da2636d6f7
* face recognition usage instructions * clarify lpr docs for motorcycles * person must be detected before face * add note about coral * add note about local * update reference config for face model size * clarify reference config for face
1.5 KiB
| id | title |
|---|---|
| hardware_acceleration_enrichments | Enrichments |
Enrichments
Some of Frigate's enrichments can use a discrete GPU for accelerated processing.
Requirements
Object detection and enrichments (like Semantic Search, Face Recognition, and License Plate Recognition) are independent features. To use a GPU for object detection, see the Object Detectors documentation. If you want to use your GPU for any supported enrichments, you must choose the appropriate Frigate Docker image for your GPU and configure the enrichment according to its specific documentation.
-
AMD
- ROCm will automatically be detected and used for enrichments in the
-rocmFrigate image.
- ROCm will automatically be detected and used for enrichments in the
-
Intel
- OpenVINO will automatically be detected and used for enrichments in the default Frigate image.
-
Nvidia
- Nvidia GPUs will automatically be detected and used for enrichments in the
-tensorrtFrigate image. - Jetson devices will automatically be detected and used for enrichments in the
-tensorrt-jp6Frigate image.
- Nvidia GPUs will automatically be detected and used for enrichments in the
Utilizing a GPU for enrichments does not require you to use the same GPU for object detection. For example, you can run the tensorrt Docker image for enrichments and still use other dedicated hardware for object detection.
:::note
A Google Coral is a TPU (Tensor Processing Unit), not a dedicated GPU (Graphics Processing Unit) and therefore does not provide any kind of acceleration for Frigate's enrichments.
:::