Blog

Joseph Nelson

Roboflow cofounder and CEO. On a mission to transform every industry by democratizing computer vision. Previously founded and sold a machine learning company.

Latest Posts by Joseph Nelson

atos

7 Jul 2021 • 7 min read

How Atos Uses Computer Vision to Monitor Office Occupancy

Building & deploying a privacy-first model to the edge with Roboflow in 60 days The COVID-19 pandemic changed how and where we work. Fortunately, in some countries, the pandemic appears to be nearing its final act. As companies around the globe make measured decisions regarding returning to the office, keeping

13 Jun 2021 • 4 min read

How to Train with Microsoft Azure Custom Vision and Roboflow

Roboflow is a tool for building robust machine learning operations pipelines for computer vision: from collecting and organizing images, annotating, training, deploying, and creating active learning pipelines to rapidly create improved model performance. When it comes to the training step, developers should optimize for ease. Roboflow Train enables teams to

How Computer Vision Streamlines Risk Avoidance Workflows in Oil & Gas

19 May 2021 • 6 min read

How Computer Vision Streamlines Risk Avoidance Workflows in Oil & Gas

The below is a guest post by Douglas Long [https://www.linkedin.com/in/doug-long-yyc/], a full stack developer in Calgary, Canada. Douglas previously worked in oil and gas. In the oil and gas industry, providing advanced notification for the development of energy infrastructure is a regulatory requirement. New pipelines

Prompt Engineering: The Magic Words to using OpenAI's CLIP

17 May 2021 • 4 min read

Prompt Engineering: The Magic Words to using OpenAI's CLIP

Featuring rock, paper, scissors. OpenAI's CLIP model [https://models.roboflow.com/classification/clip] (Contrastive Language-Image Pre-Training) is a powerful zero-shot classifier that leverages knowledge of the English language to classify images without having to be trained on any specific dataset. In other words, CLIP already knows a lot

Partnering with Luxonis and OpenCV for Seamless Deployment to OpenCV AI Kit

5 May 2021 • 3 min read

Partnering with Luxonis and OpenCV for Seamless Deployment to OpenCV AI Kit

Deploying computer vision models to the edge is critical to unlocking new use cases like in places with limited internet connectivity or where minimal latency is essential. That might be deploying to a rural field in agriculture or computer vision in high throughput manufacturing [https://blog.roboflow.com/computer-vision-use-cases-for-manufacturing/]. As

Image Augmentations for Aerial Datasets

26 Apr 2021 • 3 min read

Image Augmentations for Aerial Datasets

Learn how to apply image augmentations to aerial datasets for use in training computer vision models.

Our Favorite Computer Vision Courses

11 Apr 2021 • 3 min read

Our Favorite Computer Vision Courses

A question we frequently receive at Roboflow is, "What is the best class for learning computer vision?" Like most questions, the answer does depend on your background and what you're aiming to learn. Below, we've compiled a few of our favorite courses for learning

ibm watson

4 Apr 2021 • 6 min read

How to Use Roboflow with IBM Visual Recognition (IBM Watson vs Roboflow)

IBM recently announced they are shutting down IBM Visual Inspection, their product for creating custom computer vision models for classification and object detection. No new instances can be created and all current instances will be fully shutdown in December 2021. This has left many looking for IBM Visual Inspection alternatives.

embedded machine learning and embedded ai systems

20 Mar 2021 • 4 min read

What Is Embedded Machine Learning?

Machine learning – the software discipline of mapping inputs to outputs without explicitly programmed relationships – requires substantial computational resources. Traditionally, this limits where machine learning models can run to very powerful supercomputers. But this is changing. Computation is required at two core moments in the machine learning development lifecycle: model training

14 Mar 2021 • 8 min read

How We Built Paint.wtf, an AI Game with 150,000+ Submissions that Judges Your Art

Paint.wtf is an online game that uses AI to score user-submitted digital drawings to zany prompts like, "Draw a giraffe in the arctic" or "Draw a bumblebee loves capitalism." It's Cards Against Humanity meets Microsoft Paint. Paint.wtf became an internet sensation. In

8 Feb 2021 • 4 min read

Using Computer Vision to Help Win $1 Million in Mountain Dew's Big Game Contest

Last night during Super Bowl LV, Mountain Dew ran an ad featuring John Cena riding through a Mountain Dew-themed amusement park. Bottles are scattered all over the scene: neon signs on buildings, in fun house mirrors, and flying out of the car trunk. At the end of the ad, John

How to Train and Deploy a License Plate Detector to the Luxonis OAK

8 Feb 2021 • 7 min read

How to Train and Deploy a License Plate Detector to the Luxonis OAK

In this post, we will leverage Roboflow and the Luxonis OAK to train and deploy a custom license plate model to your OAK device.

Teams for All: Create Free Teams on Roboflow

17 Jan 2021 • 2 min read

Teams for All: Create Free Teams on Roboflow

Machine learning is a team sport, and getting a computer vision model to production is no exception. All parts of the process are improved with a team: collecting data from multiple sources; annotating data with colleagues; sharing versioned datasets; and using deployed models. We're pleased to introduce free

transfer

13 Jan 2021 • 4 min read

A Primer on Transfer Learning

Transfer learning is a machine learning (ML) technique where knowledge gained during training a set of problems can be used to solve other related problems. It’s very similar to the concept of reusing code in computer programming, except instead of sharing code between different applications or software projects, we’

seed

12 Jan 2021 • 2 min read

Announcing Roboflow’s Seed Round

Computer vision is a generational technology. Like the PC, internet, and mobile phones, computer vision’s impact will reshape every industry. In transportation, for example, the advent of machine vision gives rise to self-driving cars, rewiring how we navigate the world around us. Manufacturing companies are finding and reducing visual

How To Annotate Images with Your Team Using Roboflow

25 Dec 2020 • 3 min read

How To Annotate Images with Your Team Using Roboflow

Dataset annotation is better with teams: you can move more quickly, keep everyone on the same page, track annotation progress, and easier provide examples of what the ultimate dataset should look like. In this post, we'll walkthrough an example workflow of annotating data with your team using Roboflow

Share Your Datasets with the Computer Vision Community

6 Dec 2020 • 1 min read

Share Your Datasets with the Computer Vision Community

Computer vision problems start with finding high quality image datasets. Fortunately, access to common image data is increasingly easier. Datasets like Microsoft's COCO dataset [https://blog.roboflow.com/coco-dataset/] and the Pascal VOC dataset [https://public.roboflow.com/object-detection/pascal-voc-2012] provide a standard for common objects and measuring

Scaled-YOLOv4 is Now the Best Model for Object Detection

3 Dec 2020 • 8 min read

Scaled-YOLOv4 is Now the Best Model for Object Detection

(based on Microsoft COCO benchmarks) The object detection space remains white hot with the recent publication of Scaled-YOLOv4 [https://arxiv.org/abs/2011.08036], establishing a new state of the art in object detection [https://blog.roboflow.com/object-detection/]. Looking to train a Scaled-YOLOv4 model? Skip this post and jump

computer vision for street murals

15 Nov 2020 • 4 min read

Bringing Street Murals to Life with Computer Vision

In Bedford–Stuyvesant, Brooklyn (BedStuy), Yuri Fukuda regularly walks by a mural that showcases prominent female leaders. Since October 2005, a stunning 3,300 square foot mural, When Women Pursue Justice by ArtMakers-NYC, has had a central place in the BedStuy art scene. The mural celebrates 90 women who have

Hands on with the Roboflow Infer Web Application Interface Builder

8 Nov 2020 • 3 min read

Hands on with the Roboflow Infer Web Application Interface Builder

After you train a model with Roboflow Train [https://docs.roboflow.com/train], you're provided with three immediate ways to use your model: a curl command, the direct URL, and an Example Web App. In this post, we'll demonstrate hands on how to use the web

Evaluating Object Detection Models with mAP by Class

3 Nov 2020 • 3 min read

Evaluating Object Detection Models with mAP by Class

When evaluating an object detection model in computer vision, mean average precision [https://blog.roboflow.com/mean-average-precision/] is the most commonly cited metric for assessing performance. Remember, mean average precision is a measure of our model's ability to correctly predict bounding boxes at some confidence level – commonly mAP@

How to Use the Detectron2 Model Zoo (for Object Detection)

1 Nov 2020 • 3 min read

How to Use the Detectron2 Model Zoo (for Object Detection)

Detectron2 is Facebook's open source library for implementing state-of-the-art computer vision techniques in PyTorch. Facebook introduced Detectron2 [https://ai.facebook.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/] in October 2019 as a complete rewrite of Detectron (which was implemented in Caffe). Facebook uses Detectron2 in a wide array of their products, including

protect endangered species

30 Oct 2020 • 5 min read

How This Fulbright Scholar is Using Computer Vision to Protect Endangered Species

The below post is by Kasim Rafiq, a conservationist, Fulbright Scholar, and National Geographic Explorer studying at UC Santa Cruz. Kasim holds a PhD in Wildlife Ecology from Liverpool John Moores University. Introduction Nature underpins everything. From our global economy to our wellbeing and survival. Everything relies on nature. Unfortunately,

Train Test Split Guide and Overview

28 Oct 2020 • 2 min read

Train Test Split Guide and Overview

In order to ensure our models are generalizing well (rather than memorizing training data), it is best practice to create a train, test split. That is, absent rigor, our models can easily overfit to a small subset of examples we've collected. Look no further than Tesla using computer

Stay Connected

Get the Latest in Computer Vision First