Vertex AI Workbench and notebooks
The Vertex AI Workbench service provides a single development platform for the entire data science workflow; you can use it to launch Cloud VM instances/notebooks to query and explore data and to develop and train a model for deployment.
As we explained earlier in the Preparing the platform section, Jupyter Notebook is a widely used platform for ML model development. Vertex AI Workbench provides two Jupyter-Notebook-based options for your data scientists, managed notebooks and user-managed notebooks:
- Managed notebooks are Google-managed, Jupyter-based, scalable, enterprise-ready compute instances that help you set up and work in an end-to-end ML production environment.
- User-managed notebooks are heavily customizable instances and are thus fitting for users who need a lot of control over their environment. With a user-managed notebook instance, you have a suite of deep learning packages pre-installed, including TensorFlow and PyTorch...
