mirror of
https://github.com/blakeblackshear/frigate.git
synced 2026-02-15 07:35:27 +03:00
Update object_detectors.md
This commit is contained in:
parent
40fe3b4358
commit
786bb96b31
@ -5,6 +5,8 @@ title: Object Detectors
|
||||
|
||||
# Supported Hardware
|
||||
|
||||
:::tip
|
||||
|
||||
Frigate supports multiple different detectors that work on different types of hardware:
|
||||
|
||||
**Most Hardware**
|
||||
@ -26,6 +28,8 @@ Frigate supports multiple different detectors that work on different types of ha
|
||||
**Rockchip**
|
||||
- [RKNN](#rockchip-platform): RKNN models can run on Rockchip devices with included NPUs.
|
||||
|
||||
:::
|
||||
|
||||
# Officially Supported Detectors
|
||||
|
||||
Frigate provides the following builtin detector types: `cpu`, `edgetpu`, `openvino`, `tensorrt`, `rknn`, and `hailo8l`. By default, Frigate will use a single CPU detector. Other detectors may require additional configuration as described below. When using multiple detectors they will run in dedicated processes, but pull from a common queue of detection requests from across all cameras.
|
||||
@ -418,7 +422,7 @@ After placing the downloaded onnx model in your config folder, you can use the f
|
||||
|
||||
```yaml
|
||||
detectors:
|
||||
onnx:
|
||||
rocm:
|
||||
type: rocm
|
||||
|
||||
model:
|
||||
|
||||
Loading…
Reference in New Issue
Block a user