administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-07-08 21:11:25 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

update object detectors models yaml

Browse Source 
- change order of fields in UI table to match the actual settings UI
- add defaults to the table so users aren't confused about what to set
This commit is contained in:
Josh Hawkins 2026-07-07 12:55:35 -05:00
parent c99d6b0dcf
commit fbdfaf13d5
1 changed files with 122 additions and 85 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

207
docs/data/object_detectors_models.yaml
View File

@ -20,11 +20,14 @@ edgeTPU:
| Field | Value |
| ---------------------------------------- | ----------------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Object detection model input width** | `320` (should match the imgsize of the model) |
| **Object detection model input height** | `320` (should match the imgsize of the model) |
| **Custom object detector model path** | `/config/model_cache/yolov9-s-relu6-best_320_int8_edgetpu.tflite` |
| **Label map for custom object detector** | `/config/labels-coco17.txt` |
| **Object detection model input width** | `320` (should match the imgsize of the model) |
| **Object detection model input height** | `320` (should match the imgsize of the model) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nhwc` (Frigate's default value) |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
coral:
@ -35,7 +38,7 @@ edgeTPU:
model_type: yolo-generic
width: 320 # <--- should match the imgsize of the model, typically 320
height: 320 # <--- should match the imgsize of the model, typically 320
path: /config/model_cache/yolov9-s-relu6-best_320_int8_edgetpu.tflite
path: /config/model_cache/yolov9-s-relu6-best_320_int8_edgetpu.tflite # use the filename you generated above
labelmap_path: /config/labels-coco17.txt
hailo8l:
title: Hailo-8/Hailo-8L
@ -49,13 +52,13 @@ hailo8l:
| Field | Value |
| ---------------------------------------- | ----------------------- |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input Tensor Shape** | `nhwc` |
| **Model Input Pixel Color Format** | `rgb` |
| **Model Input Tensor Shape** | `nhwc` |
| **Model Input D Type** | `int` |
| **Object Detection Model Type** | `yolo-generic` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
The detector automatically selects the default model based on your hardware. Optionally, specify a local model path or URL to override.
yaml: |-
@ -96,8 +99,9 @@ hailo8l:
| --------------------------------------- | ------ |
| **Object detection model input width** | `300` |
| **Object detection model input height** | `300` |
| **Model Input Tensor Shape** | `nhwc` |
| **Model Input Pixel Color Format** | `rgb` |
| **Model Input Tensor Shape** | `nhwc` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `ssd` |
Specify the local model path or URL for SSD MobileNet v1.
@ -153,13 +157,14 @@ openvino:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match the imgsize set during model export) |
| **Object detection model input height** | `320` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
ov:
@ -172,7 +177,7 @@ openvino:
height: 320 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float
path: /config/model_cache/yolo.onnx
path: /config/model_cache/yolo.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: ssd
label: SSDLite MobileNet v2
@ -183,12 +188,14 @@ openvino:
| Field | Value |
| ---------------------------------------- | ------------------------------------------ |
| **Object detection model input width** | `300` |
| **Object detection model input height** | `300` |
| **Model Input Tensor Shape** | `nhwc` |
| **Model Input Pixel Color Format** | `bgr` |
| **Custom object detector model path** | `/openvino-model/ssdlite_mobilenet_v2.xml` |
| **Label map for custom object detector** | `/openvino-model/coco_91cl_bkgr.txt` |
| **Object detection model input width** | `300` |
| **Object detection model input height** | `300` |
| **Model Input Pixel Color Format** | `bgr` |
| **Model Input Tensor Shape** | `nhwc` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `ssd` (Frigate's default value) |
yaml: |-
detectors:
ov:
@ -219,13 +226,14 @@ openvino:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match the imgsize set during model export) |
| **Object detection model input height** | `320` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
ov:
@ -238,7 +246,7 @@ openvino:
height: 320 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float
path: /config/model_cache/yolo.onnx
path: /config/model_cache/yolo.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: yolonas
label: YOLO-NAS
@ -258,13 +266,14 @@ openvino:
