You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/cognitive-services/Custom-Vision-Service/java-tutorial-od.md
+7-7Lines changed: 7 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -52,37 +52,37 @@ Load the `Vision/CustomVision` project in your Java IDE and open the _CustomVisi
52
52
53
53
Go to the code block that creates a training client and an object detection project. The created project will show up on the [Custom Vision website](https://customvision.ai/) that you visited earlier. See the [CreateProject](https://docs.microsoft.com/java/api/com.microsoft.azure.cognitiveservices.vision.customvision.training.trainings.createproject?view=azure-java-stable#com_microsoft_azure_cognitiveservices_vision_customvision_training_Trainings_createProject_String_CreateProjectOptionalParameter_) method overloads to specify other options when you create your project (explained in the [Build a detector](get-started-build-detector.md) web portal guide).
When you tag images in object detection projects, you need to specify the region of each tagged object using normalized coordinates. Go to the definition of the `regionMap` Map. This code associates each of the sample images with its tagged region.
Then, skip to the code block that adds the images to the project. The images are read from the **src/main/resources** folder of the project and are uploaded to the service with their appropriate tags and region coordinates.
The previous code snippet makes use of two helper functions that retrieve the images as resource streams and upload them to the service (you can upload up to 64 images in a single batch).
This code creates the first iteration in the project and then publishes that iteration to the prediction endpoint. The name given to the published iteration can be used to send prediction requests. An iteration is not available in the prediction endpoint until it is published.
The prediction endpoint, represented by the `predictor` object here, is the reference that you use to submit an image to the current model and get a classification prediction. In this sample, `predictor` is defined elsewhere using the prediction key environment variable.
Copy file name to clipboardExpand all lines: articles/cognitive-services/Custom-Vision-Service/java-tutorial.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -53,33 +53,33 @@ Load the `Vision/CustomVision` project in your Java IDE and open the _CustomVisi
53
53
54
54
This first bit of code creates an image classification project. The created project will show up on the [Custom Vision website](https://customvision.ai/) that you visited earlier. See the [CreateProject](https://docs.microsoft.com/java/api/com.microsoft.azure.cognitiveservices.vision.customvision.training.trainings.createproject?view=azure-java-stable#com_microsoft_azure_cognitiveservices_vision_customvision_training_Trainings_createProject_String_CreateProjectOptionalParameter_) method overloads to specify other options when you create your project (explained in the [Build a classifier](getting-started-build-a-classifier.md) web portal guide).
The sample images are included in the **src/main/resources** folder of the project. They are read from there and uploaded to the service with their appropriate tags.
The previous code snippet makes use of two helper functions that retrieve the images as resource streams and upload them to the service (you can upload up to 64 images in a single batch).
This code creates the first iteration in the project and then publishes that iteration to the prediction endpoint. The name given to the published iteration can be used to send prediction requests. An iteration is not available in the prediction endpoint until it is published.
The prediction endpoint, represented by the `predictor` object here, is the reference that you use to submit an image to the current model and get a classification prediction. In this sample, `predictor` is defined elsewhere using the prediction key environment variable.
0 commit comments