administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-10-15 11:12:49 +03:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Add automatic RKNN conversion and support for semantic search model (#19676)

Browse Source 
* Create RKNN model runner and and use for jina v1 clip

* Formatting

* Handle model type inference

* Properly provide input to RKNN

* Adjust rknn conversion

* Update docs

* Formatting

* Fix path handling

* Handle inputs

* Cleanup

* Change normalization for better accuracy

* Clarify supported models

* Remove testing
This commit is contained in:
Nicolas Mowen
2025-08-21 05:30:14 -06:00
committed by GitHub
parent efeb089ff8
commit 1be84d6833
4 changed files with 233 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/docs/configuration/semantic_search.md
+2 -2
View File
@@ -78,7 +78,7 @@ Switching between V1 and V2 requires reindexing your embeddings. The embeddings
### GPU Acceleration
The CLIP models are downloaded in ONNX format, and the `large` model can be accelerated using GPU hardware, when available. This depends on the Docker build that is used. You can also target a specific device in a multi-GPU installation.
The CLIP models are downloaded in ONNX format, and the `large` model can be accelerated using GPU / NPU hardware, when available. This depends on the Docker build that is used. You can also target a specific device in a multi-GPU installation.
```yaml
semantic_search:
@@ -90,7 +90,7 @@ semantic_search:
:::info
If the correct build is used for your GPU and the `large` model is configured, then the GPU will be detected and used automatically.
If the correct build is used for your GPU / NPU and the `large` model is configured, then the GPU / NPU will be detected and used automatically.
Specify the `device` option to target a specific GPU in a multi-GPU system (see [onnxruntime's provider options](https://onnxruntime.ai/docs/execution-providers/)).
If you do not specify a device, the first available GPU will be used.