Choose a training method

Use this topic to understand key differences between AutoML and custom training so you can decide which one is right for you.

AutoML lets you create and train a model with minimal technical effort. Even if you want the flexibility of a custom training application, you can use AutoML to quickly prototype models and explore new datasets before investing in development. For example, you can use it to learn which are good features in a dataset.

Custom training lets you create a training application optimized for your targeted outcome. You have complete control over training application functionality; you can target any objective, use any algorithm, develop your own loss functions or metrics, or do any other customization.

Use the following table to quickly compare AutoML and custom training functionality.

AutoML Custom training
Data science expertise needed No Yes, to develop the training application and also to do some of the data preparation like feature engineering.
Programming ability needed No, AutoML is codeless. Yes, to develop the training application.
Time to trained model Lower. Less data preparation is required, and no development is needed. Higher. More data preparation is required, and training application development is needed.
Limits on machine learning objectives Yes, you must target one of AutoML's pre-defined objectives. No
Can manually optimize model performance with hyperparameter tuning No. AutoML does some automated hyperparameter tuning, but you can't modify the values used. Yes. You can tune the model during each training run for experimentation and comparison.
Can control aspects of the training environment Limited. For image and tabular datasets, you can specify the number of node hours to train for, and whether to allow early stopping of training. Yes. You can specify aspects of the environment such as Compute Engine machine type, disk size, machine learning framework, and number of nodes.
Limits on data size

Yes. AutoML uses managed datasets; data size limitations vary depending on the type of dataset. Refer to one of the following topics for specifics:

For unmanaged datasets, no. Managed datasets have the same limits as Vertex AI datasets that are used to train AutoML models.

What's next