> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/models/supported-tasks/classification.md).

# Classification

Label whole images by what they show, then train and deploy your own image classification model on Roboflow.

## What is image classification?

Classification gives a label to a whole image, without saying where things are. Roboflow supports two kinds:

* Single-label classification returns one class per image, with a confidence score (ex: "pass" or "fail").
* Multi-label classification returns every class that applies to the image, each with its own score (ex: "dented" and "label missing").

Use it when you only need to know what an image shows. To find where objects are, use [Object Detection](https://docs.roboflow.com/models/supported-tasks/object-detection.md).

<figure><img src="https://3448603185-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fcmo9mhfIjYrvFFy1U7dk%2Fuploads%2Fgit-blob-b41b34795b6e89950cbd616a9a5f2c602183029f%2Fimg-task-classification-wide.webp?alt=media" alt="An orange slice labeled orange and a peeled tangerine labeled tangerine"><figcaption></figcaption></figure>

## Supported image classification models

Roboflow supports these classification models. See the [Classification models](https://docs.roboflow.com/models/supported-models.md#classification) table for export and deployment support per model.

<table data-search="false"><thead><tr><th>Model</th><th>License</th><th data-type="checkbox">Trainable on Roboflow</th><th>Latest release</th></tr></thead><tbody><tr><td><a href="https://docs.roboflow.com/models/supported-models/roboflow-3.md">Roboflow 3.0</a></td><td><a href="https://roboflow.com/licensing">Roboflow Licensing</a></td><td>false</td><td>2023</td></tr><tr><td><a href="https://docs.roboflow.com/models/supported-models/dino-v3.md">DINOv3</a></td><td><a href="https://docs.roboflow.com/models/model-licenses.md#other-models">Upstream license</a></td><td>true</td><td>2025</td></tr><tr><td><a href="https://docs.roboflow.com/models/supported-models/vit.md">ViT</a></td><td><a href="https://docs.roboflow.com/models/model-licenses.md#other-models">Upstream license</a></td><td>true</td><td>2020</td></tr><tr><td><a href="https://docs.roboflow.com/models/supported-models/resnet.md">ResNet</a></td><td><a href="https://docs.roboflow.com/models/model-licenses.md#other-models">Upstream license</a></td><td>true</td><td>2015</td></tr></tbody></table>

## Fine-tuning a classification model

{% stepper %}
{% step %}

### Create a classification project

Create a [Project](https://docs.roboflow.com/datasets/create-and-upload/create-a-project) and pick Single-Label Classification or Multi-Label Classification as the project type.

<figure><img src="https://3448603185-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fcmo9mhfIjYrvFFy1U7dk%2Fuploads%2Fgit-blob-1d77b799d2ee67437f44dce9451712749f2a4045%2Fcreate-project-classification.webp?alt=media" alt="Create project form with Classification selected as the project type and a preview of a classification example"><figcaption></figcaption></figure>
{% endstep %}

{% step %}

### Upload and label images

[Upload images](https://docs.roboflow.com/datasets/create-and-upload/adding-data), then label them. The fastest way is [Auto Label](https://docs.roboflow.com/datasets/annotate/annotate/ai-labeling/auto-label): a foundation model (ex: GPT-6.1 Sol or CLIP) or one of your trained models picks the class for every image in a batch, and you review the results. You can also pick each image's class in the [annotation editor](https://docs.roboflow.com/datasets/annotate/annotate/annotation-tools), with [Label Assist](https://docs.roboflow.com/datasets/annotate/annotate/ai-labeling/model-assisted-labeling) suggesting it from a model or by hand. On a multi-label project, pick every class that applies.

<figure><img src="https://3448603185-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fcmo9mhfIjYrvFFy1U7dk%2Fuploads%2Fgit-blob-12341a515b4472f5d0aa09615aefebde2c6149a9%2Fannotate-classification.webp?alt=media" alt="Annotation editor on a classification image with the class picker open and Maltese_dog selected"><figcaption></figcaption></figure>
{% endstep %}

{% step %}

### Generate a dataset version

[Generate a dataset version](https://docs.roboflow.com/datasets/versions/dataset-versions/create-a-dataset-version): a frozen snapshot of your images with a train, valid, and test split, plus any preprocessing and augmentation.
{% endstep %}

{% step %}

### Train a classification model

Click "Train" and pick an architecture and size. See [Train a Model](https://docs.roboflow.com/models/train/train-a-model.md) for every option.

<figure><img src="https://3448603185-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fcmo9mhfIjYrvFFy1U7dk%2Fuploads%2Fgit-blob-a0f81af014386ec0e7c7cdc96834b7611841c6d9%2Ftrain-architectures-classification.webp?alt=media" alt="Select Architecture step on the Train page listing DINOv3, ViT, and ResNet"><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}

## Deploy a classification model

After training, deploy your classification model with the [Serverless Cloud API](https://docs.roboflow.com/deployment/roboflow-cloud/serverless-api), a [Dedicated Deployment](https://docs.roboflow.com/deployment/roboflow-cloud/dedicated-deployments), or on your own hardware with [Roboflow Inference](https://docs.roboflow.com/deployment/self-hosted/self-hosted). See [Choosing a Deployment](https://docs.roboflow.com/deployment/choosing-a-deployment) to compare the options.
