• 6 min read
Precision and Recall in Machine Learning
Learn what precision and recall are and why they are important in computer vision.
• 2 min read
Testing A Computer Vision Model In 10 Seconds Or Less
Learn how to test your computer vision model with Roboflow.
• 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,
• 6 min read
Identifying Chocolates With Computer Vision
Learn how to identify chocoaltes using computer vision technology.
• 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
• 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
• 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
• 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.
• 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
• 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.
• 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.
• 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 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 min read
Who cares about Nemo, let's find some Sexy Shrimp!
Creating a computer vision model with Roboflow to detect sexy shrimp.
• 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 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
• 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,
• 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.
• 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
• 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
• 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.
• 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-
• 7 min read
Engineer's Guide to Figma
Your designer sent over a url that begins with figma.com and asks you to take a look at their latest work. What is Figma, you wonder as you click through a series of screens, and how can I learn more about it? Wonder no more — you’ve come to
• 3 min read
How to Safely Install OpenCV on the Mac M1
Installing OpenCV on the M1 safely is difficult because the M1 operates on an arm64 architecture and most of your python libraries are compiled for amd64. Open this guide to avoid your otherwise inevitable demise.
Stay Connected