Hello image data: Create an image classification dataset and import images
Stay organized with collections
Save and categorize content based on your preferences.
Use the Google Cloud console to create an image classification dataset.
After your dataset is created, use a CSV pointing to images in a public
Cloud Storage bucket to import those images into the dataset.
Each page assumes that you have already performed the instructions from the
previous pages of the tutorial.
Image data input file
The image files you use in this tutorial are from the flower dataset used in
this Tensorflow blog post.
These input images are stored in a public Cloud Storage bucket. This
publicly-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 second
column contains the image's label. Below you can see some sample rows:
Create an image classification dataset and import data
Visit the Google Cloud console
to begin the process of creating your dataset and training your image
classification model.
When prompted, make sure to select the project that you used for your Cloud
Storage bucket.
From the Get started with Vertex AI page, click
Create dataset.
Specify a name for this dataset (optional).
In the Image tab of the "Select a data type and objective" section, choose
the
radio_button_checkedImage classification (Single-label)
radio option. In the Region drop-down menu select US Central.
Select Create to create the empty dataset. After selecting Create you
will advance to the data import window.
Select the radio_button_checkedSelect
import files from Cloud Storage and specify the Cloud Storage
URI of the CSV file with the image location and label data. For this
quickstart, the CSV file is at
gs://cloud-samples-data/ai-platform/flowers/flowers.csv. Copy and paste
the following into the "Import file path" field:
Click Continue to begin image import. The import process takes a
few minutes. When it completes, you are taken to the next page that shows
all of the images identified for your dataset, both labeled and
unlabeled images.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-29 UTC."],[],[],null,["# Hello image data: Create an image classification dataset and import images\n\nUse the Google Cloud console to create an image classification dataset.\nAfter your dataset is created, use a CSV pointing to images in a public\nCloud Storage bucket to import those images into the dataset.\n\nThis tutorial has several pages:\n\n1. [Set up your project and environment.](/vertex-ai/docs/tutorials/image-classification-automl)\n\n2. Create an image classification dataset, and\n import images.\n\n3. [Train an AutoML image classification\n model.](/vertex-ai/docs/tutorials/image-classification-automl/training)\n\n4. [Evaluate and analyze model performance.](/vertex-ai/docs/tutorials/image-classification-automl/error-analysis)\n\n5. [Deploy a model to an endpoint, and send a\n prediction.](/vertex-ai/docs/tutorials/image-classification-automl/deploy-predict)\n\n6. [Clean up your project.](/vertex-ai/docs/tutorials/image-classification-automl/cleanup)\n\nEach page assumes that you have already performed the instructions from the\nprevious pages of the tutorial.\n\nImage data input file\n---------------------\n\n| **Key point** : A single dataset can be used for multiple objectives. This tutorial focuses on *image classification* (applying a label to an image), but the same data could be used for another objective, such as *object detection* (object identification and labeling).\n\nThe image files you use in this tutorial are from the flower dataset used in\nthis [Tensorflow blog post](https://cloud.google.com/blog/products/gcp/how-to-classify-images-with-tensorflow-using-google-cloud-machine-learning-and-cloud-dataflow).\nThese input images are stored in a public Cloud Storage bucket. This\npublicly-accessible bucket also contains a CSV file you use for data import.\nThis file has two columns:\nthe first column lists an image's URI in Cloud Storage, and the second\ncolumn contains the image's label. Below you can see some sample rows:\n\n`gs://cloud-samples-data/ai-platform/flowers/flowers.csv`: \n\n gs://cloud-samples-data/ai-platform/flowers/daisy/10559679065_50d2b16f6d.jpg,daisy\n gs://cloud-samples-data/ai-platform/flowers/dandelion/10828951106_c3cd47983f.jpg,dandelion\n gs://cloud-samples-data/ai-platform/flowers/roses/14312910041_b747240d56_n.jpg,roses\n gs://cloud-samples-data/ai-platform/flowers/sunflowers/127192624_afa3d9cb84.jpg,sunflowers\n gs://cloud-samples-data/ai-platform/flowers/tulips/13979098645_50b9eebc02_n.jpg,tulips\n\nCreate an image classification dataset and import data\n------------------------------------------------------\n\nVisit the [Google Cloud console](https://console.cloud.google.com/vertex-ai/)\nto begin the process of creating your dataset and training your image\nclassification model.\n\nWhen prompted, make sure to select the project that you used for your Cloud\nStorage bucket.\n\n1. From the Get started with Vertex AI page, click\n **Create dataset**.\n\n2. Specify a name for this dataset (optional).\n\n3. In the Image tab of the \"Select a data type and objective\" section, choose\n the\n radio_button_checked**Image classification (Single-label)**\n radio option. In the Region drop-down menu select **US Central**.\n\n4. Select **Create** to create the empty dataset. After selecting Create you\n will advance to the data import window.\n\n5. Select the radio_button_checked**Select\n import files from Cloud Storage** and specify the Cloud Storage\n URI of the CSV file with the image location and label data. For this\n quickstart, the CSV file is at\n `gs://cloud-samples-data/ai-platform/flowers/flowers.csv`. Copy and paste\n the following into the \"Import file path\" field:\n\n -\n\n ```\n cloud-samples-data/ai-platform/flowers/flowers.csv\n ```\n\n6. Click **Continue** to begin image import. The import process takes a\n few minutes. When it completes, you are taken to the next page that shows\n all of the images identified for your dataset, both labeled and\n unlabeled images.\n\n | 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.\n\n \u003cbr /\u003e\n\nWhat's next\n-----------\n\nFollow the [next page of this tutorial](/vertex-ai/docs/tutorials/image-classification-automl/training) to start an\nAutoML model training job."]]
