From 97fa9630565ce4bfad7bf35bd38a79278bae23c1 Mon Sep 17 00:00:00 2001 From: Naomi Pentrel <5212232+npentrel@users.noreply.github.com> Date: Fri, 9 Aug 2024 16:31:37 +0200 Subject: [PATCH 1/2] Update detect-people.md --- docs/get-started/detect-people.md | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/docs/get-started/detect-people.md b/docs/get-started/detect-people.md index 7a35df92bd..8a1f071912 100644 --- a/docs/get-started/detect-people.md +++ b/docs/get-started/detect-people.md @@ -97,9 +97,7 @@ Create the service. In the resulting ML model service configuration pane, ensure that **Deploy model on machine** is selected for the **Deployment** field. -Click on **Select models** and select the `ml-models-scuttle:people` model from the registry (the **people** model by **ml-models-scuttle**) to deploy an object detection TFLite model that has been trained to be able to detect a person. - -Click the **Save** button in the top right corner of the page to save your configuration and deploy an object detection TFLite model that has been trained to be able to detect a person. +Click on **Select model** and select the `ml-models-scuttle:people` model from the registry (the **people** model by **ml-models-scuttle**) to deploy an object detection TFLite model that has been trained to be able to detect a person. For more detailed information, including optional attribute configuration, see the [`tflite_cpu` docs](/services/ml/deploy/tflite_cpu/). @@ -117,9 +115,9 @@ Click the **Save** button in the top right corner of the page to save your visio {{% /expand%}} {{%expand "Step 6: Test person detection" %}} -Now, test your person detection on in the **Test** section of the computer vision service's configuration panel or on the **CONTROL** tab. +Now, test your person detection in the **Test** section of the computer vision service's configuration panel or on the **CONTROL** tab. -You will see your camera stream and see detections as labeled boxes on the images along with position, dimension, class and confidence data. +You will see your camera stream and see detections as labeled boxes on the images along with labels and confidence data. Detections in class `Person` with a high confidence score show positive person detections, but the ML model can also detect other objects: {{}} From 647173ff8f035ecb75d13176d356463d947452bf Mon Sep 17 00:00:00 2001 From: Naomi Pentrel <5212232+npentrel@users.noreply.github.com> Date: Fri, 9 Aug 2024 17:16:20 +0200 Subject: [PATCH 2/2] Update detect-people.md --- docs/get-started/detect-people.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/get-started/detect-people.md b/docs/get-started/detect-people.md index 8a1f071912..bf530a8635 100644 --- a/docs/get-started/detect-people.md +++ b/docs/get-started/detect-people.md @@ -143,14 +143,14 @@ The full configuration for the attributes of the vision service should resemble: } ``` -This optional attribute reduces your detections output (which you'll view in step 7) by filtering out detections below the threshold of 82% confidence. +This optional attribute reduces your detections output by filtering out detections below the threshold of 82% confidence. You can adjust this attribute as necessary. -Click the **Save** button in the top right corner of the page to save your configuration. -For more detailed information, including optional attribute configuration, see the [`mlmodel` docs](/services/vision/mlmodel/). - +Click the **Save** button in the top right corner of the page to save your configuration and close and reopen the **Test** panel of the vision service configuration panel. Now if you view detections, you will only see detections with a confidence value higher than the `"default_minimum_confidence"` attribute. +For more detailed information, including optional attribute configuration, see the [`mlmodel` docs](/services/vision/mlmodel/). + {{}} {{% /expand%}}