mirror of
https://github.com/deepfakes/faceswap
synced 2025-06-07 10:43:27 -04:00
cd00859c40
* model_refactor (#571) * original model to new structure * IAE model to new structure * OriginalHiRes to new structure * Fix trainer for different resolutions * Initial config implementation * Configparse library added * improved training data loader * dfaker model working * Add logging to training functions * Non blocking input for cli training * Add error handling to threads. Add non-mp queues to queue_handler * Improved Model Building and NNMeta * refactor lib/models * training refactor. DFL H128 model Implementation * Dfaker - use hashes * Move timelapse. Remove perceptual loss arg * Update INSTALL.md. Add logger formatting. Update Dfaker training * DFL h128 partially ported * Add mask to dfaker (#573) * Remove old models. Add mask to dfaker * dfl mask. Make masks selectable in config (#575) * DFL H128 Mask. Mask type selectable in config. * remove gan_v2_2 * Creating Input Size config for models Creating Input Size config for models Will be used downstream in converters. Also name change of image_shape to input_shape to clarify ( for future models with potentially different output_shapes) * Add mask loss options to config * MTCNN options to config.ini. Remove GAN config. Update USAGE.md * Add sliders for numerical values in GUI * Add config plugins menu to gui. Validate config * Only backup model if loss has dropped. Get training working again * bugfixes * Standardise loss printing * GUI idle cpu fixes. Graph loss fix. * mutli-gpu logging bugfix * Merge branch 'staging' into train_refactor * backup state file * Crash protection: Only backup if both total losses have dropped * Port OriginalHiRes_RC4 to train_refactor (OriginalHiRes) * Load and save model structure with weights * Slight code update * Improve config loader. Add subpixel opt to all models. Config to state * Show samples... wrong input * Remove AE topology. Add input/output shapes to State * Port original_villain (birb/VillainGuy) model to faceswap * Add plugin info to GUI config pages * Load input shape from state. IAE Config options. * Fix transform_kwargs. Coverage to ratio. Bugfix mask detection * Suppress keras userwarnings. Automate zoom. Coverage_ratio to model def. * Consolidation of converters & refactor (#574) * Consolidation of converters & refactor Initial Upload of alpha Items - consolidate convert_mased & convert_adjust into one converter -add average color adjust to convert_masked -allow mask transition blur size to be a fixed integer of pixels and a fraction of the facial mask size -allow erosion/dilation size to be a fixed integer of pixels and a fraction of the facial mask size -eliminate redundant type conversions to avoid multiple round-off errors -refactor loops for vectorization/speed -reorganize for clarity & style changes TODO - bug/issues with warping the new face onto a transparent old image...use a cleanup mask for now - issues with mask border giving black ring at zero erosion .. investigate - remove GAN ?? - test enlargment factors of umeyama standard face .. match to coverage factor - make enlargment factor a model parameter - remove convert_adjusted and referencing code when finished * Update Convert_Masked.py default blur size of 2 to match original... description of enlargement tests breakout matrxi scaling into def * Enlargment scale as a cli parameter * Update cli.py * dynamic interpolation algorithm Compute x & y scale factors from the affine matrix on the fly by QR decomp. Choose interpolation alogrithm for the affine warp based on an upsample or downsample for each image * input size input size from config * fix issues with <1.0 erosion * Update convert.py * Update Convert_Adjust.py more work on the way to merginf * Clean up help note on sharpen * cleanup seamless * Delete Convert_Adjust.py * Update umeyama.py * Update training_data.py * swapping * segmentation stub * changes to convert.str * Update masked.py * Backwards compatibility fix for models Get converter running * Convert: Move masks to class. bugfix blur_size some linting * mask fix * convert fixes - missing facehull_rect re-added - coverage to % - corrected coverage logic - cleanup of gui option ordering * Update cli.py * default for blur * Update masked.py * added preliminary low_mem version of OriginalHighRes model plugin * Code cleanup, minor fixes * Update masked.py * Update masked.py * Add dfl mask to convert * histogram fix & seamless location * update * revert * bugfix: Load actual configuration in gui * Standardize nn_blocks * Update cli.py * Minor code amends * Fix Original HiRes model * Add masks to preview output for mask trainers refactor trainer.