| Field | Value |
| ---------------------------------------- | ------------------------------------------------- |
| **Object Detection Model Type** | `yolonas` |
| **Object detection model input width** | `320` (should match whatever was set in notebook) |
| **Object detection model input height** | `320` (should match whatever was set in notebook) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input Pixel Color Format** | `bgr` |
| **Custom object detector model path** | `/config/yolo_nas_s.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match whatever was set in notebook) |
| **Object detection model input height** | `320` (should match whatever was set in notebook) |
| **Model Input Pixel Color Format** | `bgr` |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolonas` |
yaml: |-
detectors:
ov:
@ -288,8 +297,11 @@ openvino:
| Field | Value |
| ------------------------------------- | -------------------------------- |
| **Custom object detector model path** | `/config/yolox.onnx` (use the filename you generated above) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nhwc` (Frigate's default value) |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolox` |
| **Custom object detector model path** | path to your YOLOX ONNX model |
yaml: |-
detectors:
ov:
@ -298,7 +310,7 @@ openvino:
model:
model_type: yolox
path: /config/model_cache/yolox.onnx
path: /config/model_cache/yolox.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: rfdetr
label: RF-DETR
@ -325,12 +337,13 @@ openvino:
| Field | Value |
| --------------------------------------- | --------------------------------- |
| **Object Detection Model Type** | `rfdetr` |
| **Custom object detector model path** | `/config/model_cache/rfdetr.onnx` (use the filename you generated above) |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/rfdetr.onnx` |
| **Object Detection Model Type** | `rfdetr` |
yaml: |-
detectors:
ov:
@ -343,7 +356,7 @@ openvino:
height: 320
input_tensor: nchw
input_dtype: float
path: /config/model_cache/rfdetr.onnx
path: /config/model_cache/rfdetr.onnx # use the filename you generated above
- key: dfine
label: D-FINE / DEIMv2
recommended: false
@ -421,13 +434,14 @@ openvino:
| Field | Value |
| ---------------------------------------- | ---------------------------------- |
| **Object Detection Model Type** | `dfine` |
| **Custom object detector model path** | `/config/model_cache/dfine-s.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `640` |
| **Object detection model input height** | `640` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/dfine-s.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `dfine` |
yaml: |-
detectors:
ov:
@ -440,7 +454,7 @@ openvino:
height: 640
input_tensor: nchw
input_dtype: float
path: /config/model_cache/dfine-s.onnx
path: /config/model_cache/dfine-s.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
appleSilicon:
title: Apple Silicon
@ -476,13 +490,14 @@ appleSilicon:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match the imgsize set during model export) |
| **Object detection model input height** | `320` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
apple-silicon:
@ -495,7 +510,7 @@ appleSilicon:
height: 320 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float
path: /config/model_cache/yolo.onnx
path: /config/model_cache/yolo.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: yolo-legacy
label: YOLO (v3, v4, v7)
@ -514,13 +529,14 @@ appleSilicon:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match the imgsize set during model export) |
| **Object detection model input height** | `320` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
apple-silicon:
@ -533,7 +549,7 @@ appleSilicon:
height: 320 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float
path: /config/model_cache/yolo.onnx
path: /config/model_cache/yolo.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
onnx:
title: ONNX
@ -569,13 +585,14 @@ onnx:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match the imgsize set during model export) |
| **Object detection model input height** | `320` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
onnx:
@ -587,7 +604,7 @@ onnx:
height: 320 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float
path: /config/model_cache/yolo.onnx
path: /config/model_cache/yolo.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: rfdetr
label: RF-DETR
@ -614,12 +631,13 @@ onnx:
| Field | Value |
| --------------------------------------- | --------------------------------- |
| **Object Detection Model Type** | `rfdetr` |
| **Custom object detector model path** | `/config/model_cache/rfdetr.onnx` (use the filename you generated above) |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/rfdetr.onnx` |
