Hello image data: Training an AutoML image classification model

Use the Google Cloud Console to train an AutoML image classification model. After your dataset is created and data is imported, use the Cloud Console to review the training images and begin model training.

This tutorial has several pages:

1. Setting up your project and environment.

2. Creating an image classification dataset and importing images.

3. Training an AutoML image classification model.

4. Deploying a model to an endpoint and send a prediction.

5. Cleaning up your project.

Each page assumes that you have already performed the instructions from the previous pages of the tutorial.

1. Review imported images

After dataset import you will be taken to the Browse tab. You can also access this tab by selecting Datasets from the side menu, then selecting the annotation set (set of single-label image annotations) associated with your new dataset.

Key point: An annotation set is the collection of annotations associated with a data type and a specific objective (image data type, classification objective in this case). For more information about annotation sets, see Creating an annotation set.

Go to the Datasets page

2. Begin AutoML model training

In the Browse tab you can choose Train new model to begin training. You can also start training by selecting Models from the side menu, then selecting Create.

1. Go to the Models page

2. Select Create to open the Train new model window.

3. In the first "Choose training method" section choose the target Dataset and Annotation set if they are not automatically selected. Make sure the AutoML radio button is selected, and then choose Continue.

   

4. In the following "Define your model" section, fill the Model name field (optional), and then choose Continue.

5. In the final "Compute and pricing" specify a node hour budget of 8 node hours, and select Start training.

Training takes several hours. You will receive a notification email when model training finishes.

What's next

Follow the next page of this tutorial to deploy your trained AutoML model to an endpoint and sent an image to the model for prediction.