__base.py * Masked trainers converter support * convert bugfix * Bugfix: Converter for masked (dfl/dfaker) trainers * Additional Losses (#592) * initial upload * Delete blur.py * default initializer = He instead of Glorot (#588) * Allow kernel_initializer to be overridable * Add ICNR Initializer option for upscale on all models. * Hopefully fixes RSoDs with original-highres model plugin * remove debug line * Original-HighRes model plugin Red Screen of Death fix, take #2 * Move global options to _base. Rename Villain model * clipnorm and res block biases * scale the end of res block * res block * dfaker pre-activation res * OHRES pre-activation * villain pre-activation * tabs/space in nn_blocks * fix for histogram with mask all set to zero * fix to prevent two networks with same name * GUI: Wider tooltips. Improve TQDM capture * Fix regex bug * Convert padding=48 to ratio of image size * Add size option to alignments tool extract * Pass through training image size to convert from model * Convert: Pull training coverage from model * convert: coverage, blur and erode to percent * simplify matrix scaling * ordering of sliders in train * Add matrix scaling to utils. Use interpolation in lib.aligner transform * masked.py Import get_matrix_scaling from utils * fix circular import * Update masked.py * quick fix for matrix scaling * testing thus for now * tqdm regex capture bugfix * Minor ammends * blur size cleanup * Remove coverage option from convert (Now cascades from model) * Implement convert for all model types * Add mask option and coverage option to all existing models * bugfix for model loading on convert * debug print removal * Bugfix for masks in dfl_h128 and iae * Update preview display. Add preview scaling to cli * mask notes * Delete training_data_v2.py errant file * training data variables * Fix timelapse function * Add new config items to state file for legacy purposes * Slight GUI tweak * Raise exception if problem with loaded model * Add Tensorboard support (Logs stored in model directory) * ICNR fix * loss bugfix * convert bugfix * Move ini files to config folder. Make TensorBoard optional * Fix training data for unbalanced inputs/outputs * Fix config "none" test * Keep helptext in .ini files when saving config from GUI * Remove frame_dims from alignments * Add no-flip and warp-to-landmarks cli options * Revert OHR to RC4_fix version * Fix lowmem mode on OHR model * padding to variable * Save models in parallel threads * Speed-up of res_block stability * Automated Reflection Padding * Reflect Padding as a training option Includes auto-calculation of proper padding shapes, input_shapes, output_shapes Flag included in config now * rest of reflect padding * Move TB logging to cli. Session info to state file * Add session iterations to state file * Add recent files to menu. GUI code tidy up * [GUI] Fix recent file list update issue * Add correct loss names to TensorBoard logs * Update live graph to use TensorBoard and remove animation * Fix analysis tab. GUI optimizations * Analysis Graph popup to Tensorboard Logs * [GUI] Bug fix for graphing for models with hypens in name * [GUI] Correctly split loss to tabs during training * [GUI] Add loss type selection to analysis graph * Fix store command name in recent files. Switch to correct tab on open * [GUI] Disable training graph when 'no-logs' is selected * Fix graphing race condition * rename original_hires model to unbalanced
180 lines
9.2 KiB
Python
180 lines
9.2 KiB
Python
#!/usr/bin/env python3
|
|
""" Default configurations for models """
|
|
|
|
import logging
|
|
|
|
from lib.config import FaceswapConfig
|
|
|
|
logger = logging.getLogger(__name__) # pylint: disable=invalid-name
|
|
|
|
MASK_TYPES = ["none", "dfaker", "dfl_full"]
|
|
MASK_INFO = "The mask to be used for training. Select none to not use a mask"
|
|
COVERAGE_INFO = ("How much of the extracted image to train on. Generally the model is optimized\n"
|
|
"to the default value. Sensible values to use 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.")
|
|
|
|
|
|
class Config(FaceswapConfig):
|
|
""" Config File for Models """
|
|
|
|
def set_defaults(self):
|
|
""" Set the default values for config """
|
|
logger.debug("Setting defaults")
|
|
# << GLOBAL OPTIONS >> #
|
|
section = "global"
|
|
self.add_section(title=section,
|
|
info="Options that apply to all models")
|
|
self.add_item(
|
|
section=section, title="icnr_init", datatype=bool, default=False,
|
|
info="Use ICNR Kernel Initializer for upscaling.\nThis can help reduce the "
|
|
"'checkerboard effect' when upscaling the image.")
