administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-02-04 18:25:22 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Elaborate configuration and limitations in docs.

Browse Source
This commit is contained in:
Anil Ozyalcin 2023-01-28 22:28:50 -08:00
parent dd3cebd21a
commit 7884042709
1 changed files with 19 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
docs/docs/configuration/detectors.md
View File

@ -101,7 +101,7 @@ The OpenVINO device to be used is specified using the `"device"` attribute accor
OpenVINO is supported on 6th Gen Intel platforms (Skylake) and newer. A supported Intel platform is required to use the `GPU` device with OpenVINO. The `MYRIAD` device may be run on any platform, including Arm devices. For detailed system requirements, see [OpenVINO System Requirements](https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html) OpenVINO is supported on 6th Gen Intel platforms (Skylake) and newer. A supported Intel platform is required to use the `GPU` device with OpenVINO. The `MYRIAD` device may be run on any platform, including Arm devices. For detailed system requirements, see [OpenVINO System Requirements](https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/system-requirements.html)
An OpenVINO model is provided in the container at `/openvino-model/ssdlite_mobilenet_v2.xml` and is used by this detector type by default. The model comes from Intel's Open Model Zoo [SSDLite MobileNet V2](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/ssdlite_mobilenet_v2) and is converted to an FP16 precision IR model. Use the model configuration shown below when using the OpenVINO detector. An OpenVINO model is provided in the container at `/openvino-model/ssdlite_mobilenet_v2.xml` and is used by this detector type by default. The model comes from Intel's Open Model Zoo [SSDLite MobileNet V2](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/ssdlite_mobilenet_v2) and is converted to an FP16 precision IR model. Use the model configuration shown below when using the OpenVINO detector with the default model.
```yaml ```yaml
detectors: detectors:
@ -120,7 +120,24 @@ model:
labelmap_path: /openvino-model/coco_91cl_bkgr.txt labelmap_path: /openvino-model/coco_91cl_bkgr.txt
``` ```
This detector also supports YOLOx models, and has been verified to work with the [yolox_tiny](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/yolox-tiny) model from Intel's Open Model Zoo. If using `yolox_tiny`, or any other YOLOx variant, make sure to set `input_tensor: nchw` and `model_type: yolox`, along with the appropriate width/height settings (416 for `yolox_tiny`). There is currently no support for other types of YOLO models. This detector also supports YOLOx models, and has been verified to work with the [yolox_tiny](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/yolox-tiny) model from Intel's Open Model Zoo. Frigate does not come with `yolox_tiny` model, you will need to follow [OpenVINO documentation](https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/yolox-tiny) to provide your own model to Frigate. There is currently no support for other types of YOLO models (YOLOv3, YOLOv4, etc...). Below is an example of how `yolox_tiny` and other yolox variants can be used in Frigate:
```yaml
detectors:
ov:
type: openvino
device: AUTO
model:
path: /<path>/<to>/yolox_tiny.xml
model:
width: 416
height: 416
input_tensor: nchw
input_pixel_format: bgr
model_type: yolox
labelmap_path: /<path>/<to>/coco_80cl.txt
```
### Intel NCS2 VPU and Myriad X Setup ### Intel NCS2 VPU and Myriad X Setup