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
Mert
6356c28f64
refactor(ml): model sessions ( #10559 )
2024-06-25 12:00:24 -04:00
Mert
a42af06889
fix(ml): limit load retries ( #10494 )
2024-06-20 14:13:18 -04:00
Mert
2b1b43a7e4
feat(ml): composable ml ( #9973 )
...
* modularize model classes
* various fixes
* expose port
* change response
* round coordinates
* simplify preload
* update server
* simplify interface
simplify
* update tests
* composable endpoint
* cleanup
fixes
remove unnecessary interface
support text input, cleanup
* ew camelcase
* update server
server fixes
fix typing
* ml fixes
update locustfile
fixes
* cleaner response
* better repo response
* update tests
formatting and typing
rename
* undo compose change
* linting
fix type
actually fix typing
* stricter typing
fix detection-only response
no need for defaultdict
* update spec file
update api
linting
* update e2e
* unnecessary dimension
* remove commented code
* remove duplicate code
* remove unused imports
* add batch dim
2024-06-07 03:09:47 +00:00
CodaBool
6a4c2e97c0
feat: add docker healthchecks to server and ml ( #9583 )
...
* add healthcheck
* format, import, IMMICH_PORT, and eslint change
* chore: clean up nodejs healthcheck
* fix ruff formating
* add healthcheck
* format, import, IMMICH_PORT, and eslint change
* chore: clean up nodejs healthcheck
* fix ruff formating
* add healthcheck to dockerfile
* poetry run ruff check --fix
* removed 2 of 3 console calls
---------
Co-authored-by: Jason Rasmussen <jrasm91@gmail.com>
2024-05-22 16:54:29 +00:00
Jason Rasmussen
4807fc40a6
refactor!: LOG_LEVEL => IMMICH_LOG_LEVEL ( #9557 )
...
refactor: LOG_LEVEL => IMMICH_LOG_LEVEL
2024-05-17 11:44:22 -04:00
renovate[bot]
640f53fe0a
fix(deps): update dependency pillow to v10.3.0 [security] ( #8493 )
...
* fix(deps): update dependency pillow to v10.3.0 [security]
* fix typing
---------
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-04-11 05:48:09 +00:00
Davide
e8f0f82db0
feat(ml): add cache_dir option to OpenVINO EP ( #8018 )
...
* add cache_dir option to OpenVINO EP
* update provider options test to include cache_dir
* use forward slash instead of string concatenation
* fix cache_dir placement in provider options assertion
2024-03-17 13:48:59 -04:00
Mert
3a045b33ca
chore(deps): update onnxruntime-openvino ( #7854 )
2024-03-16 00:04:45 -04:00
DawidPietrykowski
e8b001f62f
feat: preloading of machine learning models ( #7540 )
2024-03-03 19:48:56 -05:00
Mert
7e18e69c1c
fix(ml): only use openvino if a gpu is available ( #7450 )
...
use `device_type`
2024-02-27 00:45:14 -05:00
Sourav Agrawal
2a75f884d9
Fix Smart Search when using OpenVINO ( #7389 )
...
* Fix external_path loading in OpenVINO EP
* Fix ruff lint
* Wrap block in try finally
* remove static input shape code
* add unit test
* remove unused imports
* remove repeat line
* linting
* formatting
---------
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-02-24 18:22:27 -05:00
renovate[bot]
2b8ec30767
chore(deps): update machine-learning (major) ( #6934 )
...
* chore(deps): update machine-learning
* formatting
---------
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
2024-02-12 22:29:15 -05:00
Fynn Petersen-Frey
49c378d706
fix(ml): re-enable ARMNN integration ( #7053 )
2024-02-12 13:29:55 -05:00
Mert
0c4df216d7
feat(ml): improve test coverage ( #7041 )
...
* update e2e
* tokenizer tests
* more tests, remove unnecessary code
* fix e2e setting
* add tests for loading model
* update workflow
* fixed test
2024-02-11 17:58:56 -05:00
Mert
c9b7f4e690
chore(ml): make execution provider log info-level ( #7024 )
...
* change debug log to info
* update test
2024-02-11 06:12:11 +00:00
