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.

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 .