slashtechno
/
wyzely-detect
mirror of https://github.com/slashtechno/wyzely-detect
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
93 Commits 10 Branches 4 Tags 533 KiB
Commit Graph

93 Commits

Author SHA1 Message Date
slashtechno bbcede0b3e
Check if video source is valid 2024-02-16 12:45:31 -06:00
slashtechno 8f500e0186
Multiple sources can now be used 
Added `--fake-second-source` to help with debugging
 2024-02-16 12:34:39 -06:00
slashtechno 494708a376
Supress TensorFlow warnings; update dependencies 
Also use PrettyTable to list source resolution
 2024-02-11 15:41:46 -06:00
slashtechno e9ace0f5e1
Merge pull request #10 from slashtechno/fix-dependency-issues 
Make PyTorch GPU functionality optional
 2024-02-11 14:29:13 -06:00
slashtechno 1a09004e3f
Made GPU capability toggleable 2024-02-11 14:27:05 -06:00
slashtechno 401c5cee16
Don't install TensorFlow with `and-cuda` 
Most likely, this will prevent the GPU from being used by Deepface.
Thus, the optimal solution would be to do something similar to Torch where the GPU capability is optional.
 2024-02-10 21:48:26 -06:00
slashtechno 3ac460a060
Made PyTorch GPU functionality optional 2024-02-10 21:38:22 -06:00
slashtechno d3c157df4d
(untested) - Added args for multiple sources 
Could not test due to dependency problems on Windows
 2024-02-10 21:16:11 -06:00
slashtechno 5cc5e04642
Works on MacOS? 2023-12-31 16:37:57 -06:00
slashtechno 82abe8b6d5
Fixed `--detect-object` when specifying multiple objects 2023-12-24 16:07:53 -06:00
slashtechno 06bd1ccbd7
Fixed incorrect warning when using `--detect-object` 2023-12-24 15:28:47 -06:00
slashtechno e7b63126d2
Fixed (?) prior error causing null `frame_to_show` 2023-12-22 16:44:21 -06:00
slashtechno bec1d5b979
Moved processing to `utils/utils.py` 
Crashes when another face is introduced
 2023-12-22 15:22:01 -06:00
slashtechno e2e4554031
Merge pull request #9 from funnukes/patch-1 
Update condition for more than one face in frame
 2023-12-09 10:21:36 -06:00
funnukes beeffdd8b8
Update condition for more than one face in frame 2023-12-09 21:40:41 +05:30
slashtechno fc943644fc
Somehow got CUDA working 2023-12-08 16:26:04 -06:00
slashtechno ecf47a05aa
Add devcontainer config 2023-12-02 21:32:53 -06:00
slashtechno 6928fdace5
Added flag to disable TensorFlow using GPU 
Added since on Linux, it seems Tensorflow attempts to use GPU by default
 2023-12-02 21:23:42 -06:00
slashtechno de5d6c1ab0
Fix `deepface` error when no images exist 
Accomplished by adding another check for ValueError message
Might be better to warn user if no images exist
 2023-12-02 18:21:41 -06:00
slashtechno b5d95ed963
Fixed unknown face causing error 2023-11-02 19:54:55 -05:00
slashtechno 1cf74e13ed
Add details on installing from PyPi in README 
Also:
- Bump version to `0.1.1`
- Pull Docker image rather than building in docker-compose.yml
 2023-10-27 12:54:28 -05:00
slashtechno 8026fd88f2
Merge pull request #7 from slashtechno/improve-argparse-organization 
Improve argparse organization
 2023-10-27 12:01:51 -05:00
slashtechno 85b59f4c21
Fixed nonexistent arg being used for RTSP 2023-10-27 12:00:17 -05:00
slashtechno 9e39132506
Add more groups to argparse 2023-10-27 11:52:33 -05:00
slashtechno 5af2b24fe4
Rename `--url` to `--rtsp-url` 2023-10-27 11:37:38 -05:00
slashtechno 792a095782
Add `--no-remove-representations` 2023-10-27 11:33:05 -05:00
slashtechno 32d523b727
Add `--face-confidence-threshold` 2023-10-27 11:23:44 -05:00
slashtechno eedc2783c9
Make ntfy url optional 2023-10-27 11:08:17 -05:00
slashtechno f669a39056
Move argparse code to `cli_args.py` 2023-10-27 10:54:36 -05:00
slashtechno 3235bb61bb
Merge pull request #6 from slashtechno/publish-to-pypi 
Prepare to publish to PyPi
 2023-10-22 16:57:45 -05:00
slashtechno 259cc8f200
Format code 2023-10-22 16:54:30 -05:00
slashtechno 504ccb6695
Changed repo URL and added repo to pyproject.toml 2023-10-22 16:53:29 -05:00
slashtechno c767a819c2
Added facial recognition confidence threshold 
Also reset version and added release workflow
 2023-10-22 16:45:01 -05:00
slashtechno 4f1f253c6c
Fix representations_<model>.pkl not being created 2023-10-22 16:20:57 -05:00
slashtechno 2cf945feec
Check if face directory exists; switch to ArcFace 
Other fixes:
* Improve error handling during face recognition
* Change VS Code run configuration name
* Update `deepface-test.ipynb`
* Reset version to `0.1.0` (not pushed to PyPi yet)
 2023-10-22 12:02:07 -05:00
slashtechno d83315518a
Standardize program name and description 2023-10-22 09:24:11 -05:00
slashtechno 96247767fb
Changed project name to `wyzely-detect` 2023-10-21 19:59:02 -05:00
slashtechno 4f8e26b2a2
Free up space when building Docker image 2023-10-15 15:48:36 -05:00
slashtechno 6e8e3b6eee
Disabled Docker caching in docker.yml 2023-10-15 15:39:33 -05:00
slashtechno 0daa8ddd3b
Merge pull request #5 from slashtechno/object-detection 
Add object detection and switch to Deepface
 2023-10-14 22:38:56 -05:00
slashtechno cb6c705e9d
Removed requirements.txt 2023-10-14 22:38:28 -05:00
slashtechno 8cc9054e67
Fixed Docker support and updated README.md 2023-10-14 22:31:48 -05:00
slashtechno 1d17bb629b
Fixed scaling 🎉 2023-10-14 19:25:27 -05:00
slashtechno 7d942ee456
Merge pull request #4 from slashtechno/deepface 
Add facial recognition
 2023-10-14 17:39:49 -05:00
slashtechno b2f10280b3
Fix facial recognition 
Scaling still seems to be imperfect
 2023-10-14 17:37:42 -05:00
slashtechno b6948aded2
Allow program to be run as a script 2023-10-14 15:46:42 -05:00
slashtechno 3bf1966bfd
Manage timers in notify.py 2023-10-14 15:40:36 -05:00
slashtechno 3c6919d2c6
Create Deepface Jupyter Notebook 2023-10-13 20:51:16 -05:00
slashtechno 556a90da3c
Format 2023-10-13 18:16:55 -05:00
slashtechno 000692a7af
Optionally only detect specific objects 2023-10-13 18:13:46 -05:00