounts given more detail "
"versus higher amounts avoiding noticeable swap transitions. For 'Face' "
@ -148,25 +159,26 @@ class Config(FaceswapConfig):
"\n\t62.5% spans from eyebrow to eyebrow."
"\n\t75.0% spans from temple to temple."
"\n\t87.5% spans from ear to ear."
"\n\t100.0% is a mugshot.")
"\n\t100.0% is a mugshot."))
self.add_item(
section=section,
title="icnr_init",
datatype=bool,
default=False,
group="initialization",
info="Use ICNR to tile the default initializer in a repeating pattern. "
group=_("initialization"),
info=_(
"Use ICNR to tile the default initializer in a repeating pattern. "
"This strategy is designed for pairing with sub-pixel / pixel shuffler "
"to reduce the 'checkerboard effect' in image reconstruction. "
"\n\t https://arxiv.org/ftp/arxiv/papers/1707/1707.02937.pdf")
"\n\t https://arxiv.org/ftp/arxiv/papers/1707/1707.02937.pdf"))
self.add_item(
section=section,
title="conv_aware_init",
datatype=bool,
default=False,
group="initialization",
info="Use Convolution Aware Initialization for convolutional layers. "
group=_("initialization"),
info=_(
"Use Convolution Aware Initialization for convolutional layers. "
"This can help eradicate the vanishing and exploding gradient problem "
"as well as lead to higher accuracy, lower loss and faster convergence.\nNB:"
"\n\t This can use more VRAM when creating a new model so you may want to "
@ -177,16 +189,17 @@ class Config(FaceswapConfig):
"multi-GPU and resume."
"\n\t Building the model will likely take several minutes as the calculations "
"for this initialization technique are expensive. This will only impact starting "
"a new model.")
"a new model."))
self.add_item(
section=section,
title="optimizer",
datatype=str,
gui_radio=True,
group="optimizer",
group=_("optimizer"),
default="adam",
choices=["adabelief", "adam", "nadam", "rms-prop"],
info="The optimizer to use."
info=_(
"The optimizer to use."
"\n\t adabelief - Adapting Stepsizes by the Belief in Observed Gradients. An "
"optimizer with the aim to converge faster, generalize better and remain more "
"stable. (https://arxiv.org/abs/2010.07468). NB: Epsilon for AdaBelief needs to "
@ -198,7 +211,7 @@ class Config(FaceswapConfig):
"Adam but uses a different formula for calculating momentum."
"\n\t rms-prop - Root Mean Square Propagation. Maintains a moving (discounted) "
"average of the square of the gradients. Divides the gradient by the root of "
"this average.")
"this average."))
self.add_item(
section=section,
title="learning_rate",
@ -207,12 +220,13 @@ class Config(FaceswapConfig):
min_max=(1e-6, 1e-4),
rounding=6,
fixed=False,
group="optimizer",
info="Learning rate - how fast your network will learn (how large are the "
group=_("optimizer"),
info=_(
"Learning rate - how fast your network will learn (how large are the "
"modifications to the model weights after one batch of training). Values that "
"are too large might result in model crashes and the inability of the model to "
"find the best solution. Values that are too small might be unable to escape "
"from dead-ends and find the best global minimum.")
"from dead-ends and find the best global minimum."))
self.add_item(
section=section,
title="epsilon_exponent",
@ -221,8 +235,9 @@ class Config(FaceswapConfig):
min_max=(-20, 0),
rounding=1,
fixed=False,
group="optimizer",
info="The epsilon adds a small constant to weight updates to attempt to avoid 'divide "
group=_("optimizer"),
info=_(
"The epsilon adds a small constant to weight updates to attempt to avoid 'divide "
"by zero' errors. Unless you are using the AdaBelief Optimizer, then Generally "
"this option should be left at default value, For AdaBelief, setting this to "
"around '-16' should work.\n"
@ -233,51 +248,55 @@ class Config(FaceswapConfig):
"final result.\n"
"NB: The value given here is the 'exponent' to the epsilon. For example, "
"choosing '-7' will set the epsilon to 1e-7. Choosing '-3' will set the epsilon "
"to 0.001 (1e-3).")
"to 0.001 (1e-3)."))
self.add_item(
section=section,
title="autoclip",
datatype=bool,
default=False,
info="[Not PlaidML] Apply AutoClipping to the gradients. AutoClip analyzes the "
info=_(
"[Not PlaidML] Apply AutoClipping to the gradients. AutoClip analyzes the "
"gradient weights and adjusts the normalization value dynamically to fit the "
"data. Can help prevent NaNs and improve model optimization at the expense of "
"VRAM. Ref: AutoClip: Adaptive Gradient Clipping for Source Separation Networks "
"https://arxiv.org/abs/2007.14469",
"https://arxiv.org/abs/2007.14469"),
fixed=False,
gui_radio=True,
group="optimizer")
group=_("optimizer"))
self.add_item(
section=section,
title="reflect_padding",
datatype=bool,
default=False,
group="network",
info="Use reflection padding rather than zero padding with convolutions. "
group=_("network"),
info=_(
"Use reflection padding rather than zero padding with convolutions. "
"Each convolution must pad the image boundaries to maintain the proper "
"sizing. More complex padding schemes can reduce artifacts at the "
"border of the image."
