* Separate predict and implement pool
* Add check and raise error to multithreading
Box functions to config. Add crop box option.
* All masks to mask module. Refactor convert masks
Predicted mask passed from model. Cli update
* Intesect box with mask and fixes
* Use raw NN output for convert
Use raw mask for face adjustments. Split adjustments to pre and post warp
* Separate out adjustments. Add unmask sharpen
* Set sensible defaults. Pre PR Testing
* Fix queue sizes. Move masked.py to lib
* Fix Skip Frames. Fix GUI Config popup
* Sensible queue limits. Add a less resource intensive single processing mode
* Fix predicted mask. Amend smooth box defaults
* Deterministic ordering for video output
* Video to Video convert implemented
* Fixups
- Remove defaults from folders across all stages
- Move match-hist and aca into color adjustments selectable
- Handle crashes properly for pooled processes
- Fix output directory does not exist error when creating a new output folder
- Force output to frames if input is not a video
* Add Color Transfer adjustment method
Wrap info text in GUI plugin configure popup
* Refactor image adjustments. Easier to create plugins
Start implementing config options for video encoding
* Add video encoding config options
Allow video encoding for frames input (must pass in a reference video)
Move video and image output writers to plugins
* Image writers config options
Move scaling to cli
Move draw_transparent to images config
Add config options for cv2 writer
Add Pillow image writer
* Add gif filetype to Pillow. Fix draw transparent for Pillow
* Add Animated GIF writer
standardize opencv/pillow defaults
* [speedup] Pre-encode supported writers in the convert pool (opencv, pillow)
Move scaling to convert pool
Remove dfaker mask
* Fix default writer
* Bugfixes
* Better custom argparse formatting
* 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
* Convert main scripts to use face hashes
* Alignment tool: Use hashes, add logging, add face rename function
* More logging. Update Manual tool to work with hashing
* Add preview functionality to effmpeg. (#435)
* Add preview functionality to effmpeg.
effmpeg tool:
Preview for actions that have a video output now available.
Preview does not work when muxing audio.
* Model json unicode fix1 (#443)
* fixed Windows 10 path error while loading weights
* - fixed TypeError: the JSON object must be str, not 'bytes' with OriginalHighRes Model
* MTCNN Extractor and Extraction refactor (#453)
* implement mtcnn extractor
* mtcnn refactor and vram management changes
* cli arguments update for mtcnn/dlib split
* Add mtcnn models to gitignore
* Change multiprocessing on extract
* GUI changes to handle nargs defaults
* Early exit bugfix (#455)
* Fix extract early termination bug
* Fix extract early exit bug
* Multi face detection bugfix (#456)
* Multi face extraction fix
* Original high res cleanup 1 (#457)
* slight model re-factoring
- removed excess threading code
- added random kernel initialization to dense layer
* Slight OriginalHighRes re-factoring an code cleanup
* Improving performance of extraction. Two main changes to improve the most recent modifications to extract: 1st FaceLandmarkExtractor would try to use cnn first, then try hog. The problem was that this reduced the speed by 4 for images where cnn didn't find anything, and most of the times hog wouldn't find anything either or it would be a bad extract. For me it wasn't worth it. With this you can specify on input -D if you want to use hog, cnn, or all. 'all' will try cnn, then hog like FaceLandmarkExtractor was doing. cnn or hog will just use 1 detection method. 2nd change is a rehaul of the verbose parameter. Now warnings when a face is not detected will just be shown if indicated by -v or --verbose. This restores the verbose function to what it once was. With this change I was able to process 1,000 per each 4 minutes regardless if faces were detected or not. Performance improvement just applies to not detected images but I normally will have lots of images without clear faces in my set, so I figured it would impact others. Also the introduction of 'all' would allow trying other models together more easily in the future.
* Update faces_detect.py
* Update extract.py
* Update FaceLandmarksExtractor.py
* spacing fix
* Image rotator for extract and convert ready for testing
* Revert "Image rotator for extract and convert ready for testing"
This reverts commit bbeb19ef26.
Error in extract code
* add image rotation support to detect more faces
* Update convert.py
Amended to do a single check for for rotation rather than checking twice. Performance gain is likely to be marginal to non-existent, but can't hurt.
* Update convert.py
remove type
* cli.py: Only output message on verbose. Convert.py: Only check for rotation amount once
* Changed command line flag to take arguments to ease future development
* Realigning for upstream/Master
* Minor fix
* Change default rotation value from None to 0
* Image rotator for extract and convert ready for testing
* Revert "Image rotator for extract and convert ready for testing"
This reverts commit bbeb19ef26.
Error in extract code
* add image rotation support to detect more faces
* Update convert.py
Amended to do a single check for for rotation rather than checking twice. Performance gain is likely to be marginal to non-existent, but can't hurt.
* Update convert.py
remove type
* cli.py: Only output message on verbose. Convert.py: Only check for rotation amount once
* Changed command line flag to take arguments to ease future development
* Realigning for upstream/Master
* Minor fix
* port 'face_alignment' from PyTorch to Keras. It works x2 faster, but initialization takes 20secs.
2DFAN-4.h5 and mmod_human_face_detector.dat included in lib\FaceLandmarksExtractor
fixed dlib vs tensorflow conflict: dlib must do op first, then load keras model, otherwise CUDA OOM error
if face location not found by CNN, its try to find by HOG.
removed this:
- if face.landmarks == None:
- print("Warning! landmarks not found. Switching to crop!")
- return cv2.resize(face.image, (size, size))
because DetectedFace always has landmarks
* removing DetectedFace.landmarks
* Preparing GAN plugin
* Adding multithreading for extract
* Adding support for mmod human face detector
* Adding face filter argument
* Added process number argument to multiprocessing extractor.
Fixed progressbar for multiprocessing.
* Added tiff as image type.
compression artefacts hurt my feelings.
* Cleanup
* Making Models as plugins
* Do not reload model on each image #39 + Adding FaceFilter #53
* Adding @lukaville PR for #43 and #44 (possibly)
* Training done in a separate thread
* Better log for plugin load
* Adding a prefetch to train.py #49
(Note that we prefetch 2 batches of images, due to the queue behavior)
+ More compact logging with verbose info included
* correction of DirectoryProcessor signature
* adding missing import
* Convert with parallel preprocessing of files
* Added coverage var for trainer
Added a var with comment. Feel free to add it as argument
* corrections
* Modifying preview and normalization of image + correction
* Cleanup
Added face_recongition from
https://github.com/ageitgey/face_recognition/
It is based on dlib, but does not have the glitches I had previously!
Also reworked Dockerfile (sticking to Python2 for now)
