Skip to content

Commit e7ad38d

Browse files
authored
Update model docs (#15779)
1 parent a1ce9aa commit e7ad38d

File tree

2 files changed

+14
-7
lines changed

2 files changed

+14
-7
lines changed

Diff for: docs/docs/configuration/object_detectors.md

+6-1
Original file line numberDiff line numberDiff line change
@@ -144,7 +144,9 @@ detectors:
144144

145145
#### SSDLite MobileNet v2
146146

147-
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.
147+
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.
148+
149+
Use the model configuration shown below when using the OpenVINO detector with the default OpenVINO model:
148150

149151
```yaml
150152
detectors:
@@ -254,6 +256,7 @@ yolov4x-mish-640
254256
yolov7-tiny-288
255257
yolov7-tiny-416
256258
yolov7-640
259+
yolov7-416
257260
yolov7-320
258261
yolov7x-640
259262
yolov7x-320
@@ -282,6 +285,8 @@ The TensorRT detector can be selected by specifying `tensorrt` as the model type
282285

283286
The TensorRT detector uses `.trt` model files that are located in `/config/model_cache/tensorrt` by default. These model path and dimensions used will depend on which model you have generated.
284287

288+
Use the config below to work with generated TRT models:
289+
285290
```yaml
286291
detectors:
287292
tensorrt:

Diff for: docs/docs/configuration/reference.md

+8-6
Original file line numberDiff line numberDiff line change
@@ -117,25 +117,27 @@ auth:
117117
hash_iterations: 600000
118118

119119
# Optional: model modifications
120+
# NOTE: The default values are for the EdgeTPU detector.
121+
# Other detectors will require the model config to be set.
120122
model:
121-
# Optional: path to the model (default: automatic based on detector)
123+
# Required: path to the model (default: automatic based on detector)
122124
path: /edgetpu_model.tflite
123-
# Optional: path to the labelmap (default: shown below)
125+
# Required: path to the labelmap (default: shown below)
124126
labelmap_path: /labelmap.txt
125127
# Required: Object detection model input width (default: shown below)
126128
width: 320
127129
# Required: Object detection model input height (default: shown below)
128130
height: 320
129-
# Optional: Object detection model input colorspace
131+
# Required: Object detection model input colorspace
130132
# Valid values are rgb, bgr, or yuv. (default: shown below)
131133
input_pixel_format: rgb
132-
# Optional: Object detection model input tensor format
134+
# Required: Object detection model input tensor format
133135
# Valid values are nhwc or nchw (default: shown below)
134136
input_tensor: nhwc
135-
# Optional: Object detection model type, currently only used with the OpenVINO detector
137+
# Required: Object detection model type, currently only used with the OpenVINO detector
136138
# Valid values are ssd, yolox, yolonas (default: shown below)
137139
model_type: ssd
138-
# Optional: Label name modifications. These are merged into the standard labelmap.
140+
# Required: Label name modifications. These are merged into the standard labelmap.
139141
labelmap:
140142
2: vehicle
141143
# Optional: Map of object labels to their attribute labels (default: depends on model)

0 commit comments

Comments
 (0)