mirror of
https://github.com/blakeblackshear/frigate.git
synced 2026-05-05 04:57:42 +03:00
Mention support for multiple rknn detectors
This commit is contained in:
parent
4c749e3004
commit
175190006d
@ -813,6 +813,22 @@ Hardware accelerated object detection is supported on the following SoCs:
|
|||||||
|
|
||||||
This implementation uses the [Rockchip's RKNN-Toolkit2](https://github.com/airockchip/rknn-toolkit2/), version v2.3.2.
|
This implementation uses the [Rockchip's RKNN-Toolkit2](https://github.com/airockchip/rknn-toolkit2/), version v2.3.2.
|
||||||
|
|
||||||
|
:::tip
|
||||||
|
|
||||||
|
When using many cameras one detector may not be enough to keep up. Multiple detectors can be defined assuming NPU resources are available. An example configuration would be:
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
detectors:
|
||||||
|
rknn_0:
|
||||||
|
type: rknn
|
||||||
|
num_cores: 0
|
||||||
|
rknn_1:
|
||||||
|
type: rknn
|
||||||
|
num_cores: 0
|
||||||
|
```
|
||||||
|
|
||||||
|
:::
|
||||||
|
|
||||||
### Prerequisites
|
### Prerequisites
|
||||||
|
|
||||||
Make sure to follow the [Rockchip specific installation instructions](/frigate/installation#rockchip-platform).
|
Make sure to follow the [Rockchip specific installation instructions](/frigate/installation#rockchip-platform).
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user