Roboflow Blog

25 Jul 2021 • 9 min read

Experimenting with CLIP and VQGAN to Create AI Generated Art

SUMMARY Combining OpenAI's CLIP model with VQGAN allows a generative network to be steered toward a text prompt by using CLIP as a scoring signal during image generation, replicating some of the behavior behind DALL-E before that model was publicly released. This post documents a series of

21 Jul 2021 • 2 min read

Announcing On-Prem and Offline Mode for Roboflow Deploy

SUMMARY Organizations handling sensitive data such as private healthcare images, security camera feeds, or classified infrastructure footage need computer vision inference to stay inside their private networks. Roboflow's on-premise inference server runs as a Docker container inside a private cloud or on dedicated hardware, requires only a

19 Jul 2021 • 3 min read

Using Computer Vision to Clean the World's Oceans

SUMMARY Researchers from CSU Monterey Bay, The Ocean Cleanup, and UC San Diego built a computer vision model to detect underwater plastic debris for autonomous underwater vehicles. Using a 3,200-image dataset collected from real California field sites and annotated with Roboflow, the team compared YOLOv4, YOLOv4-tiny, and

16 Jul 2021 • 4 min read

5 Reasons to not Fully Outsource Labeling

So you're working on building a machine learning model, and you have hit the realization that you will need to annotate a lot of data to build a performant model. In the machine learning meta today, you will be bombarded with services offering to fully outsource your labeling woes.

16 Jul 2021 • 4 min read

Solving the Out of Scope Problem

When we are teaching a machine learning model to recognize items of interest, we often take a laser focus towards gathering a dataset that is representative of the task we want our algorithm to master.

12 Jul 2021 • 11 min read

How AI Protects My Garden from Rabbits

Rabbits were eating all of my vegetables. I decided to take a stand and implement a computer vision enabled system to automatically spook them away from my garden.

8 Jul 2021 • 3 min read

Announcing Image Classification Support, End to End

We are excited to announce full support for image classification in Roboflow, from image collection and organization, to annotation, to custom training, and deployment.

7 Jul 2021 • 7 min read

How Atos Uses Computer Vision to Monitor Office Occupancy

SUMMARY Atos, a digital transformation firm with over 100,000 employees, built a privacy-first office occupancy counter using computer vision and Roboflow, going from initial data collection to a production client demo running on an NVIDIA Jetson Nano in under 60 days. The system connects to existing security camera

5 Jul 2021 • 6 min read

How Your Favorite Brands Are Using Computer Vision

SUMMARY Major consumer brands already embed computer vision throughout the products most people use daily: Apple Face ID uses keypoint detection and instance segmentation on-device, Facebook applies it to generate image alt-text for accessibility, Pinterest powers visual search, and Google organizes photos by recognizing faces and objects. These

4 Jul 2021 • 1 min read

Roboflow Changelog: July 2021

Welcome to this month's installment of the Roboflow Changelog highlighting all the updates we've pushed in the past month. The update for last month can be found here. In June we pushed our major revamp of the backend that supports collaboration between team members ("Workspaces&

2 Jul 2021 • 7 min read

How to Train YOLOR on a Custom Dataset

The YOLO family recently got a new champion - YOLOR: You Only Learn One Representation. In this post, we will walk through how you can train YOLOR to recognize object detection data for your custom use case.

28 Jun 2021 • 3 min read

Choosing the Right Problem Statement

SUMMARY Before picking a model or sourcing images, defining a well-scoped problem statement is the step that determines whether a computer vision project succeeds. A good problem statement is specific (naming exact objects to detect), achievable (accounting for annotation feasibility and domain expertise), and measurable (informing deployment strategy and

28 Jun 2021 • 2 min read

An Introduction to ImageNet

Learn what the ImageNet dataset is, how the dataset is structured, and applications for the dataset.

27 Jun 2021 • 2 min read

Announcing Classification Support for Roboflow Annotate

SUMMARY Roboflow Annotate now supports image classification labeling, expanding the platform beyond its original object detection focus. Teams can upload raw images or folder-organized datasets and assign class labels directly inside Roboflow, with training and deployment support for classification models to follow. This addition makes Roboflow a consistent workflow

21 Jun 2021 • 3 min read

What Is the JAX Deep Learning Framework?

You've probably heard of TensorFlow and PyTorch, and maybe you've even heard of MXNet - but there is a new kid on the block of machine learning frameworks - Google's JAX.

20 Jun 2021 • 5 min read

For the People, By the People

SUMMARY Computer vision models are only as representative as the datasets behind them, and gaps in that data encode real-world bias into deployed systems. This post examines what representative training data means across dimensions like skin tone, accessibility, religion, and gender, drawing on examples from hand detection to pedestrian

16 Jun 2021 • 3 min read

The Joys of Sharing Models on OpenCV's Modelplace

If we could all get together and share our model creation and deployments, that would be a very good thing for the computer vision community. Modelplace is a big step in that direction.

14 Jun 2021 • 6 min read

How to Train MobileNetV2 On a Custom Dataset

In this post, we will walk through how you can train MobileNetV2 to recognize image classification data for your custom use case.

14 Jun 2021 • 7 min read

Building vs. Buying a Computer Vision Platform

SUMMARY Building a computer vision pipeline in-house requires stitching together image upload, annotation, dataset versioning, training, deployment, and active learning, and the result is typically fragile, hard to maintain, and difficult to debug when components break. This post examines seven recurring problems teams encounter when building their own infrastructure,

13 Jun 2021 • 5 min read

How to Train with Microsoft Azure Custom Vision and Roboflow

SUMMARY Teams with existing Microsoft Azure credits can route their Roboflow datasets directly into Azure Custom Vision for training by linking API keys once at the workspace level. After that connection is established, any versioned Roboflow dataset (including preprocessing and augmentation steps applied in Roboflow) can be exported to Azure

6 Jun 2021 • 6 min read

How to Train the Hugging Face Vision Transformer On a Custom Dataset

Learn how to train a Hugging Face Vision Transformer on a custom dataset for classification.

2 Jun 2021 • 1 min read

Roboflow Changelog: June 2021

Each month, we publish a list of recent features and additions to the Roboflow suite of products. The previous month's update is here. In May there has been a bevy of backend changes to support a huge user-facing release coming next month. The most noticeable updates this

30 May 2021 • 6 min read

What Does "End to End" Really Mean?

SUMMARY Building a working computer vision model once required stitching together custom pipelines, cloud services, and ML expertise. Roboflow closes that loop by covering every stage from raw image upload through annotation, dataset versioning, model training, and deployment to a hosted API endpoint, then feeds inference results back as training

27 May 2021 • 6 min read

License Plate Detection and OCR on an NVIDIA Jetson

In this blog, we discuss how to train and deploy a custom license plate detection model to the NVIDIA Jetson. While we focus on the detection of license plates in particular, this guide also provides an end-to-end guide on deploying custom computer vision models to your NVIDIA Jetson on the edge.