|
|
self.add_item(
|
|
section=section, title="subpixel_upscaling", datatype=bool, default=False,
|
|
info="Use subpixel upscaling rather than pixel shuffler.\n"
|
|
"Might increase speed at cost of VRAM")
|
|
self.add_item(
|
|
section=section, title="reflect_padding", datatype=bool, default=False,
|
|
info="Use reflect padding rather than zero padding.")
|
|
self.add_item(
|
|
section=section, title="dssim_mask_loss", datatype=bool, default=True,
|
|
info="If using a mask, Use DSSIM loss for Mask training rather than Mean Absolute "
|
|
"Error\nMay increase overall quality.")
|
|
self.add_item(
|
|
section=section, title="penalized_mask_loss", datatype=bool, default=True,
|
|
info="If using a mask, Use Penalized loss for Mask training. Can stack with DSSIM.\n"
|
|
"May increase overall quality.")
|
|
|
|
# << DFAKER OPTIONS >> #
|
|
section = "model.dfaker"
|
|
self.add_section(title=section,
|
|
info="Dfaker Model (Adapted from https://github.com/dfaker/df)")
|
|
self.add_item(
|
|
section=section, title="mask_type", datatype=str, default="dfaker",
|
|
choices=MASK_TYPES, info=MASK_INFO)
|
|
self.add_item(
|
|
section=section, title="coverage", datatype=float, default=100.0, rounding=1,
|
|
min_max=(62.5, 100.0), info=COVERAGE_INFO)
|
|
|
|
# << DFL MODEL OPTIONS >> #
|
|
section = "model.dfl_h128"
|
|
self.add_section(title=section,
|
|
info="DFL H128 Model (Adapted from "
|
|
"https://github.com/iperov/DeepFaceLab)")
|
|
self.add_item(
|
|
section=section, title="lowmem", datatype=bool, default=False,
|
|
info="Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models "
|
|
"with a changed lowmem mode are not compatible with each other.")
|
|
self.add_item(
|
|
section=section, title="mask_type", datatype=str, default="dfl_full",
|
|
choices=MASK_TYPES, info=MASK_INFO)
|
|
self.add_item(
|
|
section=section, title="coverage", datatype=float, default=62.5, rounding=1,
|
|
min_max=(62.5, 100.0), info=COVERAGE_INFO)
|
|
|
|
# << IAE MODEL OPTIONS >> #
|
|
section = "model.iae"
|
|
self.add_section(title=section,
|
|
info="Intermediate Auto Encoder. Based on Original Model, uses "
|
|
"intermediate layers to try to better get details")
|
|
self.add_item(
|
|
section=section, title="dssim_loss", datatype=bool, default=False,
|
|
info="Use DSSIM for Loss rather than Mean Absolute Error\n"
|
|
"May increase overall quality.")
|
|
self.add_item(
|
|
section=section, title="mask_type", datatype=str, default="none",
|
|
choices=MASK_TYPES, info=MASK_INFO)
|
|
self.add_item(
|
|
section=section, title="coverage", datatype=float, default=62.5, rounding=1,
|
|
min_max=(62.5, 100.0), info=COVERAGE_INFO)
|
|
|
|
# << ORIGINAL MODEL OPTIONS >> #
|
|
section = "model.original"
|
|
self.add_section(title=section,
|
|
info="Original Faceswap Model")
|
|
self.add_item(
|
|
section=section, title="lowmem", datatype=bool, default=False,
|
|
info="Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models "
|
|
"with a changed lowmem mode are not compatible with each other.")
|
|
self.add_item(
|
|
section=section, title="dssim_loss", datatype=bool, default=False,
|
|
info="Use DSSIM for Loss rather than Mean Absolute Error\n"
|
|
"May increase overall quality.")
