1
0
Fork 0
mirror of https://github.com/deepfakes/faceswap synced 2025-06-07 10:43:27 -04:00
Commit graph

1835 commits

Author SHA1 Message Date
torzdf
2a3845152b bugfix: Convert - patch writer. Fix TIFF metadata 2024-01-07 14:58:48 +00:00
torzdf
b72b730adb setup.py:
- Don't try to call ldconfig when it doesn't exist
  - Adjust Cuda versions to TF compiled versions
  - Multiple package install handling
  - Use XFT version of tk under Linux
2024-01-05 13:46:07 +00:00
torzdf
a62a85c021 bugfix: setup.py - Force pip for imagio-ffmpeg 2023-11-17 02:09:55 +00:00
torzdf
4557331cb9 bugfix: Preview in GUI when converting to vid/gif 2023-10-24 23:47:08 +01:00
torzdf
8e6c6c3500 patch writer: Sort the json file by key 2023-10-04 10:47:59 +01:00
torzdf
3336772ff1 bugfix: patch writer - remove hard coded values 2023-09-30 12:19:04 +01:00
torzdf
f23c87c899 bugfix: Preview tool regression 2023-09-29 14:50:52 +01:00
torzdf
e80ae046d5
Convert - Patch writer (#1352)
* Add cli-args and config opts for patch writer
* Add supporting code to convert funcs
* writers
  - move frame count functions to _base
  - Add kwargs for pre_encode
* scripts/lib convert - add code for patch writer
* lib.image.encode_image - Add cv2.imencode args
* patch_defaults: Add face index location option
* Add patch writer with PNG support
* Send correct matrix to patch plugin
* Add canvas origin option
* Add Tiff format to Patch Writer
* Docs and locales
* Add ROI to output
* convert: choose warp border by face count
2023-09-28 11:55:38 +01:00
torzdf
a660eda8e1 Convert: Add face scale option 2023-09-09 18:40:36 +01:00
torzdf
48aca1462a bugfix: LR finder. Reset optimizer state 2023-09-08 09:48:09 +01:00
torzdf
8388241db9 bugfix: Always load images as 3 channel color 2023-09-01 22:36:31 +01:00
torzdf
4588adbd16 remove debug code 2023-09-01 19:44:57 +01:00
torzdf
460a229e79 bugfix: edge case NaN in pose estimation 2023-09-01 19:43:05 +01:00
torzdf
603fdc2a35 Phaze A - Allow outputs divisible by 16 2023-09-01 09:50:47 +01:00
torzdf
5d00025884 bugfix: error loading images with special chars 2023-08-27 02:15:55 +01:00
torzdf
cf0efff6ba
Learning Rate finder (#1341)
* Add LR Finder support structure

