Before You Begin

Before you can use AutoML Vision, you must enable it for your project. Follow the instructions on this page, or visit the [AutoML Vision UI] (https://beta-dot-custom-vision.appspot.com/vision/) and click Do it for me to automatically set up your project (once you've enabled billing in step 1 of the linked page.)

  1. Sign in to your Google Account.

    If you don't already have one, sign up for a new account.

  2. In the GCP Console, go to the Manage resources page and select or create a new project.

    Go to the Manage resources page

  3. Make sure that billing is enabled for your project.

    Learn how to enable billing

  4. Enable the Cloud AutoML and Storage APIs.

    Enable the APIs

  5. Install the gcloud command line tool.
  6. Follow the instructions to create a service account and download a key file.
  7. Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path to the service account key file that you downloaded when you created the service account. For example:
         export GOOGLE_APPLICATION_CREDENTIALS=key-file
  8. Add your new service account to the AutoML Editor IAM role with the following commands. Replace project-id with the name of your GCP project and replace service-account-name with the name of your new service account, for example service-account1@myproject.iam.gserviceaccount.com.
         gcloud auth login
         gcloud config set project project-id
         gcloud projects add-iam-policy-binding project-id \
           --member=serviceAccount:service-account-name \
           --role='roles/automl.editor'
  9. Allow the AutoML Vision service accounts to access your Google Cloud project resources:
    gcloud projects add-iam-policy-binding project-id \
      --member="serviceAccount:custom-vision@appspot.gserviceaccount.com" \
      --role="roles/ml.admin"
    gcloud projects add-iam-policy-binding project-id \
      --member="serviceAccount:custom-vision@appspot.gserviceaccount.com" \
      --role="roles/storage.admin"
  10. Create a Google Cloud Storage bucket for storing your images:
    gsutil mb -p $PROJECT -c regional -l us-central1 gs://project-id-vcm/

Was this page helpful? Let us know how we did:

Send feedback about...

Cloud AutoML Vision