Commit Graph

84 Commits

Author SHA1 Message Date
Nicolas Mowen
c5ed95ec52
More inference speed updates (#19947)
* More inference speed updates

* Update hardware.md

* Update hardware.md

* Update index.md

* More inference speeds

* Update home-assistant.md

* Update object_detectors.md

* Update first_model.md
2025-09-08 07:43:04 -05:00
Nicolas Mowen
4347402fcc
Don't mention 9.0.0 GFX version (#19742) 2025-08-25 07:32:50 -05:00
Nicolas Mowen
c3410cd13e
Revamp RF-DETR Export Docs (#19341)
* Revamp RFDETR docs

* Clarify model size

* Specify model size
2025-07-31 09:11:46 -05:00
Jack
23b32cbacf
Update object_detectors.md (#19328)
Minor documentation clarity
2025-07-30 07:08:44 -06:00
Felipe Santos
6d5fb65a68
Revamp YOLOv9 export guide (#19224)
* Revamp YOLOv9 export guide

* Make variant a build arg

* Change VARIANT to MODEL_SIZE

* Mention available models
2025-07-20 09:19:23 -06:00
Marc Altmann
60923ac1e3
RKNN: Fix broken models for Toolkit v2.3.2 (#19189)
* update models

* don't set input_dtype: float for yolov9 (rknn)
2025-07-18 06:26:41 -06:00
Nicolas Mowen
d69916694b
Remove TensorRT Detector from AMD64 Build (#19030)
* Don't support tensorrt detector for amd64 builds

* Add logs for directing users not to use tensorrt detector

* Rework docs

* Fix dockerfile index

* Don't undo jetson fix
2025-07-07 18:12:52 -05:00
Blake Blackshear
7238b3ea22 Merge remote-tracking branch 'origin/master' into dev 2025-06-27 06:53:02 -05:00
Nicolas Mowen
cbdac9ece5
Fixes (#18379)
* Don't return weighted name if it has the same number of results

* Remove link to incorrect format yolov9 models

* Fix command list from appearing when other inputs are focused

the description box in the tracked object details pane was causing the command input list to show when focused.

* clarify face docs

* Add note about python yolov9 export

* Check if hailort thread is still alive when timeout error is run into

* Reduce inference timeout

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
2025-05-27 10:25:34 -05:00
Thomas A.
63f9689b0e
Improve documentation for YOLO-NAS notebook (#18381)
* Add readme file for notebooks
It took me quite some time to find out this workbook opens in Google Colab, so i though it may help someone else to have this visible in the folder aswell.

* Add explicit link to Google Colab for YOLO-NAS
2025-05-24 09:42:32 -06:00
Nicolas Mowen
3a69273f0c
revert onnx runtime update (#18074)
* revert onnx runtime update

* Fix docs
2025-05-06 09:02:34 -05:00
Nicolas Mowen
895afcdb0e
Various Fixes (#18035)
* Support multi and single core rknn npus

* Update docs config to be more clear
2025-05-04 09:33:27 -06:00
Josh Hawkins
08c087f221
Docs updates (#17986)
* docs updates

* revamp hwaccel

* remove

* clarify

* fix

* more clarity

* clean up
2025-05-01 08:17:35 -05:00
Nicolas Mowen
aa7899e9dc
Docs / typing updates (#17878)
* Mention support for multiple rknn detectors

* Improve typing

* Fix mypy change

* Fix typing
2025-04-23 17:06:06 -06:00
Marc Altmann
4c749e3004
update rknn toolkit version (#17877) 2025-04-23 14:30:44 -06:00
Nicolas Mowen
212784b68e
implement RKNN downloads for yolov9 and yolox models (#17875)
* Add other rockchip download models

* Specify newer release version

* Specify newer release version

* Update docs for rknn downloads

* Update hardware docs
2025-04-23 12:22:23 -05:00
Nicolas Mowen
89b54f19c8
Add YOLOv9 support to RKNN (#17791)
* Add yolov9