* Move trainer.Feeder to lib.training.generator

* Expose model.io

* Add lr_finder

* Update docs and locales

* Pre-PR fixups
  - Fix training graph not displaying
  - CI fixes
  - Switch lr finder progress to tqdm
  - Exit lr finder early on NaN
  - Display lr finder progress in GUI
2023-08-22 17:07:36 +01:00
torzdf
68a3322748 bugfix: train - fix learn_mask training 2023-08-09 19:37:24 +01:00
torzdf
0bba6ffd8b bugfix: train - fix occasional mem leak in preview 2023-08-06 13:16:32 +01:00
torzdf
81e3bf5cbe
Merge pull request #1331 from torzdf/macos
macOS Installer
2023-07-14 14:00:44 +01:00
torzdf
31eff9c096 macos fixes
- setup.py - reduce width of progress bar
  - macos bash install script
  - macos app launcher
2023-07-14 01:40:41 +01:00
torzdf
12814ce049 bugfix: Manual tool - face filtering 2023-07-12 08:23:48 +01:00
torzdf
1786d7a4d6
Merge pull request #1330 from torzdf/clip3
Add visual encoder from CLIP to Phaze-A encoders
2023-07-11 23:39:57 +01:00
torzdf
c34756c828 fixes
- Farl weight name fix
  - Embedding layers to fp32
  - nn_blocks - unique names for conv_output
  - Phaze-A - Add clipfaker presets
2023-07-11 23:11:47 +01:00
torzdf
fb7084effa Merge branch 'clip' into clip3 2023-07-08 18:04:45 +01:00
torzdf
c4204c7d8a Updates:
- Remove clipfaker
    - Add clip to Phaze-A
    - streamline clip to vision only
    - update lib.model.networks
    - Docs and tests update
    - Phaze-A - add option to flatten bottleneck
2023-07-08 17:20:39 +01:00
torzdf
6a3b4ed4b3 Training fixes:
- Fix mixed precision layer storing and switching
  - typofix in _requirements_base.txt
  - lib.model.layers - cleanup, docs and tests fixes
  - lib.model.nn_blocks - typing fixes
2023-07-08 16:47:25 +01:00
torzdf
c39a77f63e bugfix: setup.py pull in zlib-wapi on nvidia windows 2023-07-06 13:33:30 +01:00
torzdf
efbbe55267 bugfix: Pillow version pinning 2023-07-06 11:41:17 +01:00
torzdf
93d5a1a031 bugfix: DirectML backend GPU stats 2023-07-06 11:34:03 +01:00
torzdf
1bcc151cc5 bugfix: lib.gui.wrapper - Allow errors in stdout 2023-07-01 10:45:38 +01:00
torzdf
c22e105f18 bugfix: setup.py - fix logic ordering 2023-06-30 22:15:13 +01:00
torzdf
2bf529ad65 bugfix: Optimizer save error on older models 2023-06-30 12:14:23 +01:00
torzdf
f4c912e273 bugfix: GUI force stdout/stderr reading to utf-8 2023-06-30 11:52:58 +01:00
torzdf
8fb96b0d6e mask tool: log and exit if batch not using folder 2023-06-30 09:42:52 +01:00
torzdf
4e7e5fe308 bugfix: graph pop-up - log/linear switching 2023-06-30 09:30:21 +01:00
torzdf
ce86d091db bugfix: git communication fixes 2023-06-30 02:45:19 +01:00
torzdf
b870c7d9bb typofix 2023-06-28 19:17:43 +01:00
torzdf
467ff6bf20 bugfix: Handle dtype change for cv2-dnn aligner 2023-06-28 19:16:03 +01:00
torzdf
99fd844bb3 bugfix: plugins.aligner - predict dtype 2023-06-28 18:54:59 +01:00
torzdf
4b20316975 bugfix: manual tool - alignments saving 2023-06-28 18:43:37 +01:00
torzdf
efa4471243 typing:
- tools.manual.detected_faces
  - tools.manual.thumbnails
2023-06-28 18:30:17 +01:00
torzdf
adc96b7d31 bugfix: Sphinx Requirements 2023-06-27 18:34:43 +01:00
torzdf
bb532c6e4a typofix: sphinx_requirements.txt 2023-06-27 18:32:26 +01:00
torzdf
caa97d2d36 bugfix: Sphjinx Requirements 2023-06-27 18:28:37 +01:00
torzdf
dd03aa8573 setup.py: Revert redundant conda check 2023-06-27 18:03:41 +01:00
torzdf
4819d5b97d bugfixes:
- Remove duplicate line from Dockerfile.gpu
  - Add more robust Conda checking
2023-06-27 16:05:53 +01:00
torzdf
6a3b674bef
Rebase code (#1326)
* Remove tensorflow_probability requirement

* setup.py - fix progress bars

* requirements.txt: Remove pre python 3.9 packages

* update apple requirements.txt

* update INSTALL.md

* Remove python<3.9 code

* setup.py - fix Windows Installer

* typing: python3.9 compliant

* Update pytest and readthedocs python versions

* typing fixes

* Python Version updates
  - Reduce max version to 3.10
  - Default to 3.10 in installers
  - Remove incompatible 3.11 tests

* Update dependencies

* Downgrade imageio dep for Windows

* typing: merge optional unions and fixes

* Updates
  - min python version 3.10
  - typing to python 3.10 spec
  - remove pre-tf2.10 code
  - Add conda tests

* train: re-enable optimizer saving

* Update dockerfiles

* Update setup.py
  - Apple Conda deps to setup.py
  - Better Cuda + dependency handling

* bugfix: Patch logging to prevent Autograph errors

* Update dockerfiles

* Setup.py - Setup.py - stdout to utf-8

* Add more OSes to github Actions

* suppress mac-os end to end test
2023-06-27 11:27:47 +01:00
torzdf
e4ba12ad2a tests: Fix event-reader test 2023-06-21 22:51:59 +01:00
torzdf
a903a55837 bugfix: Correctly read event data in GUI 2023-06-21 22:45:40 +01:00
torzdf
c3f38bf80b bugfix: Windows installer - venv creation 2023-06-21 17:41:25 +01:00