142c6c4de8
Refactor constants management to use Pydantic BaseModel for configuration
...
- Replaced module-level path variables in constants.py with a structured Pydantic Config class.
- Updated all relevant modules (train.py, augmentation.py, exports.py, dataset-visualiser.py, manual_run.py) to access paths through the new config structure.
- Fixed bugs related to image processing and model saving.
- Enhanced test infrastructure to accommodate the new configuration approach.
This refactor improves code maintainability and clarity by centralizing configuration management.
2026-03-27 18:18:30 +02:00
538dc8efa9
train is ready
...
manual_run reuses train's export
add current_model to constants
2025-05-31 18:41:10 +03:00
eecc11b1e5
queue handler done
2025-05-22 02:15:21 +03:00
26eb3b991d
add download big engine file to cdn manager
...
revise onnx export process
fixes
2025-04-24 16:23:39 +03:00
06a23525a6
fix tensor rt engine
2025-04-06 18:45:06 +03:00
b4a4826b19
add rabbit consumer
2025-03-05 20:58:33 +02:00
2fa864018f
upload model to cdn and api
...
switch to yolov11
2025-03-03 23:36:10 +02:00
ceb50bf48a
add rknn conversion - install and use scripts, auto convert to rknn after AI training is done and put pt and rknn models to /azaion/models directory
2025-02-21 14:26:54 +02:00
6b0a0e678e
copy images and labels during forming dataset. add folder for corrupted labels, small refactor
2024-08-13 01:57:42 +03:00
bb1dbfe1e7
fix folder names, refactoring
...
move to yolov8m
use checkpoint.txt instead of yaml
2024-06-29 22:18:34 +03:00
66987f4d95
add checkpoints and config system
...
convert from bbox oriented and pascal xml
fixes
2024-06-18 21:32:15 +03:00
2325fd0916
update gitignore
...
simplify paths
remove runs folder
2024-06-10 09:07:13 +03:00
07ea67746a
add train.py
...
form dataset for current date
add exception catching
2024-06-05 23:35:06 +03:00
Oleksandr Bezdieniezhnykh