mirror of
https://github.com/blakeblackshear/frigate.git
synced 2026-02-03 17:55:21 +03:00
Updates for model config documentation
This commit is contained in:
parent
fc676e7107
commit
c914573090
@ -50,18 +50,28 @@ database:
|
|||||||
|
|
||||||
If using a custom model, the width and height will need to be specified.
|
If using a custom model, the width and height will need to be specified.
|
||||||
|
|
||||||
Custom models may also require different input tensor formats. The colorspace conversion supports RGB, BGR, or YUV frames to be sent to the object detector. The input tensor shape parameter is a list of axis to let the detector reorder (transpose) the standard layout [BHWC] to match what specified by the model.
|
Custom models may also require different input tensor formats. The colorspace conversion supports RGB, BGR, or YUV frames to be sent to the object detector. The input tensor shape parameter is an enumeration to match what specified by the model.
|
||||||
|
|
||||||
| Tensor Dimension | Description |
|
| Tensor Dimension | Description |
|
||||||
| :--------------: | -------------- |
|
| :--------------: | -------------- |
|
||||||
| B | Batch Size |
|
| N | Batch Size |
|
||||||
| H | Model Height |
|
| H | Model Height |
|
||||||
| W | Model Width |
|
| W | Model Width |
|
||||||
| C | Color Channels |
|
| C | Color Channels |
|
||||||
|
|
||||||
|
| Available Input Tensor Shapes |
|
||||||
|
| :---------------------------: |
|
||||||
|
| "nhwc" |
|
||||||
|
| "nchw" |
|
||||||
|
|
||||||
```yaml
|
```yaml
|
||||||
|
# Optional: model config
|
||||||
model:
|
model:
|
||||||
|
path: /path/to/model
|
||||||
|
width: 320
|
||||||
|
height: 320
|
||||||
input_tensor: "nhwc"
|
input_tensor: "nhwc"
|
||||||
|
input_pixel_format: "bgr"
|
||||||
```
|
```
|
||||||
|
|
||||||
The labelmap can be customized to your needs. A common reason to do this is to combine multiple object types that are easily confused when you don't need to be as granular such as car/truck. By default, truck is renamed to car because they are often confused. You cannot add new object types, but you can change the names of existing objects in the model.
|
The labelmap can be customized to your needs. A common reason to do this is to combine multiple object types that are easily confused when you don't need to be as granular such as car/truck. By default, truck is renamed to car because they are often confused. You cannot add new object types, but you can change the names of existing objects in the model.
|
||||||
|
|||||||
@ -100,7 +100,8 @@ model:
|
|||||||
# Optional: Object detection model input colorspace
|
# Optional: Object detection model input colorspace
|
||||||
# Valid values are rgb, bgr, or yuv. (default: shown below)
|
# Valid values are rgb, bgr, or yuv. (default: shown below)
|
||||||
input_pixel_format: rgb
|
input_pixel_format: rgb
|
||||||
# Optional: Object detection model input tensor format (default: shown below)
|
# Optional: Object detection model input tensor format
|
||||||
|
# Valid values are nhwc or nchw (default: shown below)
|
||||||
input_tensor: "nhwc"
|
input_tensor: "nhwc"
|
||||||
# Optional: Label name modifications. These are merged into the standard labelmap.
|
# Optional: Label name modifications. These are merged into the standard labelmap.
|
||||||
labelmap:
|
labelmap:
|
||||||
|
|||||||
Loading…
Reference in New Issue
Block a user