| **Object Detection Model Type** | `rfdetr` |
yaml: |-
detectors:
onnx:
@ -631,7 +649,7 @@ onnx:
height: 320
input_tensor: nchw
input_dtype: float
path: /config/model_cache/rfdetr.onnx
path: /config/model_cache/rfdetr.onnx # use the filename you generated above
- key: yolonas
label: YOLO-NAS
recommended: false
@ -650,13 +668,14 @@ onnx:
| Field | Value |
| ---------------------------------------- | ------------------------------------------------- |
| **Object Detection Model Type** | `yolonas` |
| **Custom object detector model path** | `/config/yolo_nas_s.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match whatever was set in notebook) |
| **Object detection model input height** | `320` (should match whatever was set in notebook) |
| **Model Input Pixel Color Format** | `bgr` |
| **Model Input Tensor Shape** | `nchw` |
| **Custom object detector model path** | `/config/yolo_nas_s.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolonas` |
yaml: |-
detectors:
onnx:
@ -679,13 +698,14 @@ onnx:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolox` |
| **Custom object detector model path** | `/config/model_cache/yolox_tiny.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `416` (should match the imgsize set during model export) |
| **Object detection model input height** | `416` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float_denorm` |
| **Custom object detector model path** | `/config/model_cache/yolox_tiny.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolox` |
yaml: |-
detectors:
onnx:
@ -697,7 +717,7 @@ onnx:
height: 416 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float_denorm
path: /config/model_cache/yolox_tiny.onnx
path: /config/model_cache/yolox_tiny.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: dfine
label: D-FINE / DEIMv2
@ -776,13 +796,14 @@ onnx:
| Field | Value |
| ---------------------------------------- | ------------------------------------------- |
| **Object Detection Model Type** | `dfine` |
| **Custom object detector model path** | `/config/model_cache/dfine_m_obj2coco.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `640` |
| **Object detection model input height** | `640` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/dfine_m_obj2coco.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `dfine` |
yaml: |-
detectors:
onnx:
@ -794,7 +815,7 @@ onnx:
height: 640
input_tensor: nchw
input_dtype: float
path: /config/model_cache/dfine_m_obj2coco.onnx
path: /config/model_cache/dfine_m_obj2coco.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
- key: yolo-legacy
label: YOLO (v3, v4, v7)
@ -813,13 +834,14 @@ onnx:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (should match the imgsize set during model export) |
| **Object detection model input height** | `320` (should match the imgsize set during model export) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Custom object detector model path** | `/config/model_cache/yolo.onnx` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
onnx:
@ -831,7 +853,7 @@ onnx:
height: 320 # <--- should match the imgsize set during model export
input_tensor: nchw
input_dtype: float
path: /config/model_cache/yolo.onnx
path: /config/model_cache/yolo.onnx # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
cpu:
title: CPU
@ -893,12 +915,13 @@ memryx:
| Field | Value |
| ---------------------------------------- | ------------------------------------------------- |
| **Object Detection Model Type** | `yolonas` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (can be set to `640` for higher resolution) |
| **Object detection model input height** | `320` (can be set to `640` for higher resolution) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolonas` |
yaml: |-
detectors:
memx0:
@ -929,12 +952,13 @@ memryx:
| Field | Value |
| ---------------------------------------- | ------------------------------------------------- |
| **Object Detection Model Type** | `yolo-generic` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` (can be set to `640` for higher resolution) |
| **Object detection model input height** | `320` (can be set to `640` for higher resolution) |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
memx0:
@ -964,12 +988,13 @@ memryx:
| Field | Value |
| ---------------------------------------- | ----------------------- |
| **Object Detection Model Type** | `yolox` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `640` |
| **Object detection model input height** | `640` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float_denorm` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `yolox` |
yaml: |-