"\n\t http://www-cs.engr.ccny.cuny.edu/~wolberg/cs470/hw/hw2_pad.txt")
"\n\t http://www-cs.engr.ccny.cuny.edu/~wolberg/cs470/hw/hw2_pad.txt"))
self.add_item(
section=section,
title="allow_growth",
datatype=bool,
default=False,
group="network",
group=_("network"),
fixed=False,
info="[Nvidia Only]. Enable the Tensorflow GPU 'allow_growth' configuration option. "
info=_(
"[Nvidia Only]. Enable the Tensorflow GPU 'allow_growth' configuration option. "
"This option prevents Tensorflow from allocating all of the GPU VRAM at launch "
"but can lead to higher VRAM fragmentation and slower performance. Should only "
"be enabled if you are receiving errors regarding 'cuDNN fails to initialize' "
"when commencing training.")
"when commencing training."))
self.add_item(
section=section,
title="mixed_precision",
datatype=bool,
default=False,
fixed=False,
group="network",
info="[Not PlaidML], NVIDIA GPUs can run operations in float16 faster than in "
group=_("network"),
info=_(
"[Not PlaidML], NVIDIA GPUs can run operations in float16 faster than in "
"float32. Mixed precision allows you to use a mix of float16 with float32, to "
"get the performance benefits from float16 and the numeric stability benefits "
"from float32.\n\nThis is untested on DirectML backend, but will run on most "
@ -286,17 +305,18 @@ class Config(FaceswapConfig):
"mixed precision because they have Tensor Cores. Older GPUs offer no math "
"performance benefit for using mixed precision, however memory and bandwidth "
"savings can enable some speedups. Generally RTX GPUs and later will offer the "
"most benefit.")
"most benefit."))
self.add_item(
section=section,
title="nan_protection",
datatype=bool,
default=True,
group="network",
info="If a 'NaN' is generated in the model, this means that the model has corrupted "
group=_("network"),
info=_(
"If a 'NaN' is generated in the model, this means that the model has corrupted "
"and the model is likely to start deteriorating from this point on. Enabling NaN "
"protection will stop training immediately in the event of a NaN. The last save "
"will not contain the NaN, so you may still be able to rescue your model.",
"will not contain the NaN, so you may still be able to rescue your model."),
fixed=False)
self.add_item(
section=section,
@ -306,11 +326,12 @@ class Config(FaceswapConfig):
min_max=(1, 32),
rounding=1,
fixed=False,
group="convert",
info="[GPU Only]. The number of faces to feed through the model at once when running "
group=_("convert"),
info=_(
"[GPU Only]. The number of faces to feed through the model at once when running "
"the Convert process.\n\nNB: Increasing this figure is unlikely to improve "
"convert speed, however, if you are getting Out of Memory errors, then you may "
"want to reduce the batch size.")
"want to reduce the batch size."))
def _set_loss(self) -> None:
# pylint:disable=line-too-long
@ -326,45 +347,45 @@ class Config(FaceswapConfig):
logger.debug("Setting Loss config")
section = "global.loss"
self.add_section(section,
"Loss configuration options\n"
_("Loss configuration options\n"
"Loss is the mechanism by which a Neural Network judges how well it "
"thinks that it is recreating a face." + ADDITIONAL_INFO)
"thinks that it is recreating a face.") + ADDITIONAL_INFO)
self.add_item(
section=section,
title="loss_function",
datatype=str,
group="loss",
group=_("loss"),
default="ssim",
fixed=False,
choices=[x for x in sorted(_LOSS_HELP) if x not in _NON_PRIMARY_LOSS],
info="The loss function to use.\n\n\t" +
"\n\n\t".join(f"{k}: {v}"
info=(_("The loss function to use.") +
"\n\n\t" + "\n\n\t".join(f"{k}: {v}"
for k, v in sorted(_LOSS_HELP.items())
if k not in _NON_PRIMARY_LOSS))
if k not in _NON_PRIMARY_LOSS)))
self.add_item(
section=section,
title="loss_function_2",
datatype=str,
group="loss",
group=_("loss"),
default="mse",
fixed=False,
choices=list(sorted(_LOSS_HELP)),
info="The second loss function to use. If using a structural based loss (such as "
info=(_("The second loss function to use. If using a structural based loss (such as "
"SSIM, MS-SSIM or GMSD) it is common to add an L1 regularization(MAE) or L2 "
"regularization (MSE) function. You can adjust the weighting of this loss "
"function with the loss_weight_2 option.\n\n\t" +
"\n\n\t".join(f"{k}: {v}"
for k, v in sorted(_LOSS_HELP.items())))
"function with the loss_weight_2 option.") +
"\n\n\t" + "\n\n\t".join(f"{k}: {v}" for k, v in sorted(_LOSS_HELP.items()))))
self.add_item(
section=section,
title="loss_weight_2",
datatype=int,
group="loss",
group=_("loss"),
min_max=(0, 400),
rounding=1,
default=100,
fixed=False,
info="The amount of weight to apply to the second loss function.\n\n"
info=_(
"The amount of weight to apply to the second loss function.\n\n"
"\n\nThe value given here is as a percentage denoting how much the selected "
"function should contribute to the overall loss cost of the model. For example:"
"\n\t 100 - The loss calculated for the second loss function will be applied at "
@ -373,29 +394,30 @@ class Config(FaceswapConfig):
"quarter prior to adding to the overall loss score. "
"\n\t 400 - The loss calculated for the second loss function will be mulitplied "
"4 times prior to adding to the overall loss score. "
"\n\t 0 - Disables the second loss function altogether.")