* Undo

* Update docs for rknn yolov9

* Update docs notes

* Add infernece times table
2025-04-18 16:51:04 -06:00
Nicolas Mowen
e8883a2a2e
Fix yolox docs (#17789) 2025-04-18 16:15:55 -05:00
Nicolas Mowen
1cdc9b6097
Implement YOLOx for RKNN (#17788)
* Implement yolox rknn inference and post processing

* rework docs
2025-04-18 14:44:02 -06:00
Nicolas Mowen
19aaa64fe9
Add support for yolox models to onnx detector (#17773) 2025-04-18 06:40:06 -05:00
Nicolas Mowen
8270967cdc
UI Fixes (#17762)
* Fix handling of non existing cameras in groups

* Update docs

* Improve typing
2025-04-17 13:48:09 -06:00
Nicolas Mowen
8744da3bf8
Fix yolov9 export script (#17744)
* Fix yolov9 export script

* Fix typo

* Update object_detectors.md
2025-04-16 14:52:21 -06:00
Nicolas Mowen
bd0ee86db9
Refactor yolov9 detector to support v3, v4, v7 as well (#17697)
* Implement blobbed yolov7 post processing and consolidate yolo implementation

* Update documentation

* Add repo

* fix name
2025-04-14 16:05:41 -05:00
Nicolas Mowen
e9787c5a88
Small Tweaks (#17652)
* Ensure that hailo uses correct labelmap

* Make whole button clickable

* Add weblate to readme

* Update docs for HEIC

* Fix explore chip icon logic

* Sort regardless of case

* Don't allow selection

* Fix image uploading
2025-04-11 08:21:01 -06:00
Nicolas Mowen
7cfa818e63
Update tensorrt model config to use coco-80 (#17640) 2025-04-10 17:28:57 -05:00
Nicolas Mowen
30ac868757
Quick fixes (#17639)
* Use mobile drawer for face selection

* Convert face selection to separate component

* Cleanup dialogs

* Add FAQ for record resolution

* Update image name

* Remove unused

* Cleanup
2025-04-10 16:33:51 -05:00
Felipe Santos
f8b0329b37
Move database and config from homeassistant /config to addon /config (#16337)
* Move database and config from homeassistant /config to addon /config

* Re-implement config migration for the add-on

* Align some terms

* Improve function name

* Use local variables

* Add model.path migration

* Fix homeassistant config path

* Ensure migration scripts run before go2rtc and frigate

* Migrate all files I know

* Add ffmpeg.path migration

* Update docker/main/rootfs/etc/s6-overlay/s6-rc.d/prepare/run

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>

* Improve some variable names and organization

* Update docs to reflect addon config dir

* Update live.md with /addon_configs

* Move addon config section to configuration doc

* Align several terminologies and improve text

* Fix webrtc example config title

* Capitalize Add-on in more places

* Improve specific add-on config dir docs

* Align bash and python scripts to prefer config.yml over config.yaml

* Support config.json in migration shell scripts

* Change docs to reflect config.yml is preferred over config.yaml

* If previous config was yaml, migrate to yaml

* Fix typo in edgetpu.md

* Fix formatting of Python files

* Remove HailoRT Beta add-on variant from docs

* Add migration for labelmap and certs

* Fix variable name

* Fix new_config_file var unset

* Fix addon config directories table

* Improve db migration to avoid migrating files like .db.bak

* Fix echo location

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
2025-03-24 09:05:59 -05:00
Nicolas Mowen
18af06237c
Support RF-DETR models with OpenVINO (#17321)
* Add support for openvino to run rf-detr models

* Add more inference time examples

* organize

* Add example to docs

* Add support for yolo generic
2025-03-23 14:02:16 -06:00
Nicolas Mowen
17e14cefd9
Various fixes & tweaks (#17308)
* Catch case where returned face box is invalid

* Update detector docs

* Add note for customizing rfdetr resolution
2025-03-22 13:58:27 -05:00
Nicolas Mowen
48e4c44b32
Add support for RF-DETR models (#17298)
* Add support for rf-detr models

* Add docs for rf-detr model

* Cleanup
2025-03-21 19:55:46 -05:00
Jason Hunter
e340c9aaba
Add openvino support for the DFINE model (#17238)
* add openvino support for the dfine model

* update docs to show DFINE support for openvino

* remove warning about OpenVINO for DFINE
2025-03-19 07:23:24 -05:00
OmriAx
7411a8bafa
Hailo Official integration (#16906)
* Adding Models

* Final Async Update

* Bug Fixing

* Fix

* Adding fixes

* Working async infer

* Final Documenatation and debug update

* Removing some extra prints

* Post-process correct label push

* config docs fix

* Review Fix

* Review fix 2.0

* Fixing the ASYNC API to work from 30ms to 10ms

* Fix for multi stream async infernce

* Format

* Fix #3

* Format#2

* Remove Unnessery includes

* Sort Imports
2025-03-11 13:36:07 -06:00
Nicolas Mowen
6f9d9cd5a8
Fix yolov9 link (#17007) 2025-03-07 08:50:04 -06:00
Nicolas Mowen
71e6e04d77
Remove rocm detector (#16913)
* Remove rocm detector plugin

* Update docs to recommend using onnx for rocm

* Formatting
2025-03-03 08:16:14 -06:00
Nicolas Mowen
b8f4cb5435
Fix docs (#16889) 2025-03-02 09:30:18 -07:00
Nicolas Mowen
f56668e467
Update d-fine documentation (#16881) 2025-03-01 17:09:41 -06:00
Jason Hunter
0de928703f
Initial implementation of D-FINE model via ONNX (#16772)
* initial implementation of D-FINE model

* revert docker-compose

* add docs for D-FINE

* remove weird auto-format issue
2025-02-24 08:56:01 -07:00
Nicolas Mowen
761c5109dc
Update nvidia driver req (#16560) 2025-02-13 17:18:38 -06:00
Nicolas Mowen
0f0b2687af
Add support for YoloV9 to OpenVINO (#16495)
* Add support for yolov9 to OpenVINO

* Cleanup detector docs

* Fix link
2025-02-11 11:23:19 -07:00
Nicolas Mowen
198d067e25
Implement support for YOLOv9 via ONNX (#16459)
* WIP yolov9

* Implement post processing for yolov9

* Cleanup detection

* Update docs to make note of supported yolov9

* Move post processing to separate utility

* Add note about other models
2025-02-10 15:00:12 -06:00
Marc Altmann
4c7d4e6c0a rockchip: update dependencies and add script for model conversion (#15699)
* rockchip: update dependencies and add script for model conversion

* rockchip: update docs

---------

Co-authored-by: Nicolas Mowen <nickmowen213@gmail.com>
2025-02-08 12:47:01 -06:00
Nicolas Mowen
0645dc70a5
Detector docs (#16292)
* Refactor hardware docs to show model specific speeds

* Move hailo to first party detectors

* Make note of multiple detectors

* Improve hierarchy

* Update object_detectors.md

* Update hardware.md
2025-02-03 07:57:21 -06:00
Nicolas Mowen
d57a61b50f
Simplify model config (#15881)
* Add migration to migrate to model_path

* Simplify model config

* Cleanup docs

* Set config version

* Formatting

* Fix tests
2025-01-07 20:59:37 -07:00
Nicolas Mowen
e7ad38d827
Update model docs (#15779) 2025-01-02 10:04:16 -06:00
Nicolas Mowen
f9c1600f0d
Duplicate onnx build info (#15020) 2024-11-16 13:24:42 -06:00
Nicolas Mowen
46ed520886
Don't generate tensorrt models by default (#14865) 2024-11-08 07:37:18 -06:00
Nicolas Mowen
553676aade
Fix missing tensor_input (#14790) 2024-11-04 13:04:33 -06:00
Nicolas Mowen
c7a4220d65
Jetson onnxruntime (#14688)
* Add support for using onnx runtime with jetson

* Update docs

* Clarify
2024-10-30 08:22:28 -06:00
Blake Blackshear
47ad0ca993 Merge remote-tracking branch 'origin/master' into dev 2024-10-05 10:48:14 -05:00
Nicolas Mowen
da1478c0c1
Update object_detectors.md (#13994)
* Update object_detectors.md

* Use info

* Move CPU detector to bottom

* Moce CPU to bottom

* Add missing detector keys
2024-09-26 18:58:58 -05:00