administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-04-26 16:47:41 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Add tip to docs

Browse Source
This commit is contained in:
Nicolas Mowen 2025-09-27 09:12:40 -06:00
parent a5488f6a90
commit 74defd2526
2 changed files with 32 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
docs/docs/configuration/object_detectors.md
View File

@ -555,6 +555,17 @@ $ docker exec -it frigate /bin/bash -c '(unset HSA_OVERRIDE_GFX_VERSION && /opt/
### ROCm Supported Models ### ROCm Supported Models
:::tip
The AMD GPU kernel is known problematic especially when converting models to mxr format. The recommended approach is:
1. Disable object detection in the config.
2. Startup Frigate with the onnx detector configured, the main object detection model will be converted to mxr format and cached in the config directory.
3. Once this is finished as indicated by the logs, enable object detection in the UI and confirm that it is working correctly.
4. Re-enable object detection in the config.
:::
See [ONNX supported models](#supported-models) for supported models, there are some caveats: See [ONNX supported models](#supported-models) for supported models, there are some caveats:
- D-FINE models are not supported - D-FINE models are not supported

8
frigate/detectors/detection_runners.py
View File

@ -456,10 +456,10 @@ def get_optimized_runner(
options[0]["device_id"], options[0]["device_id"],
) )
if providers[ if (
0 providers
] == "MIGraphXExecutionProvider" and ONNXModelRunner.is_migraphx_complex_model( and providers[0] == "MIGraphXExecutionProvider"
model_type and ONNXModelRunner.is_migraphx_complex_model(model_type)
): ):
# Don't use MIGraphX for models that are not supported # Don't use MIGraphX for models that are not supported
providers.pop(0) providers.pop(0)