1
0
Fork 0
mirror of https://github.com/deepfakes/faceswap synced 2025-06-09 04:36:50 -04:00
Commit graph

8 commits

Author SHA1 Message Date
torzdf
4153a7ea0d
Tools Restructure (#990)
* Restructure tools to allow dynamic (plugable) loading

* Update gui cli parsing to allow new tools structure
2020-03-16 19:12:52 +00:00
kvrooman
47681a8bab Landmarks stored and used as floating point numbers (#928)
* remove and fix int adjustments
* masking rounding
2019-11-15 11:01:37 +00:00
torzdf
78bd012a99 Align Eyes Deprecation - Bugfixes, Linting, and warning removal 2019-09-24 11:19:58 +01:00
kvrooman
139b581177 Align eyes deprecation (#851)
* align eyes removal

* add align_eyes tool
2019-09-24 11:16:03 +01:00
torzdf
88352b0268
De-Multiprocess Extract (#871)
* requirements.txt: - Pin opencv to 4.1.1 (fixes cv2-dnn error)

* lib.face_detect.DetectedFace: change LandmarksXY to landmarks_xy. Add left, right, top, bottom attributes

* lib.model.session: Session manager for loading models into different graphs (for Nvidia + CPU)

* plugins.extract._base: New parent class for all extract plugins

* plugins.extract.pipeline. Remove MultiProcessing. Dynamically limit batchsize for Nvidia cards. Remove loglevel input

* S3FD + FAN plugins. Standardise to Keras version for all backends

* Standardize all extract plugins to new threaded codebase

* Documentation. Start implementing Numpy style docstrings for Sphinx Documentation

* Remove s3fd_amd. Change convert OTF to expect DetectedFace object

* faces_detect - clean up and documentation

* Remove PoolProcess

* Migrate manual tool to new extract workflow

* Remove AMD specific extractor code from cli and plugins

* Sort tool to new extract workflow

* Remove multiprocessing from project

* Remove multiprocessing queues from QueueManager

* Remove multiprocessing support from logger

* Move face_filter to new extraction pipeline

* Alignments landmarksXY > landmarks_xy and legacy handling

* Intercept get_backend for sphinx doc build

# Add Sphinx documentation
2019-09-15 17:07:41 +01:00
torzdf
3a41cfdcbc
Add Face Hashes to Alignments (#550)
* 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
2018-12-14 12:49:11 +00:00
torzdf
2783c27e00
Fix convert-adjust (#531)
* Add dimensions to alignments + refactor

* Add frame_dims + funcs to DetectFaces. Add alignments lib

* Convert Adjust working

* Refactor and tidy up
2018-11-07 20:21:22 +00:00
torzdf
b26cbf5e03
Alignments Tool - Manual (#503)
* Initial alignment tool implementation

* Add face processing. Fix helptext formatting for cli and gui

* Extract faces from alignments file

* Add draw landmarks

* fix analysis hours past 24 bug

* Remove tools flag. Enlarge GUI tooltips

* Add filename extension check for image folders

* Fix folder nonetype bug and linting

* Bugfix renaming of faces

* Import alignments from DeepFaceLab

* Remove frames requirement for dfl

* Alignments Tool: Add remove frames

* Alignments: Add remove frames (#492)

* Alignments Tool: Add remove frames

* Implement Frame display for manual extract

* Alignments refactor

* Further navigation improvements

* Further navigation improvements

* Alignment Tool: Refactor

* Move rotate_image_by_angle() to utils

* Further refactoring improvements

* Reduce key bindings. Add skip to has faces, Add resize frame binding

* More navigation options. Delete faces added. Save alignments added

* Add: Reload alignments. Add extra api calls. Better redraw handling.

* Manual Alignments - Alpha Build

* Rotate landmarks for rotated images

* Rebase to remove OriginalHiRes changes
2018-09-17 16:31:43 +01:00