a1ee077e0a
split to 2 files: tensorrt_engine and onnx engine
2025-04-30 19:33:59 +03:00
5ff4ee58b9
fix publish script
2025-04-24 22:07:34 +03:00
e9a44e368d
autoconvert tensor rt engine from onnx to specific CUDA gpu
2025-04-24 16:30:21 +03:00
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
277aaf09b0
throttle reimplemented
2025-04-17 09:16:34 +03:00
0c66607ed7
failsafe load dlls
...
add user config queue offsets
throttle improvements
2025-04-17 01:19:48 +03:00
ca1682a86e
add gps matcher service
2025-04-14 09:50:34 +03:00
b21f8e320f
fix bug with annotation result gradient stops
...
add tensorrt engine
2025-04-02 00:29:21 +03:00
e0c88bd8fb
fix close external clients
2025-03-24 11:48:26 +02:00
6429ad62c2
refactor external clients
...
put model batch size as parameter in config
2025-03-24 00:33:41 +02:00
a493606f64
correct app close
...
fix publishing
2025-03-03 19:37:07 +02:00
d93da15528
fix switcher between modes in DatasetExplorer.xaml
2025-03-02 21:32:31 +02:00
58839933fc
fix id problems with day/winter switch
2025-02-26 22:09:07 +02:00
d1af7958f8
fix initialization, throttle operations
...
day/winter/night switcher fixes
2025-02-19 23:07:16 +02:00
2ecbc9bfd4
move zmq port to config file for C# and python
2025-02-16 16:35:52 +02:00
0d6ea4264f
add publish script, check its work
2025-02-14 23:08:50 +02:00
961d2499de
fix inference
...
fix small issues
2025-02-14 09:00:04 +02:00
cfd5483a18
make python app load a bit eariler, making startup a bit faster
2025-02-13 18:13:15 +02:00
e329e5bb67
make start faster
2025-02-12 13:49:01 +02:00
43cae0d03c
make cython app exit correctly
2025-02-11 20:40:49 +02:00
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
ba3e3b4a55
move python inference to Azaion.Inference folder
2025-02-06 10:48:03 +02:00
739759628a
fixed inference bugs
...
add DONE during inference, correct handling on C# side
2025-02-01 02:09:11 +02:00
62623b7123
add ramdisk, load AI model to ramdisk and start recognition from it
...
rewrite zmq to DEALER and ROUTER
add GET_USER command to get CurrentUser from Python
all auth is on the python side
inference run and validate annotations on python
2025-01-29 17:45:26 +02:00
82b3b526a7
rewrite to zmq push and pull patterns.
...
file load works, suite can start up
2025-01-23 14:37:13 +02:00
ce25ef38b0
fix auth, decryption, api interaction
2025-01-20 10:17:35 +02:00
1bc1d81fde
small fixes, renames
2025-01-15 16:41:42 +02:00
8b94837f18
add offset
...
fixes
add visual validation border and validate functionality
2024-12-28 15:51:27 +02:00
81dcb2a92e
add resource folder to config for proper folder auto upload
2024-12-24 12:55:36 +02:00
5fa18aa514
queue + local sqlite WIP
2024-12-17 18:46:33 +02:00
Alex Bezdieniezhnykh