Roboflow Features

Everything you need to establish processes and infrastructure for your computer vision projects.

Dataset Management

Annotation and Labeling
Label images using Roboflow Annotate. Upload and export JSON, XML, CSV, and TXT annotation formats.
Image Formats
Upload JPG, PNG, BMP, and TIF image files.
Model-assisted Labeling
Use your Roboflow Train models to accelerate your annotation work by using AI as a starting point to apply labels.
Video Processing
Upload video files and Roboflow will extract frames based on the sample rate you specify. Upload mov, mp4, avi files.
Pre-processing and Augmentation
Augmentation: Random flip, rotate, crop, shear, brightness, exposure, blur, noise, cutout and mosaic.
Generate up to 50 augmented versions of each source image in your dataset. Public Plan users: Generate up to three augmented versions.
Unlimited Datasets
Organize your data, your way. Create as many datasets as you need without worrying about limits.
Unlimited Exports
Choose from 15+ different formats when exporting your training data and refer back to previous versions to track your progress.
Universal Hosting
For each export, get a curl link that can be pasted directly into your notebooks and download from the command line.
Unlimited Data Retention
Keep datasets securely stored and archived indefinitely.
Train/Test Split
Divide your data into sets (train, validate, and test) so you have everything you need to evaluate your model performance after training.

Model Training

Model Understanding & Analytics
Health Check: Detailed statistics and charts containing helpful insights into the quality of your dataset and how to improve it.
Class Balance: View a breakdown of all the classes in your dataset and the number of annotations that appear in each.
Dimension Insights: A dot chart displaying all the sizes of your images along with a breakdown of all the various aspect ratios.
Annotation Heatmap: Displays the location of all the annotations in your dataset so you can see where they are most commonly positioned.
Roboflow Train
Train your model with one click using Roboflow Train. Within 24 hours, you'll get results including mAP, precision, and recall, as well as a hosted API for inference.
Two model types to choose from, to give you options depending on your use cases.
Model Training Tools
Direct integrations with hosted computer vision model training services including Amazon Rekognition, Google Cloud Vision AutoML, Azure Custom Vision.

Hosted Inference

Inference API Access
Hosted API to receive predictions from your model as fast as your network connection can handle sending the frames.
Deploy To The Cloud
Autoscaling infrastructure includes load balancing, supports burst and no burst, and is always on without any custom engineering work.
pip install roboflow
Collect sample inferences whether at specific time intervals, at random, and with different confidence thresholds to improve your model's performance

Edge Deployment

roboflow.js web, NVIDIA Jetson, Luxonis OAK, Mobile (iOS), self-hosting, VPC and on-premise.
Edge Devices
Run your model on embedded devices for drones, robotics, IoT, offline scenarios, and more.
Luxonis OAK
Use Luxonis OAK devices via pip install roboflowoak or via Docker for a standardized device that combines a camera with a built in hardware accelerator
Mobile iOS
Mobile iOS SDK is available for deploying your model directly to an iOS application running on iPhone or iPad.
Optimized it to get maximum performance from the NVIDIA Jetson line of edge-AI devices by specifically tailoring the drivers, libraries, and binaries specifically to its CPU and GPU architectures.
Self-hosting, Enterprise Deployments, and Offline
Deploy our Docker container in your private cloud (or on your own metal) using our Inference Server and our License Server Docker containers. Cache weights for up to 30 days to run completely air-gapped or in locations where an Internet connection is not readily available.

Access & Security

SOC 2 Type 2 Compliant
Roboflow holds SOC 2 Type 2 certification for our security and data privacy standards.
Public Sharing
Autoscaling infrastructure includes load balancing, supports burst and no burst, and is always on without any custom engineering work.
SOC 2 Type 2 Compliant
Share datasets with other members of your team and seamlessly collaborate on projects.


Roboflow Knowledge Base
A comprehensive set of resources to get you started in computer vision with the help of Roboflow’s tools for preparing and managing your datasets.
Roboflow Docs
Developer documentation walking you through how to use Roboflow and how to get the most out of our tools.
Community Help
Can't find the answers you need in our documentation or on the Roboflow Blog? Join the Roboflow forums for help from the Roboflow team and community.
Roboflow YouTube
Helpful tutorials on creating and training models along with interviews with leading computer vision experts.
Priority Support
Your questions and requests will be bumped to the top of the queue and answered by computer vision experts on our team via email and in-app live chat.

Ready To Try Roboflow?