administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-03-25 09:38:22 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

docs: remove OpenVINO D-FINE configuration device

Browse Source
This commit is contained in:
GuoQing Liu 2025-12-11 16:28:50 +08:00 committed by GitHub
parent 1de7519d1a
commit a2061f0d96
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docs/docs/configuration/object_detectors.md
View File

@ -395,7 +395,6 @@ After placing the downloaded onnx model in your config/model_cache folder, you c
detectors:
ov:
type: openvino
device: GPU
model:
model_type: dfine
@ -431,10 +430,10 @@ When using Docker Compose:
```yaml
services:
frigate:
---
devices:
- /dev/dri
- /dev/kfd
...
devices:
- /dev/dri
- /dev/kfd
```
For reference on recommended settings see [running ROCm/pytorch in Docker](https://rocm.docs.amd.com/projects/install-on-linux/en/develop/how-to/3rd-party/pytorch-install.html#using-docker-with-pytorch-pre-installed).
@ -462,9 +461,9 @@ When using Docker Compose:
```yaml
services:
frigate:
environment:
HSA_OVERRIDE_GFX_VERSION: "10.0.0"
...
environment:
HSA_OVERRIDE_GFX_VERSION: "10.0.0"
```
Figuring out what version you need can be complicated as you can't tell the chipset name and driver from the AMD brand name.