"\n\t 0 - Disables the second loss function altogether."))
self.add_item(
section=section,
title="loss_function_3",
datatype=str,
group="loss",
group=_("loss"),
default="none",
fixed=False,
choices=list(sorted(_LOSS_HELP)),
info="The third loss function to use. You can adjust the weighting of this loss "
"function with the loss_weight_3 option.\n\n\t" +
"\n\n\t".join(f"{k}: {v}"
for k, v in sorted(_LOSS_HELP.items())))
info=(_("The third loss function to use. You can adjust the weighting of this loss "
"function with the loss_weight_3 option.") +
"\n\n\t" +
"\n\n\t".join(f"{k}: {v}" for k, v in sorted(_LOSS_HELP.items()))))
self.add_item(
section=section,
title="loss_weight_3",
datatype=int,
group="loss",
group=_("loss"),
min_max=(0, 400),
rounding=1,
default=0,
fixed=False,
info="The amount of weight to apply to the third loss function.\n\n"
info=_(
"The amount of weight to apply to the third loss function.\n\n"
"\n\nThe value given here is as a percentage denoting how much the selected "
"function should contribute to the overall loss cost of the model. For example:"
"\n\t 100 - The loss calculated for the third loss function will be applied at "
@ -404,29 +426,30 @@ class Config(FaceswapConfig):
"quarter prior to adding to the overall loss score. "
"\n\t 400 - The loss calculated for the third loss function will be mulitplied 4 "
"times prior to adding to the overall loss score. "
"\n\t 0 - Disables the third loss function altogether.")
"\n\t 0 - Disables the third loss function altogether."))
self.add_item(
section=section,
title="loss_function_4",
datatype=str,
group="loss",
group=_("loss"),
default="none",
fixed=False,
choices=list(sorted(_LOSS_HELP)),
info="The fourth loss function to use. You can adjust the weighting of this loss "
"function with the loss_weight_3 option.\n\n\t" +
"\n\n\t".join(f"{k}: {v}"
for k, v in sorted(_LOSS_HELP.items())))
info=(_("The fourth loss function to use. You can adjust the weighting of this loss "
"function with the loss_weight_3 option.") +
"\n\n\t" +
"\n\n\t".join(f"{k}: {v}" for k, v in sorted(_LOSS_HELP.items()))))
self.add_item(
section=section,
title="loss_weight_4",
datatype=int,
group="loss",
group=_("loss"),
min_max=(0, 400),
rounding=1,
default=0,
fixed=False,
info="The amount of weight to apply to the fourth loss function.\n\n"
info=_(
"The amount of weight to apply to the fourth loss function.\n\n"
"\n\nThe value given here is as a percentage denoting how much the selected "
"function should contribute to the overall loss cost of the model. For example:"
"\n\t 100 - The loss calculated for the fourth loss function will be applied at "
@ -435,62 +458,66 @@ class Config(FaceswapConfig):
"quarter prior to adding to the overall loss score. "
"\n\t 400 - The loss calculated for the fourth loss function will be mulitplied "
"4 times prior to adding to the overall loss score. "
"\n\t 0 - Disables the fourth loss function altogether.")
"\n\t 0 - Disables the fourth loss function altogether."))
self.add_item(
section=section,
title="mask_loss_function",
datatype=str,
group="loss",
group=_("loss"),
default="mse",
fixed=False,
choices=["mae", "mse"],
info="The loss function to use when learning a mask."
info=_(
"The loss function to use when learning a mask."
