Blog

Brad Dwyer

Roboflow cofounder and CTO. Building the computer vision infrastructure for developers. Previously founded Hatchlings and created Product Hunt's AR App of the Year.

Latest Posts by Brad Dwyer

training robots to identify other robots

22 Sep 2020 • 3 min read

Training Robots to Identify Other Robots

SUMMARY Amitabha Banerjee trained a computer vision model to teach his Anki Vector robot to detect other robots, addressing a real gap since the Vector's onboard AI handles speech and human recognition but not robot-to-robot identification. He collected 303 images from the robot's own

Y Combinator

25 Aug 2020 • 2 min read

Roboflow Joins Y Combinator's Summer 20 Batch

Roboflow is enabling any developer to use computer vision (without being a machine learning expert). Computer vision is the first technology that fundamentally allows us to rewrite human-computer interaction. Until now, when using computers to interact with the world, humans would assess their environment, provide commands to a computer,

rekognition

24 Aug 2020 • 1 min read

Video: How to Use Amazon Rekognition Custom Labels with Roboflow

SUMMARY This webinar recording from Roboflow and AWS Premier Consulting Partner Onica covers the full pipeline for training and deploying a custom mask detection model using Roboflow for dataset preparation and AWS Rekognition Custom Labels for training and hosting. The session goes end to end from raw images to a

website

21 Aug 2020 • 3 min read

The crazy story of how we got our .com domain

For almost a year, Roboflow (our computer vision dataset management tool) has lived at roboflow.ai. It's served us well but we have always lusted after the dot com. No longer! We managed to acquire roboflow.com from the giant German company that owned it since 2001. The

Ontology Management for Computer Vision

3 Aug 2020 • 5 min read

Ontology Management for Computer Vision

SUMMARY Choosing class names at the start of a computer vision project and then needing to change them later is one of the most time-consuming parts of iterating on a dataset. This post covers practical ontology management strategies: labeling at the most specific level possible so classes can be

Advanced Augmentations in Roboflow

29 Jul 2020 • 2 min read

Advanced Augmentations in Roboflow

SUMMARY Roboflow added two augmentations to its platform, Mosaic and Cutout, that were central to accuracy gains in recent detection model research. Mosaic combines four training images into one, simulating random crops, mixing classes that rarely appear together, and varying object counts per image. Cutout overlays randomly placed black boxes

Roboflow can now ingest video!

23 Jul 2020 • 1 min read

Roboflow can now ingest video!

SUMMARY Roboflow now accepts video file uploads directly, removing the manual step of extracting frames with command-line tools. Users select a sample rate to pull a subset of frames from the video, then annotate those frames using Roboflow's integrated labeling tools or by outsourcing the job in

vs scale

5 Jul 2020 • 1 min read

Roboflow vs Scale

SUMMARY Roboflow and Scale serve different stages of the computer vision pipeline: Scale and similar services (LabelBox, SuperAnnotate, SageMaker Ground Truth) handle outsourced annotation, while Roboflow takes over after labeling to manage preprocessing, augmentation, dataset versioning, and training integrations. Roboflow imports annotations directly from most of these services, and its

Introducing the Roboflow Model Library

28 Apr 2020 • 1 min read

Introducing the Roboflow Model Library

SUMMARY The Roboflow Model Library brings together 7 open source object detection models and 3 classification models in one place, each accessible via GitHub, a downloadable Jupyter notebook, or Google Colab with free GPU access. All notebooks integrate directly with Roboflow, so datasets uploaded and annotated on the platform can

pioneer leaderboard post

20 Feb 2020 • 3 min read

How to Win Pioneer

SUMMARY Roboflow held the number one spot on the Pioneer.app global leaderboard for 18 consecutive weeks by following a consistent discipline: set concrete, completable goals each Sunday (not open-ended ones like "continue X"), then exceed them by focusing on controllable inputs rather than unpredictable outputs like

dataset

11 Feb 2020 • 2 min read

A popular self-driving car dataset is missing labels for hundreds of pedestrians

SUMMARY A hand-check of the 15,000 images in the widely used Udacity Dataset 2 found problems in 4,986 of them (33%), including thousands of unlabeled vehicles, hundreds of unlabeled pedestrians, dozens of unlabeled cyclists, and 217 completely unannotated images that contained real objects. Phantom annotations, duplicated bounding

Stay Connected

Get the Latest in Computer Vision First