-
Book Overview & Buying
-
Table Of Contents
-
Feedback & Rating

Computer Vision on AWS
By :

Now we have labeled data, we can use it to train machine learning models with SageMaker or Rekognition Custom Labels. We will navigate to the Rekognition Custom Labels console (https://us-east-2.console.aws.amazon.com/rekognition/custom-labels#/).
Navigate to the Projects panel on the left sidebar and select on Create project. Give it a name, such as logo-detection
.
Next, we need to create a dataset. Select on Create dataset. Select Start with a single dataset and then select Import images labeled by SageMaker Ground Truth under Training dataset details.
Figure 9.16: Creating a dataset in the Rekognition Custom Labels console
Provide the location of output manifest file, such as s3://cv-on-aws-book-xxxx/chapter_09/output_data/packt-logo-labeling/manifests/output/output.manifest
, and select Create Dataset...