Commit Graph

19 Commits

Author SHA1 Message Date
Oleksandr Bezdieniezhnykh 9a16099194 fix split tile size
rework inference events and handling
todo: add Medias table and reflect recognition status there
2025-09-05 16:50:09 +03:00
Oleksandr Bezdieniezhnykh 7d68f7faee fix race condition issue
put AIAvailabilityEnum.ENABLED to the end of model conversion
2025-09-04 15:39:43 +03:00
Oleksandr Bezdieniezhnykh be77a81875 fix converting model initialization 2025-09-04 10:39:41 +03:00
Oleksandr Bezdieniezhnykh b6b6751c37 fix loader bug with _CACHED_HW_INFO
put tile size to name and set it dynamically for AI recognition
2025-09-02 13:59:23 +03:00
Oleksandr Bezdieniezhnykh 067f02cc63 update AI initializing
rework AIAvailabilityStatus events to mediatr
2025-09-01 20:12:13 +03:00
Oleksandr Bezdieniezhnykh 9e4dc5404c remove cpdef, add constants h 2025-08-12 14:53:14 +03:00
Oleksandr Bezdieniezhnykh ad782bcbaa splitting python complete 2025-08-12 14:48:56 +03:00
Oleksandr Bezdieniezhnykh fc6e5db795 add manual Tile Processor
zoom on video on pause (temp image)
2025-07-28 12:39:52 +03:00
Alex Bezdieniezhnykh c0f8dd792d fixed console Log
fix same files problem in python different libs
correct command logging in command handler
2025-06-14 21:01:32 +03:00
Alex Bezdieniezhnykh 7750025631 separate load functionality from inference client to loader client. Call loader client from inference to get the model.
remove dummy dlls, remove resource loader from c#.

TODO: Load dlls separately by Loader UI and loader client

WIP
2025-06-06 20:04:03 +03:00
dzaitsev d92da6afa4 Errors sending to UI
notifying client of AI model conversion
2025-05-14 12:43:50 +03:00
Alex Bezdieniezhnykh e9a44e368d autoconvert tensor rt engine from onnx to specific CUDA gpu 2025-04-24 16:30:21 +03:00
Alex Bezdieniezhnykh e798af470b read cdn yaml config from api
automate tensorrt model conversion in case of no existing one for user's gpu
2025-04-23 23:20:08 +03:00
Alex Bezdieniezhnykh b21f8e320f fix bug with annotation result gradient stops
add tensorrt engine
2025-04-02 00:29:21 +03:00
Alex Bezdieniezhnykh d93da15528 fix switcher between modes in DatasetExplorer.xaml 2025-03-02 21:32:31 +02:00
Alex Bezdieniezhnykh e329e5bb67 make start faster 2025-02-12 13:49:01 +02:00
Alex Bezdieniezhnykh 9973a16ada print detection results 2025-02-10 18:02:44 +02:00
Alex Bezdieniezhnykh c1b5b5fee2 use nms in the model itself, simplify and make postprocess faster.
make inference in batches, fix c# handling, add overlap handling
2025-02-10 14:55:00 +02:00
Alex Bezdieniezhnykh ba3e3b4a55 move python inference to Azaion.Inference folder 2025-02-06 10:48:03 +02:00