GithubStar/faceswap
1
0
Fork 0
mirror of https://github.com/deepfakes/faceswap.git synced 2026-10-18 14:34:30 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,734 Commits 7 Branches 6 Tags
r2.2
Commit Graph

280 Commits

Author SHA1 Message Date
torzdf 82e927d3e7 bugfix: Preview tool Don't error if too few images 2023-06-18 11:38:43 +01:00
torzdf 4a5a10977b Bugfix: Disable batch mode patch for non-Linux machines 2023-02-10 18:02:14 +00:00
torzdf 8a5ee6d9bf Bugfix: Patch extract memory leak in batch mode 2023-02-10 15:52:34 +00:00
torzdf a1ef5edd39 tests: 
- unit test: tools.alignments.media
  - Add mypy test
  - Typing fixes
 2023-01-21 00:41:18 +00:00
torzdf dc94ed9cad DirectML Support (#1291) 
* DML Support
  - Add requirements. Update setup.py. Update Windows Installer
  - Add 'directml' backend. Update backend supporting logic
  - GPUStats - Add GPU querying from Win SDK for DML backend
  - Windows PlaidML - Deprecation Warning
  - Remove deprecated '-d' training flag
  - Logging in DML functions
- Unittest
  - Windows Unit Test
  - lib.utils
 2023-01-06 14:45:57 +00:00
torzdf 9e2026f6fe Extract: Implement re-align/2nd pass 
- implement configurable re-align function in extract
  - update locales + documentation
  - re-factor align._base and split to separate modules
  - move normalization method to plugin parent
  - bugfix: FAN use zeros for pre-processing crop
  - lint AlignedFilter
 2022-11-22 00:37:29 +00:00
torzdf e3b457693e bugfix - extract filters: spaces in folder names 2022-11-10 01:41:40 +00:00
torzdf 0f5d2e887c Face-filter updates: 
- Allow selecting folder as well as multiple images
  - Lower default threshold and update helptext
  - bugfix: detector error when using all aligned faces
  - Standardize output folder name
 2022-11-04 18:43:55 +00:00
torzdf 1d1face00d Update Face Filter 
- Remove old face filter
  - plugins.extract.pipeline: Expose plugins directly
  - Change `is_aligned` from plugin level to ExtractMedia level
  - Allow extract pipeline to take faceswap aligned images
  - Add ability for recognition plugins to accept aligned faces as input
  - Add face filter to recognition plugin
  - Move extractor pipeline IO ops to own class
 2022-10-31 18:25:32 +00:00
torzdf 2e8ef5e3c8 GUI - Preview updates 
- Training preview. Embed preview pop-out window
  - Bugfix - convert/extract previews
 2022-10-20 18:51:39 +01:00
torzdf dab823a3eb Typing - lib.gui.display_command 2022-10-17 18:14:04 +01:00
torzdf f32f460e3f Refactoring 
- Change saved previews to PNG
  - Split lib.gui.utils
  - Disable flake8 on __init__ imports
 2022-10-15 19:17:24 +01:00
torzdf f1e3339fbe Add vggface2 to extraction pipeline 2022-10-10 13:09:02 +01:00
torzdf 220335f55d bugfix: Extract: Add video_meta to alignments dict 2022-09-26 22:51:25 +01:00
torzdf 1c8eb24b38 Bugfix: Correct naming of alignments file for videos with dots in filename 2022-09-23 14:14:29 +01:00
torzdf de11b4c189 Bugfix: Extract. numbering issue when binning results 2022-09-23 01:37:51 +01:00
torzdf 50d23792ca Aligner filter - set sensible defaults 2022-09-21 01:04:33 +01:00
torzdf 71726c1ff5 Extract: Add metric information to debug images 2022-09-19 02:14:09 +01:00
torzdf f5fa5b4337 Extract filter: Allow saving of filtered images 2022-09-19 00:13:41 +01:00
torzdf a8f22cc019 Extract updates: 
- Default CPU detector to MTCNN
  - add basic Aligner false positive filters
  - Typing: align + plugins
  - Use specific AlignerBatch class for alignment
  -
 2022-09-18 19:44:41 +01:00
torzdf 952d79922b Bugfixes: 
- Extract - batch mode. Exclude folders with no images
  - Train. Trigger the correct preview/mask update from gui trigger
 2022-09-13 18:54:01 +01:00
torzdf 7da2cc3dd2 Training - Use custom preview pop-out 2022-09-07 11:49:52 +01:00
torzdf ae7793e876 bugfix: convert - Process final items on truncated batch 2022-09-02 12:42:52 +01:00
torzdf 13cfb3f39e extract: Add batch processing mode 2022-08-31 19:48:47 +01:00
torzdf 04b197ec5f convert: reduce RAM consumption 2022-08-27 08:13:45 +01:00
torzdf 1022651eb8 Bugfix: convert - Gif Writer 
- Fix non-launch error on Gif Writer
  - convert plugins - linting
  - convert/fs_media/preview/queue_manager - typing
  - Change convert items from dict to Dataclass
 2022-08-26 23:56:03 +01:00
torzdf 9e503bdaa2 bugfix: debug landmarks 2022-08-23 19:19:16 +01:00
torzdf 2beceffad9 Data Augmentation update (#1263) 
- lib.detected_face
    - Subclass Masks for Landmark based masks
    - Add training mask propery + methods to DetectedFace
  - lib.training_training
    - subclass TrainingDataGenerator for training and preview data
    - Split cache into own module
    - Reduce thread count to 1 to prevent image corruption + data re-use
    - Process on largest model input/output size rather than stored image size
    - Size and crop masks during caching stage
    - Implement ring buffer for data flow
    - Fix preview reload bug
  - augmentation
    - typing
    - switch color aug order
    - better initialization
    - Fix warp + landmark warp to correctly apply at different image scales
    - Slightly improved warp caching
    - Don't store whether image is_preview. Handle all data as training images implicitly
  - plugins.trainer: Typing and fixes to work with trainingdata refactor
 2022-08-21 18:59:45 +01:00
torzdf 26e26c6288 Update TF to 2.9 
- Update TF to 2.7 to 2.9
    - Bump dependencies
    - Remove decode from pynvml calls
    - force keras predict functions to non-verbose
    - update tests
    - update Tensorboard logging
    - Update docs
 2022-08-02 17:12:26 +01:00
torzdf 2ea05623bd Update Distibution Strategies: 
- Add Central Storage Stategy
  - Deprecate 'distributed' cli argument
 2022-07-19 18:23:16 +01:00
torzdf c8122bc499 bugfix: Stop preview window from stealing focus 2022-07-06 11:15:51 +01:00
torzdf 3c73ae4ec9 bugfix: Update preview screen in GUI 2022-07-01 19:06:42 +01:00
torzdf 7b9fc0454d Live Preview - Replace cv2 with matplotlib viewer 2022-07-01 13:07:01 +01:00
torzdf b1a8183ab4 scripts.train - type checking 2022-06-30 18:41:58 +01:00
torzdf c279ac3518 Disable saving optimizer state option 2022-06-24 13:43:26 +01:00
torzdf 06468c97d4 Training: Add setting option to save optimizer weights 2022-06-23 14:54:09 +01:00
torzdf 0d23714875 bugfix: extract - stop progress bar from going over max value 2022-05-16 23:26:42 +01:00
torzdf b11ed6ead0 typofix 2022-05-13 12:10:51 +01:00
torzdf 0f7ee1603f training - Enable resize in popup preview image 2022-05-13 12:08:25 +01:00
Dhyey Patel feac8a0108 trainer: add support for non-interactive jobs (#1193) 
Add support for training in non-interactive shell environment such
as Sun Grid Engine, Univa Grid Engine and others.

