Use the Face Blur model with the Python SDK

---

This tutorial shows you how to use the Python SDK to blur faces in video. The example blurs video files from a Cloud Storage bucket and generates blurred video outputs. These output videos are stored to the same Cloud Storage bucket as the source videos.

Objectives

This tutorial shows you how to do the following:

• Create a Cloud Storage bucket.
• Upload a local video file to the bucket.
• Send a request using the Python SDK.
• View blurred output videos.

Costs

In this document, you use the following billable components of Google Cloud:

• Vertex AI Vision (Models - Person / face blur)
• Cloud Storage

To generate a cost estimate based on your projected usage, use the pricing calculator. New Google Cloud users might be eligible for a free trial.

When you finish the tasks that are described in this document, you can avoid continued billing by deleting the resources that you created. For more information, see Clean up.

Before you begin

1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.
2. Install the Google Cloud CLI.

3. To initialize the gcloud CLI, run the following command:

   gcloud init

4. Create or select a Google Cloud project.

   Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

   • Create a Google Cloud project:

     gcloud projects create PROJECT_ID

     Replace PROJECT_ID with a name for the Google Cloud project you are creating.

   • Select the Google Cloud project that you created:

     gcloud config set project PROJECT_ID

     Replace PROJECT_ID with your Google Cloud project name.

5. Make sure that billing is enabled for your Google Cloud project.

6. Enable the Vertex AI Vision, Cloud Storage APIs:

   gcloud services enable visionai.googleapis.com storage.googleapis.com

7. If you're using a local shell, then create local authentication credentials for your user account:

   gcloud auth application-default login

   You don't need to do this if you're using Cloud Shell.

8. Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/visionai.editor, roles/storage.objectAdmin

   gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE

   • Replace PROJECT_ID with your project ID.

   • Replace USER_IDENTIFIER with the identifier for your user account. For example, user:[e-mail].

   • Replace ROLE with each individual role.
9. Install the Google Cloud CLI.

10. To initialize the gcloud CLI, run the following command:

    gcloud init

11. Create or select a Google Cloud project.

    Note: If you don't plan to keep the resources that you create in this procedure, create a project instead of selecting an existing project. After you finish these steps, you can delete the project, removing all resources associated with the project.

    • Create a Google Cloud project:

      gcloud projects create PROJECT_ID

      Replace PROJECT_ID with a name for the Google Cloud project you are creating.

    • Select the Google Cloud project that you created:

      gcloud config set project PROJECT_ID

      Replace PROJECT_ID with your Google Cloud project name.

12. Make sure that billing is enabled for your Google Cloud project.

13. Enable the Vertex AI Vision, Cloud Storage APIs:

    gcloud services enable visionai.googleapis.com storage.googleapis.com

14. If you're using a local shell, then create local authentication credentials for your user account:

    gcloud auth application-default login

    You don't need to do this if you're using Cloud Shell.

15. Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/visionai.editor, roles/storage.objectAdmin

    gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE

    • Replace PROJECT_ID with your project ID.

    • Replace USER_IDENTIFIER with the identifier for your user account. For example, user:[e-mail].

    • Replace ROLE with each individual role.
16. Get the Vertex AI Vision SDK source code:

    git clone https://github.com/google/visionai.git

    The Python examples are located in the visionai/python/example/ directory.

17. Get the Python SDK:

    wget https://github.com/google/visionai/releases/download/v0.0.5/visionai-0.0.5-py3-none-any.whl

Add input files to Cloud Storage

Before you can send a request using the Python SDK, create a Cloud Storage bucket and upload a local video to use as input.

1. Create a Cloud Storage bucket:

   gcloud storage buckets create gs://BUCKET_NAME
   

2. Upload a local video file to the new bucket:

   gcloud storage cp LOCAL_FILE gs://BUCKET_NAME
   

Install dependencies and send the request

After you create your Cloud Storage bucket for input and output videos and add a local video, install the necessary dependencies and send your request.

1. Optional. Set up your virtual environment:

   1. If not installed, install virtualenv:

      sudo apt-get install python3-venv
      

   2. Create a new virtual environment:

      python3 -m venv vaivenv
      

   3. Activate your virtual environment:

      source vaivenv/bin/activate
      

2. Install dependencies:

   pip3 install visionai-0.0.5-py3-none-any.whl
   pip3 install google-cloud-storage
   

3. Send your request with the Python SDK.

   Make the following variable substitutions:

   • PROJECT_ID: Your Google Cloud project ID.
   • LOCATION_ID: Your location ID. For example, us-central1. More information. Supported regions.
   • BUCKET_NAME: The Cloud Storage bucket you created.

   python3 visionai/python/example/blur_gcs_video.py \
   --project_id=PROJECT_ID –cluster_id=application-cluster-0 \
   –location_id=LOCATION_ID –bucket_name=BUCKET_NAME
   

   You should see output similar to the following:

    Listing mp4 files...
    test1.mp4
    test2.mp4
    Creating deid processes...
    process vnluvxgl is created
    process rvrdoucx is created
    Waiting for processes to finish...
    process vnluvxgl state is COMPLETED
    process rvrdoucx state is COMPLETED
    All processes have finished, please check the GCS bucket!
    ```
   

Examine output

After your video has finished processing you can examine the output in your Cloud Storage bucket. The generated blurred video files will be in the same Cloud Storage bucket as the source video.

1. List all objects in your bucket with the gcloud storage ls command:

   gcloud storage ls gs://bucket
   

   You should see the source files and output files similar to the following:

   test1.mp4
   test2.mp4
   test1_deid_output.mp4
   test2_deid_output.mp4
   

2. Optional. Download the output files locally with the gcloud storage cp command and view the blurred videos:

   gcloud storage cp gs://BUCKET_NAME/FILE_NAME .
   

Clean up

To avoid incurring charges to your Google Cloud account for the resources used in this tutorial, either delete the project that contains the resources, or keep the project and delete the individual resources.

What's next

• Read more about the Person blur model.
• Explore reference architectures, diagrams, and best practices about Google Cloud. Take a look at our Cloud Architecture Center.