chris/frigate
1
0
Fork 0
forked from Github/frigate
Code Pull Requests Packages Activity

Don't generate tensorrt models by default (#14865)

Browse Source
This commit is contained in:
Nicolas Mowen
2024-11-08 06:37:18 -07:00
committed by GitHub
parent ace02a6dfa
commit 46ed520886
4 changed files with 9 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/docs/configuration/object_detectors.md
View File

@@ -223,7 +223,7 @@ The model used for TensorRT must be preprocessed on the same hardware platform t
The Frigate image will generate model files during startup if the specified model is not found. Processed models are stored in the `/config/model_cache` folder. Typically the `/config` path is mapped to a directory on the host already and the `model_cache` does not need to be mapped separately unless the user wants to store it in a different location on the host.
By default, the `yolov7-320` model will be generated, but this can be overridden by specifying the `YOLO_MODELS` environment variable in Docker. One or more models may be listed in a comma-separated format, and each one will be generated. To select no model generation, set the variable to an empty string, `YOLO_MODELS=""`. Models will only be generated if the corresponding `{model}.trt` file is not present in the `model_cache` folder, so you can force a model to be regenerated by deleting it from your Frigate data folder.
By default, no models will be generated, but this can be overridden by specifying the `YOLO_MODELS` environment variable in Docker. One or more models may be listed in a comma-separated format, and each one will be generated. Models will only be generated if the corresponding `{model}.trt` file is not present in the `model_cache` folder, so you can force a model to be regenerated by deleting it from your Frigate data folder.
If you have a Jetson device with DLAs (Xavier or Orin), you can generate a model that will run on the DLA by appending `-dla` to your model name, e.g. specify `YOLO_MODELS=yolov7-320-dla`. The model will run on DLA0 (Frigate does not currently support DLA1). DLA-incompatible layers will fall back to running on the GPU.
@@ -264,7 +264,7 @@ An example `docker-compose.yml` fragment that converts the `yolov4-608` and `yol
```yml
frigate:
environment:
- YOLO_MODELS=yolov4-608,yolov7x-640
- YOLO_MODELS=yolov7-320,yolov7x-640
- USE_FP16=false
```