Ctrlk
Sign InBook a DemoGet Started
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Models

Train, evaluate, and choose computer vision models on Roboflow.

Train state-of-the-art computer vision models on your datasets - no ML expertise or GPU setup required. Roboflow manages the training infrastructure and hosts the resulting models for deployment.

Choose & Train

Cover

Supported Models

Every model you can train, upload, or deploy with Roboflow, and where each runs.

Cover

Train a Model

Start a training job from the dashboard, API, SDK, or CLI.

Cover

Roboflow Instant

A model trained automatically from your first approved annotations.

Cover

Neural Architecture Search

Discover and fine-tune novel architectures.

Cover

Roboflow Rapid

Build a working model from a small sample of data in minutes.

Cover

Train from a Checkpoint

Start training from an existing Roboflow Universe model.

You can also train from a third-party checkpoint on Azure Vision or Google Cloud.

Evaluate & Understand

Cover

Evaluate Trained Models

Evaluation runs, mAP, and confusion matrices.

Cover

Training Results

Review metrics and graphs from a completed training job.

Cover

View Trained Models

Browse the models trained in your workspace.

Cover

Training Resolutions

See the input resolution used by each model type.

Cover

Versions, Trainings, and Models

How datasets, training jobs, and models relate.

Cover

Model IDs

How models are identified when you deploy or run inference.

Trained models deploy through the Serverless Cloud API, Dedicated Deployments, or self-hosted Inference.

NextModel IDs

Last updated

Was this helpful?