Overview

Steps to building a computer vision model on Roboflow
About
Roboflow empowers developers to build their own computer vision applications, no matter their skillset or experience. We provide all of the tools needed to convert raw images into a custom trained computer vision model and deploy it for use in applications. Today, Roboflow supports object detection and classification models. 
Roboflow can be used to:
​Annotate images or upload existing annotations
​Convert existing VOC XML annotations to COCO JSON annotations​
See if labels are in-frame (and one-click correct them if they are not)
​Preprocess images: resizing, grayscale, auto-orientation, contrast adjustments
​Augment images to increase your training data: flip, rotate, brighten / darken, crop, shear, blur, and add random noise
​Generate annotation formats like TFRecords, CreateML and Turi Create, and custom YOLOv3 implementations (flat text files or Darknet)
​Quickly assess your dataset quality​
Share version-controlled datasets with your team
Easily use data across models built in Tensorflow, PyTorch, fast.ai, Keras, and more
​Train models in one click​
​Deploy models as an infinitely scalable API, to an edge device, or to a web browser.
​Obtain and share public datasets​
Consider our Getting Started Guide for more

Quick Start

Last modified 1mo ago

Copy link

Contents

About