Tested on Univa Grid Engine.

Reference: https://stackoverflow.com/questions/967369/python-find-out-if-running-in-shell-or-not-e-g-sun-grid-engine-queue.
 2022-05-04 23:07:31 +01:00
torzdf cf4b567cc6 Tensorflow 2.6 Support (#1182) 
* lib.cli.launcher - Bump max tf version to 2.6

* Remove pathlib requirement

* Update requirements files

* Update setup.py

* bugfix - GUI: Supress errors when attempting to load previews in extract

* GUI: Suppress ptxas error messages for Windows
 2021-09-05 02:25:12 +01:00
torzdf b5b0da42c8 convert - bugfix - Race condition when checking for predicted mask existence 2021-08-07 12:15:56 +01:00
torzdf ac22d40a91 extract: mask - Delete any mask from outside of frame boundaries 2021-07-22 13:04:29 +01:00
torzdf 60a4231832 Bugfixes 
- extract - debug landmarks - fix non integer errror
  - training (gui) - fix mask toggling
 2021-05-30 11:45:03 +01:00
torzdf 18e3139275 Updates 
- Change shortcut key to M
  - Slight optimizations
  - GUI support for mask toggling
 2021-05-28 19:41:11 +01:00
AnDenixa 486375ec99 - added push t to disable mask display at preview window 
trsprmvd

- added extra checks for mask presence in the set
 2021-05-28 18:00:08 +01:00
torzdf 3d914ee382 bugfix: Convert - don't error if no mask is selected 2021-05-21 10:52:39 +01:00
torzdf 8ec4b4fb82 bugfix: GUI - Correctly handle shutdown when closing during a running task 2021-05-04 10:07:41 +00:00
torzdf 29cfdaad46 Training startup updates 
- Remove alignments path option from cli
  - Restructure training_data.py
  - Load alignment data from PNG header during first epoch
  - lib.image.read_image_batch - Add option to return metadata
  - lib.utils.get_image_paths - Add option for explicit extension
  - plugins.train.trainer._base - remove pre-cache alignments code
  - scripts.train - Check first image in training folders for metadata
  - Documentation
 2021-03-21 23:29:31 +00:00
torzdf cff0f5698b GUI updates 
- Control panel fixes
  - Basic themeing support
  - Fix tools to display more natively
  - Give all config items a group
 2021-03-16 19:46:14 +00:00