|
|
self.add_item(
|
|
section=section, title="mask_type", datatype=str, default="none",
|
|
choices=MASK_TYPES, info=MASK_INFO)
|
|
self.add_item(
|
|
section=section, title="coverage", datatype=float, default=62.5, rounding=1,
|
|
min_max=(62.5, 100.0), info=COVERAGE_INFO)
|
|
|
|
# << UNBALANCED MODEL OPTIONS >> #
|
|
section = "model.unbalanced"
|
|
self.add_section(title=section,
|
|
info="An unbalanced model with adjustable input size options.\n"
|
|
"This is an unbalanced model so b>a swaps may not work well")
|
|
self.add_item(
|
|
section=section, title="lowmem", datatype=bool, default=False,
|
|
info="Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models "
|
|
"with a changed lowmem mode are not compatible with each other. NB: lowmem will "
|
|
"override cutom nodes and complexity settings.")
|
|
self.add_item(
|
|
section=section, title="dssim_loss", datatype=bool, default=False,
|
|
info="Use DSSIM for Loss rather than Mean Absolute Error\n"
|
|
"May increase overall quality.")
|
|
self.add_item(
|
|
section=section, title="mask_type", datatype=str, default="none",
|
|
choices=MASK_TYPES, info=MASK_INFO)
|
|
self.add_item(
|
|
section=section, title="nodes", datatype=int, default=1024, rounding=64,
|
|
min_max=(512, 4096),
|
|
info="Number of nodes for decoder. Don't change this unless you "
|
|
"know what you are doing!")
|
|
self.add_item(
|
|
section=section, title="complexity_encoder", datatype=int, default=128,
|
|
rounding=16, min_max=(64, 1024),
|
|
info="Encoder Convolution Layer Complexity. sensible ranges: "
|
|
"128 to 160")
|
|
self.add_item(
|
|
section=section, title="complexity_decoder_a", datatype=int, default=384,
|
|
rounding=16, min_max=(64, 1024),
|
|
info="Decoder A Complexity.")
|
|
self.add_item(
|
|
section=section, title="complexity_decoder_b", datatype=int, default=512,
|
|
rounding=16, min_max=(64, 1024),
|
|
info="Decoder B Complexity.")
|
|
self.add_item(
|
|
section=section, title="input_size", datatype=int, default=128,
|
|
rounding=64, min_max=(64, 512),
|
|
info="Resolution (in pixels) of the image to train on.\n"
|
|
"BE AWARE Larger resolution will dramatically increase"
|
|
"VRAM requirements.\n"
|
|
"Make sure your resolution is divisible by 64 (e.g. 64, 128, 256 etc.).\n"
|
|
"NB: Your faceset must be at least 1.6x larger than your required input size.\n"
|
|
" (e.g. 160 is the maximum input size for a 256x256 faceset)")
|
|
self.add_item(
|
|
section=section, title="coverage", datatype=float, default=62.5, rounding=1,
|
|
min_max=(62.5, 100.0), info=COVERAGE_INFO)
|
|
|
|
# << VILLAIN MODEL OPTIONS >> #
|
|
section = "model.villain"
|
|
self.add_section(title=section,
|
|
info="A Higher resolution version of the Original "
|
|
"Model by VillainGuy.\n"
|
|
"Extremely VRAM heavy. Full model requires 9GB+ for batchsize 16")
|
|
self.add_item(
|
|
section=section, title="lowmem", datatype=bool, default=False,
|
|
info="Lower memory mode. Set to 'True' if having issues with VRAM useage.\nNB: Models "
|
|
"with a changed lowmem mode are not compatible with each other.")
|
|
self.add_item(
|
|
section=section, title="dssim_loss", datatype=bool, default=False,
|
|
info="Use DSSIM for Loss rather than Mean Absolute Error\n"
|
|
"May increase overall quality.")
|
|
self.add_item(
|
|
section=section, title="mask_type", datatype=str, default="none",
|
|
choices=["none", "dfaker", "dfl_full"],
|
|
info="The mask to be used for training. Select none to not use a mask")
|
|
self.add_item(
|
|
section=section, title="coverage", datatype=float, default=62.5, rounding=1,
|
|
min_max=(62.5, 100.0), info=COVERAGE_INFO)
|