Hello image data: Create an image classification dataset and import images

Use the Google Cloud console to create an image classification dataset.After your dataset is created, use a CSV pointing to images in a publicCloud Storage bucket to import those images into the dataset.

This tutorial has several pages:

  1. Set up your project and environment.

  2. Create an image classification dataset, and import images.

  3. Train an AutoML image classification model.

  4. Evaluate and analyze model performance.

  5. Deploy a model to an endpoint, and send a prediction.

  6. Clean up your project.

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

Image data input file

Key point: A single dataset can be used for multiple objectives. This tutorial focuses onimage classification (applying a label to an image), but the same data could be used for another objective, such asobject detection (object identification and labeling).

The image files you use in this tutorial are from the flower dataset used inthisTensorflow blog post.These input images are stored in a public Cloud Storage bucket. Thispublicly-accessible bucket also contains a CSV file you use for data import.This file has two columns:the first column lists an image's URI in Cloud Storage, and the secondcolumn contains the image's label. Below you can see some sample rows:

gs://cloud-samples-data/ai-platform/flowers/flowers.csv:

gs://cloud-samples-data/ai-platform/flowers/daisy/10559679065_50d2b16f6d.jpg,daisygs://cloud-samples-data/ai-platform/flowers/dandelion/10828951106_c3cd47983f.jpg,dandeliongs://cloud-samples-data/ai-platform/flowers/roses/14312910041_b747240d56_n.jpg,rosesgs://cloud-samples-data/ai-platform/flowers/sunflowers/127192624_afa3d9cb84.jpg,sunflowersgs://cloud-samples-data/ai-platform/flowers/tulips/13979098645_50b9eebc02_n.jpg,tulips

Create an image classification dataset and import data

Visit theGoogle Cloud consoleto begin the process of creating your dataset and training your imageclassification model.

When prompted, make sure to select the project that you used for your CloudStorage bucket.

  1. From the Get started with Vertex AI page, clickCreate dataset.

    Vertex AI dashboard

  2. Specify a name for this dataset (optional).

  3. In the Image tab of the "Select a data type and objective" section, choosetheImage classification (Single-label)radio option. In the Region drop-down menu selectUS Central.

    New dataset window

  4. SelectCreate to create the empty dataset. After selecting Create youwill advance to the data import window.

  5. Select theSelectimport files from Cloud Storage and specify the Cloud StorageURI of the CSV file with the image location and label data. For thisquickstart, the CSV file is atgs://cloud-samples-data/ai-platform/flowers/flowers.csv. Copy and pastethe following into the "Import file path" field:

    • cloud-samples-data/ai-platform/flowers/flowers.csv

    Select file import window

  6. ClickContinue to begin image import. The import process takes afew minutes. When it completes, you are taken to the next page that showsall of the images identified for your dataset, both labeled andunlabeled images.When using the indicated flower dataset, you will see several warning alerts. This is purposeful, to show you error messages you may encounter with your own data.

What's next

Follow thenext page of this tutorial to start anAutoML model training job.

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026-02-18 UTC.