simcop2387/faceswap
1
0
Fork 0
mirror of https://github.com/deepfakes/faceswap synced 2025-06-09 04:36:50 -04:00
Code Issues Releases Wiki Activity
1125 commits 7 branches 4 tags 319 MiB
Commit graph

20 commits

Author SHA1 Message Date
torzdf
cbba53ea67
Core Updates (#1015) 
- Remove lib.utils.keras_backend_quiet and replace with get_backend() where relevant
- Document lib.gpu_stats and lib.sys_info
- Remove call to GPUStats.is_plaidml from convert and replace with get_backend()
- lib.gui.menu - typofix
 2020-04-24 16:41:27 +01:00
torzdf
cbdef0b925 gpu_stats: log unhandled errors and continue 2019-07-30 17:20:13 +00:00
torzdf
5ee0f84c61 GPUStats: Bugfix for no Handles 2019-07-13 21:33:02 +00:00
torzdf
4908e82e23 Bugfixes 
lib/utils.py: Fix variable reference prior to assignment
lib/gpu_stats.py: Return warning rather than  error if NVML cannot be loaded.
 2019-07-13 16:03:01 +00:00
torzdf
f5dd18352c Fixups 
- GPUStats: Add more useful advice for pynvml errors
- Setup.py - Fix missing Cuda Path on Windows
- Setup.py - Handle Nonetype error on required packages
 2019-06-28 18:34:23 +01:00
torzdf
240751aff0 PlaidML Updates 
- Add fan-amd details to Cli
- Update Extract Parallel Processing rules for plaidML
- Handle missing plaidML lib on amd flag
- Pass through correct loglevel from GPUStats to plaidml_tools
 2019-06-23 17:57:09 +01:00
torzdf
11f35fa798 Fix Active Devices for plaidML. Add Supports PlaidML to Extractors 2019-06-20 18:25:28 +01:00
torzdf
779dd60280
Experimental AMD Support (#764) 
* PlaidML support in setup.py

* Add AMD flag for plaidml support

* PlaidML - Use .plaidML file if present, otherwise default to largest available

* Update training info message for GUI

* Add AMD option to Windows Installer

* Add quiet keras.backend importer and minor sysinfo amend.

* plug PlaidMLStats into GPUStats

* Update Docs
 2019-06-19 18:18:31 +01:00
torzdf
b156882405 Active Devices bugfix 2019-05-15 10:37:56 +01:00
torzdf
43de5e427d gpu_stats: Respect CUDA_VISIBLE_DEVICES 2019-05-01 11:00:35 +00:00
kilroythethird
7df92f6907 Catch nvml permission exception (#681) 2019-03-25 10:51:06 +00:00
torzdf
25349f60b9 bugfix 2018-12-27 12:14:25 +00:00
torzdf
1a31e7259b Return empty list for VRAM when no GPU Found 2018-12-27 11:54:05 +00:00
torzdf
38a0827e15 Bugfix: Return empty list when no GPU found 2018-12-27 11:34:44 +00:00
kilroythethird
7ff077a05a Catch pynvml.NVMLError_DriverNotLoaded Exception in gpu_stats (#552) 
* Catch pynvml.NVMLError_DriverNotLoaded Exception in gpu_stats

* Log when no CUDA able GPU is found

* Moved to logging to handle MacOs too
 2018-12-17 22:35:39 +00:00
torzdf
7f53911453
Logging (#541) 
* Convert prints to logger. Further logging improvements. Tidy  up

* Fix system verbosity. Allow SystemExit

* Fix reload extract bug

* Child Traceback handling

* Safer shutdown procedure

* Add shutdown event to queue manager

* landmarks_as_xy > property. GUI notes + linting. Aligner bugfix

* fix FaceFilter. Enable nFilter when no Filter is supplied

* Fix blurry face filter

* Continue on IO error. Better error handling

* Explicitly print stack trace tocrash log

* Windows Multiprocessing bugfix

* Add git info and conda version to crash log

* Windows/Anaconda mp bugfix

* Logging fixes for training
 2018-12-04 13:31:49 +00:00
torzdf
7b2cf02390 Bugfixes 2018-10-27 23:52:09 +01:00
torzdf
ca63242996
Extraction - Speed improvements (#522) (#523) 
* Extraction - Speed improvements (#522)

* Initial Plugin restructure

* Detectors to plugins. Detector speed improvements

* Re-implement dlib aligner, remove models, FAN to TF. Parallel processing

* Update manual, update convert, implement parallel/serial switching

* linting + fix cuda check (setup.py). requirements update keras 2.2.4

* Add extract size option. Fix dlib hog init

* GUI: Increase tooltip width

* Update alignment tool to support new DetectedFace

* Add skip existing faces option

* Fix sort tool to new plugin structure

* remove old align plugin

* fix convert -skip faces bug

* Fix convert skipping no faces frames

* Convert - draw onto transparent layer

* Fix blur threshold bug

* fix skip_faces convert bug

* Fix training
 2018-10-27 10:12:08 +01:00
1132719438
1ce5214e59 Fixed face extract with dlib on OS X (#510) 
* fix: gpu stat for OS X
- Use pynvx to get GPU info on OS X
- fix face extract with dlib

Issue #488
 2018-10-01 11:38:59 +01:00
torzdf
e76ab16bfe
Effmpeg preview, MTCNN Extractor. HiRes model fixes (#458) 
* 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
 2018-07-03 10:42:58 +02:00