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

13 commits

Author SHA1 Message Date
kvrooman
64a400f6b4 Refine S3FD post-processing: NMS box voting (#902) 2019-11-14 12:49:47 +00:00
torzdf
ad035f2a24 Optimize Extract parallel VRAM allocation 2019-10-19 23:53:42 +00:00
torzdf
29a75b90d4 Extract: Expose "allow_growth" option 2019-09-29 12:06:04 +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
502df1e4a9 Bump S3FD VRam requiremets 2019-08-03 17:03:23 +00:00
torzdf
8e9c901aeb Bugfix: Extract - Remove BoundingBox object and replace with dict 2019-07-06 09:44:01 +00:00
torzdf
148318778c
Face filter vgg face (#724)
* Implement extraction pipeline

* Face filter to vgg_face. Resume partial model downloads

* On-the-fly conversion to extraction pipeline

* Move git model ids from get_model to model definition
2019-05-11 18:43:09 +01:00
torzdf
ab7fa48b8b Remove dlib.rectangles. Replace with BoundingBox class 2019-05-07 10:01:00 +00:00
torzdf
ffd72b32d6 Remove all saved models from repo
All models now download when required
Model downloader can handle multiple files in model
2019-05-07 00:18:08 +00:00
torzdf
6c6aac77aa Dlib Detector Removal. CV2 Detector add. Bugfix on-the-fly convert
Remove dlib-hog + dlib-cnn detectors
Add cv2-dnn detector
Change on-the-fly detector to cv2-dnn
Bugfix: on-the-fly conversion
Bugfix: Pool processes
2019-05-01 22:46:33 +00:00
torzdf
86947eca37 Allow s3fd to run at less than optimal vram availability 2019-03-09 13:19:23 +00:00
torzdf
a12ae63265 Better extractor error handling on initialization 2019-03-09 12:43:40 +00:00
torzdf
f2e4c5a12c
S3fd detector (#649)
* Implement s3fd detect plugin

* s3fd: Add confidence slider to config. Update cli helptext
2019-03-08 11:00:47 +00:00