detectors:
memx0:
@ -999,12 +1024,13 @@ memryx:
| Field | Value |
| ---------------------------------------- | ----------------------- |
| **Object Detection Model Type** | `ssd` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `float` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object Detection Model Type** | `ssd` |
yaml: |-
detectors:
memx0:
@ -1047,12 +1073,14 @@ tensorrt:
| Field | Value |
| ---------------------------------------- | ------------------------------------------------------------ |
| **Custom object detector model path** | `/config/model_cache/tensorrt/yolov7-320.trt` |
| **Custom object detector model path** | `/config/model_cache/tensorrt/yolov7-320.trt` (use the filename you generated above) |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input Pixel Color Format** | `rgb` |
| **Object detection model input width** | `320` (MUST match the chosen model, e.g., yolov7-320 -> 320) |
| **Object detection model input height** | `320` (MUST match the chosen model, e.g., yolov7-320 -> 320) |
| **Model Input Pixel Color Format** | `rgb` |
| **Model Input Tensor Shape** | `nchw` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `ssd` (Frigate's default value) |
yaml: |-
detectors:
tensorrt:
@ -1060,7 +1088,7 @@ tensorrt:
device: 0 #This is the default, select the first GPU
model:
path: /config/model_cache/tensorrt/yolov7-320.trt
path: /config/model_cache/tensorrt/yolov7-320.trt # use the filename you generated above
labelmap_path: /labelmap/coco-80.txt
input_tensor: nchw
input_pixel_format: rgb
@ -1079,10 +1107,13 @@ synaptics:
| Field | Value |
| ---------------------------------------- | ---------------------------- |
| **Custom object detector model path** | `/synaptics/mobilenet.synap` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `224` |
| **Object detection model input height** | `224` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nhwc` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `ssd` (Frigate's default value) |
yaml: |-
detectors: # required
synap_npu: # required
@ -1110,11 +1141,13 @@ rknn:
| Field | Value |
| ---------------------------------------- | -------------------------------------------------- |
| **Custom object detector model path** | `frigate-fp16-yolov9-t` (or other yolov9 variants) |
| **Object Detection Model Type** | `yolo-generic` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nhwc` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
model: # required
# name of model (will be automatically downloaded) or path to your own .rknn model file
@ -1146,12 +1179,13 @@ rknn:
| Field | Value |
| ---------------------------------------- | ----------------------------------------------------------------------- |
| **Custom object detector model path** | `deci-fp16-yolonas_s` (or `deci-fp16-yolonas_m`, `deci-fp16-yolonas_l`) |
| **Object Detection Model Type** | `yolonas` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input Pixel Color Format** | `bgr` |
| **Model Input Tensor Shape** | `nhwc` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolonas` |
yaml: |-
model: # required
# name of model (will be automatically downloaded) or path to your own .rknn model file
@ -1180,11 +1214,13 @@ rknn:
| Field | Value |
| ---------------------------------------- | ---------------------------------------------- |
| **Custom object detector model path** | `rock-i8-yolox_nano` (or other yolox variants) |
| **Object Detection Model Type** | `yolox` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `416` |
| **Object detection model input height** | `416` |
| **Model Input Pixel Color Format** | `rgb` (Frigate's default value) |
| **Model Input Tensor Shape** | `nhwc` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input D Type** | `int` (Frigate's default value) |
| **Object Detection Model Type** | `yolox` |
yaml: |-
model: # required
# name of model (will be automatically downloaded) or path to your own .rknn model file
@ -1213,12 +1249,13 @@ axengine:
| Field | Value |
| ---------------------------------------- | ----------------------- |
| **Custom object detector model path** | `frigate-yolov9-tiny` |
| **Object Detection Model Type** | `yolo-generic` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Object detection model input width** | `320` |
| **Object detection model input height** | `320` |
| **Model Input D Type** | `int` |
| **Model Input Pixel Color Format** | `bgr` |
| **Label map for custom object detector** | `/labelmap/coco-80.txt` |
| **Model Input Tensor Shape** | `nhwc` (Frigate's default value) |
| **Model Input D Type** | `int` |
| **Object Detection Model Type** | `yolo-generic` |
yaml: |-
detectors:
axengine: