Nicolas MowenandGitHub 2236ecf23f Auto convert ONNX models to RKNN format (#19674) ...

* Implement base rknn conversion

* Remove unused

* Formatting

* Add model conversion lock so it doesn't break when multiple detectors are defined

* Ignore unused impor
t

2025-08-20 15:15:57 -06:00

..

__init__.py

Fix go2rtc init (#18708)

2025-08-16 10:20:33 -05:00

audio.py

Audio transcription support (#18398)

2025-08-16 10:20:33 -05:00

builtin.py

Semantic Search Triggers (#18969)

2025-08-16 10:20:33 -05:00

classification.py

Improve the tablet layout (#19320)

2025-08-16 10:20:33 -05:00

config.py

Fix record motion config (#19672)

2025-08-20 14:45:17 -06:00

downloader.py

Fix facedet download (#15811)

2025-02-08 12:47:01 -06:00

image.py

Fix various typing issues (#18187)

2025-05-13 08:27:20 -06:00

model.py

Update deps (#19617)

2025-08-19 11:08:34 -05:00

object.py

Fix various typing issues (#18187)

2025-05-13 08:27:20 -06:00

path.py

Improve Face Library Management (#17213)

2025-03-17 16:57:46 -05:00

process.py

Require setting process priority for FrigateProcess (#19207)

2025-08-16 10:20:33 -05:00

rknn_converter.py

Auto convert ONNX models to RKNN format (#19674)

2025-08-20 15:15:57 -06:00

services.py

Replaces sriov flag with explicit path to the Intel GPU device (#19136)

2025-07-14 07:11:25 -05:00

velocity.py

Fixes (#18935)

2025-07-07 06:35:55 -06:00