Latest Posts

8 Mar 2022 • 5 min read

Building a U.S. License Plate Detection Model And Sharing It On Roboflow Universe

SUMMARY This post walks through building a U.S. license plate detection model trained with Roboflow, achieving 94.9% mAP, 95.7% precision, and 90.4% recall on images collected from Google and Central Florida locations. The workflow covers annotation, preprocessing with auto-orient and resize, augmentations tuned for occlusion

7 Mar 2022 • 2 min read

Roboflow Changelog: February 2022

Even though it's the shortest month of the year, we accomplished a lot! Each month, we share a recap of product and company updates; if you missed last month's edition of the Roboflow Changelog, you can find it here. Roboflow Organize * Polished and improved the new

3 Mar 2022 • 6 min read

Precision and Recall in Machine Learning

Learn what precision and recall are and why they are important in computer vision.

23 Feb 2022 • 2 min read

Testing A Computer Vision Model In 10 Seconds Or Less

Learn how to test your computer vision model with Roboflow.

14 Feb 2022 • 5 min read

How To Avoid Bias In Computer Vision Models

SUMMARY Bias in a computer vision model is the average error that persists after training, and it almost always traces back to data quality rather than model architecture. The practical mitigation steps covered here include collecting large and representative datasets, using active learning to surface gaps, running model error analysis,

9 Feb 2022 • 6 min read

Identifying Chocolates With Computer Vision

Learn how to identify chocoaltes using computer vision technology.

7 Feb 2022 • 7 min read

How to Train Computer Vision Models on Aerial Imagery

SUMMARY Aerial imagery from drones and planes presents distinct challenges for computer vision: small objects have few pixels to form features from, large image sizes slow training and inference, and orientation bias can mislead models. This post walks through the full pipeline for building a custom model on aerial data

4 Feb 2022 • 1 min read

Roboflow Changelog: January 2022

It might be cold outside, but Roboflow is bringing the heat to kick off 2022! Each month, we share a recap of product and company updates. If you missed last month's edition of the Roboflow Changelog, you can find it here. Roboflow Organize * Major update to the Annotations

2 Feb 2022 • 4 min read

Launch: Collaborative Annotations

SUMMARY Roboflow Annotate now supports team-scale annotation workflows with a board view that shows image status at a glance, job assignment to divide work across team members, reviewer notifications, annotator instructions, and a review mode where a second person can approve or reject labeled images before they enter the

18 Jan 2022 • 2 min read

Introducing the Roboflow Universe Dataset Research Internship

We are seeking an intern who would be interested in first-authoring the paper that introduces the Roboflow Universe Datasets.

6 Jan 2022 • 1 min read

Roboflow Changelog: December 2021

Even though the year was coming to a close and holidays gave us the chance to spend time with family and friends, we kept our focus right up to the end in order to make Roboflow even better. Each month, we share a recap of product and company updates to

27 Dec 2021 • 5 min read

SageMaker Studio Lab vs Google Colab

Recently, AWS released SageMaker Studio Lab, its competitor service to Google Colab. I dove into comparing Google Colab to Studio Lab and here is what I found.

22 Dec 2021 • 1 min read

Introducing the Roboflow Inference Widget

Now, you can easily test any model that has been trained with Roboflow Train by dragging an image file onto your dataset version page.

9 Dec 2021 • 5 min read

Florence: A New Foundation for Computer Vision

Microsoft Research recently released the foundational Florence model, setting the state of the art across a wide array of computer vision tasks.

7 Dec 2021 • 7 min read

Remote, Not Distant

As Roboflow has grown, we have put a great deal of effort into creating an unparalleled remote-first workplace. To achieve our goal of empowering every developer to use computer vision, we need to assemble a world class team and put them in an environment where they can thrive. We&

7 Dec 2021 • 7 min read

Who cares about Nemo, let's find some Sexy Shrimp!

Creating a computer vision model with Roboflow to detect sexy shrimp.

3 Dec 2021 • 4 min read

Using Computer Vision to Play Dreidel

As a brand new employee at Roboflow, I was asked to do a computer vision project. So I thought, why not combine a holiday I love so much, Chanukah, with something brand new in my life, Roboflow.

1 Dec 2021 • 1 min read

Roboflow Changelog: November 2021

It's been a whirlwind of a month at Roboflow with lots of changes, updates, and expansion going on behind the scenes. Each month, we share a recap of product and company updates. If you missed last month's edition of the Roboflow Changelog, you can find it

28 Oct 2021 • 4 min read

ReefOS: Supercharging Coral Reef Restoration with AI

SUMMARY Coral Gardeners' ReefOS platform uses computer vision to monitor coral reef health at scale in Mo'orea, replacing time-intensive in-water surveys with underwater cameras connected to cloud servers. The platform trains models on annotated camera footage to track reef and nursery health in real time,

28 Oct 2021 • 4 min read

What is YOLOS? What's New in the Model?

YOLOS - You Only Look At One Sequence is the newest, and potentially most impactful, iteration on the YOLO family of object detection models.

24 Oct 2021 • 4 min read

AI Football Play Generator

SUMMARY Scott Bronkema, a former college football player turned developer, built a computer vision application that automatically identifies player positions and formations at the pre-snap moment and tracks player routes throughout each play, outputting a digital playbook diagram. Built with Roboflow for model training and annotation plus OpenCV for

20 Oct 2021 • 6 min read

Let's Talk About Company Culture

Company culture is a feeling in the air, the social norms of a group, the manifestation of collective goals and beliefs, and the one intangible thing that can make or break a growth stage company. For some, culture becomes a priority too late in the business. It starts to become

13 Oct 2021 • 4 min read

YOLOv5 v6.0 is here - new Nano model at 1666 FPS

With the v6.0 release, YOLOv5 further solidifies its position as the leading object detection model and repository.

8 Oct 2021 • 2 min read

New Feature: Isolate Objects

SUMMARY Roboflow's Isolate Objects preprocessing step lets you export an object detection dataset as a set of cropped bounding-box images, one per annotation, organized by class and ready for use as a classification dataset. Enabling the step at version-generation time makes it practical to prototype two-