"\n\t MAE - Mean absolute error will guide reconstructions of each pixel "
"towards its median value in the training dataset. Robust to outliers but as "
"a median, it can potentially ignore some infrequent image types in the dataset."
"\n\t MSE - Mean squared error will guide reconstructions of each pixel "
"towards its average value in the training dataset. As an average, it will be "
"susceptible to outliers and typically produces slightly blurrier results.")
"susceptible to outliers and typically produces slightly blurrier results."))
self.add_item(
section=section,
title="eye_multiplier",
datatype=int,
group="loss",
group=_("loss"),
min_max=(1, 40),
rounding=1,
default=3,
fixed=False,
info="The amount of priority to give to the eyes.\n\nThe value given here is as a "
info=_(
"The amount of priority to give to the eyes.\n\nThe value given here is as a "
"multiplier of the main loss score. For example:"
"\n\t 1 - The eyes will receive the same priority as the rest of the face. "
"\n\t 10 - The eyes will be given a score 10 times higher than the rest of the "
"face."
"\n\nNB: Penalized Mask Loss must be enable to use this option.")
"\n\nNB: Penalized Mask Loss must be enable to use this option."))
self.add_item(
section=section,
title="mouth_multiplier",
datatype=int,
group="loss",
group=_("loss"),
min_max=(1, 40),
rounding=1,
default=2,
fixed=False,
info="The amount of priority to give to the mouth.\n\nThe value given here is as a "
info=_(
"The amount of priority to give to the mouth.\n\nThe value given here is as a "
"multiplier of the main loss score. For Example:"
"\n\t 1 - The mouth will receive the same priority as the rest of the face. "
"\n\t 10 - The mouth will be given a score 10 times higher than the rest of the "
"face."
"\n\nNB: Penalized Mask Loss must be enable to use this option.")
"\n\nNB: Penalized Mask Loss must be enable to use this option."))
self.add_item(
section=section,
title="penalized_mask_loss",
datatype=bool,
default=True,
group="loss",
info="Image loss function is weighted by mask presence. For areas of "
group=_("loss"),
info=_(
"Image loss function is weighted by mask presence. For areas of "
"the image without the facial mask, reconstruction errors will be "
"ignored while the masked face area is prioritized. May increase "
"overall quality by focusing attention on the core face area.")
"overall quality by focusing attention on the core face area."))
self.add_item(
section=section,
title="mask_type",
@ -498,9 +525,10 @@ class Config(FaceswapConfig):
default="extended",
choices=PluginLoader.get_available_extractors("mask",
add_none=True, extend_plugin=True),
group="mask",
group=_("mask"),
gui_radio=True,
info="The mask to be used for training. If you have selected 'Learn Mask' or "
info=_(
"The mask to be used for training. If you have selected 'Learn Mask' or "
"'Penalized Mask Loss' you must select a value other than 'none'. The required "
"mask should have been selected as part of the Extract process. If it does not "
"exist in the alignments file then it will be generated prior to training "
@ -531,7 +559,7 @@ class Config(FaceswapConfig):
"\n\tunet-dfl: Mask designed to provide smart segmentation of mostly frontal "
"faces. The mask model has been trained by community members and will need "
"testing for further description. Profile faces may result in sub-par "
"performance.")
"performance."))
self.add_item(
section=section,
title="mask_blur_kernel",
@ -539,12 +567,13 @@ class Config(FaceswapConfig):
min_max=(0, 9),
rounding=1,
default=3,
group="mask",
info="Apply gaussian blur to the mask input. This has the effect of smoothing the "
group=_("mask"),
info=_(
"Apply gaussian blur to the mask input. This has the effect of smoothing the "
"edges of the mask, which can help with poorly calculated masks and give less "
"of a hard edge to the predicted mask. The size is in pixels (calculated from "
"a 128px mask). Set to 0 to not apply gaussian blur. This value should be odd, "
"if an even number is passed in then it will be rounded to the next odd number.")
"if an even number is passed in then it will be rounded to the next odd number."))
self.add_item(
section=section,
title="mask_threshold",
@ -552,15 +581,17 @@ class Config(FaceswapConfig):
default=4,
min_max=(0, 50),
rounding=1,
group="mask",
info="Sets pixels that are near white to white and near black to black. Set to 0 for "
"off.")
group=_("mask"),
info=_(
"Sets pixels that are near white to white and near black to black. Set to 0 for "
"off."))
self.add_item(
section=section,
title="learn_mask",
datatype=bool,
default=False,
group="mask",
info="Dedicate a portion of the model to learning how to duplicate the input "
group=_("mask"),
info=_(
"Dedicate a portion of the model to learning how to duplicate the input "
"mask. Increases VRAM usage in exchange for learning a quick ability to try "
"to replicate more complex mask models.")
"to replicate more complex mask models."))