105 Commits

Author SHA1 Message Date
yoni13
20ba9f97e9 update mapping 2025-01-19 13:15:38 +00:00
yoni13
ac4ce3ea9c add input outputs 2025-01-19 12:10:01 +00:00
yoni13
2b967ca358 raise NotImplementedError for now 2025-01-19 12:02:08 +08:00
yoni13
32f3707e52 fix types and ignored pattern 2025-01-18 17:17:48 +08:00
yoni13
b3ae5d34cc fix typo in tests 2025-01-18 16:54:18 +08:00
Yoni Yang
4e42fbc091
Merge branch 'main' into rknn-toolkit-lite2 2025-01-18 16:45:38 +08:00
yoni13
d7381ab5c1 refactor ignore_patterns 2025-01-18 04:48:11 +00:00
yoni13
f5de3de163 fix typo and add a propper var name 2025-01-18 10:46:57 +08:00
yoni13
3634ae1f5b fix granularity 2025-01-18 09:58:39 +08:00
Tempest
d5a9294eeb
feat: Add additional env variables to ML container (#15398)
* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Update config.py

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Apply formatting

* minor update

* formatting

* root validator

* minor update

* minor update

* minor update

* change to support explicit models

* minor update

* minor change

* minor change

* minor change

* minor update

* add logs, resolve errors

* minor change

* add new enviornment variables

* minor revisons

* remove comments

* add additional variables to ML (fixed)

* add additional variables to ML (fixed)

* add additional variables to ML

* formatting

* remove comment

* remove mypy error

* remove unused module

* merge f strings
2025-01-17 17:22:05 -05:00
yoni13
f067212491 tpe 2025-01-17 19:56:23 +08:00
yoni13
f32d991131 changes some cases 2025-01-17 19:25:01 +08:00
Tempest
c5476a99b1
feat: Add additional env variables for Machine Learning (#15326)
* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Update config.py

* Add additional variables to preload part ML models

* Add additional variables to preload part ML models

* Apply formatting

* minor update

* formatting

* root validator

* minor update

* minor update

* minor update

* change to support explicit models

* minor update

* minor change

* minor change

* minor change

* minor update

* add logs, resolve errors

* minor change

* add new enviornment variables

* minor revisons

* remove comments
2025-01-14 22:06:01 +00:00
yoni13
9882b83cd4 Should FIx the quote that made mypy unhappy 2025-01-15 00:35:43 +08:00
yoni13
b5a4ed5160 this duplicated? 2025-01-14 19:22:28 +08:00
yoni13
0f03f77e8e remove non implemented tests 2025-01-14 19:02:16 +08:00
yoni13
5244ed6d4d black app export 2025-01-14 18:40:28 +08:00
yoni13
8b80d034cb fixed some bugs 2025-01-14 10:38:45 +00:00
yoni13
4b0f93cf6a add test,founds bugs, fix it tomorrow 2025-01-14 01:08:44 +08:00
yoni13
6c4e6cb96f reformat 2025-01-13 18:37:25 +08:00
yoni13
b6cc2054c5 ignore rknn model if not using it 2025-01-13 18:37:01 +08:00
yoni13
2f7e44aa63 typing be happy. 2025-01-13 18:24:12 +08:00
yoni13
ebdfe1b7b6 Load model by SOC name 2025-01-13 17:08:16 +08:00
yoni13
4c7ac1438b only load knnx model when required 2025-01-12 19:11:16 +00:00
yoni13
e6ff21b345 set default thread num to 2, not everyone has 8 gigs of ram 2025-01-12 16:05:18 +08:00
yoni13
19ee48f6f0 fix path 2025-01-12 01:09:36 +08:00
yoni13
efaf70eb9d Set running threads from env 2025-01-12 01:02:16 +08:00
yoni13
23d0ea0e7b ruff 2025-01-11 16:28:26 +08:00
yoni13
d5e453a773 ruff format 2025-01-11 16:26:17 +08:00
yoni13
7aaf3aa57b Remove unused imports. 2025-01-11 16:03:33 +08:00
yoni13
c20d110257 support for rknn.rknnpool.is_available 2025-01-11 10:39:45 +08:00
yoni13
4d704e9f73 fix inf,-inf with 2 concurrency 2025-01-10 14:04:18 +00:00
Yoni Yang
9bc3e5b2e2
Update rknn.py 2025-01-10 20:20:21 +08:00
yoni13
a94fad543b all infrencing works with 1 max job concurrency 2025-01-09 10:38:40 +00:00
Yoni Yang
257cc6c963 Init commit for using rknn, RecognitionFormDataLoadTest doesnt work 2024-12-04 14:32:46 +00:00
Yoni Yang
bc849e2e9f ViT-B-32__openai/textual/ Runs with emulator now. 2024-12-01 16:42:53 +00:00
Yoni Yang
7fddf282cf lowercase 2024-11-30 14:24:38 +00:00
Yoni Yang
8ef3e49f74 untested 2024-11-29 07:42:09 +00:00
Mert
1ec9a60e41
feat(ml): configurable batch size for facial recognition (#13689)
* configurable batch size, default openvino to 1

* update docs

* don't add a new dependency for two lines

* fix typing
2024-10-23 07:50:28 -05:00
Mert
e7397f35c9
chore(ml): update pydantic (#13230)
* update pydantic

* fix typing

* remove unused import

* remove unused schema
2024-10-13 18:00:21 -04:00
Mert
bd826b0b9b
feat(ml): round-robin device assignment (#13237)
* round-robin device assignment

* docs and tests

clarify doc
2024-10-07 17:37:45 -04:00
Mert
a68e6be7e1
chore(ml): remove deprecated kwarg when downloading models (#12589)
remove local_dir_use_symlinks
2024-09-11 22:21:33 -05:00
Mert
22dc9bcebb
fix(ml): batch axis not being added for recognition model (#12588)
* fix has_batch_axis

* fix typing
2024-09-11 22:21:12 -05:00
Mert
036676d501
fix(ml): tokenization for webli models (#11881) 2024-08-18 11:05:10 -04:00
Alex
fb962f49ea
fix(ml): pydantic dep causes starting up issue (#11773)
* fix(ml): pydantic dep causes starting up issue

* revert import
2024-08-14 10:20:12 -05:00
Robert Schütz
9ed04588b8
chore(deps): update pydantic to v2 (#11701) 2024-08-11 12:23:11 -04:00
Mert
41580696c7
feat(ml): add more search models (#11468)
* update export code

* add uuid glob, sort model names

* add new models to ml, sort names

* add new models to server, sort by dims and name

* typo in name

* update export dependencies

* onnx save function

* format
2024-07-31 04:34:45 +00:00
renovate[bot]
b53bd8c525
fix(deps): update machine-learning (#10740)
* fix(deps): update machine-learning

* update openvino options, cuda

* update openvino build

* fix indentation

* update minimum nvidia driver

---------

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-07-21 19:30:24 -04:00
Fynn Petersen-Frey
54488b1016
feat(ml): improved ARM-NN support (#11233) 2024-07-20 15:59:27 -04:00
Mert
f43721ec92
fix(ml): armnn not being used (#10929)
* fix armnn not being used, move fallback handling to main, add tests

* formatting
2024-07-10 09:20:43 -05:00