Roboflow Blog

8 Oct 2021 • 1 min read

New Feature: Isolate Objects

You can now export the bounding boxes from your object detection dataset as cropped images usable with classification models. This update will enable easily prototyping two-pass models for use-cases like OCR and object tracking. To try it out, simply enable the Isolate Objects preprocessing step and generate a new version

7 Oct 2021 • 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

5 Oct 2021 • 2 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.

3 Oct 2021 • 1 min read

Roboflow Changelog: October 2021

Our emphasis this month was on "code tentacles," or improving the ways that Roboflow integrates with your codebase. Below is a recap of what we launched and improved. Rewind to last month's (September 2021) changelog for a recap of earlier releases. Roboflow Organize * Released our REST

30 Sep 2021 • 2 min read

Roboflow and Ultralytics Partner to Grow Computer Vision Community

We're proud to share that Roboflow has entered into a partnership agreement with Ultralytics allowing Roboflow to license Ultralytics models and become the official dataset management and annotation tool for Ultralytics. This means Roboflow is an authorized licensor of Ultralytics YOLO models and is permitted by Ultralytics to

30 Sep 2021 • 4 min read

Making a Handheld Card Counter on the OAK-D-Lite

The portability of the OAK-D-Lite gives us the power to bring computer vision powered solutions anywhere on earth - including your local casino!

27 Sep 2021 • 2 min read

Deploying Computer Vision Models as Mircroservices

Roboflow's philosophy around MLOps revolves around treating your computer vision model as a microservice. The reasons for this are myriad; in this post we highlight the benefits of this approach and how it works in practice. Why Microservices? Separation of Concerns The primary motivation behind deploying your model

22 Sep 2021 • 1 min read

What is PaddlePaddle?

"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us. What is PaddlePaddle (in 60 Seconds or Fewer)? You likely ended up on this post because you Googled "PaddlePaddle machine learning" or "PaddlePaddle Baidu.

20 Sep 2021 • 1 min read

What is PyTorch?

"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us. What is PyTorch (in 60 Seconds or Fewer)? PyTorch is Facebook's open source machine learning framework. It was popularized in research in academia, but increasingly

20 Sep 2021 • 4 min read

How I Used Computer Vision to Make Sense of My Fridge

As part of a groupwork for a postgraduate applied AI at Erasmus Brussels we made an object detection model to identify ingredients in a fridge.

16 Sep 2021 • 3 min read

We Raised a $20M Series A to Continue Democratizing Computer Vision

Today, Roboflow is excited to announce our $20 million Series A led by Craft Ventures to expand on our mission to give software the sense of sight. Lachy Groom, who co-led the seed with Craft, also participated in the round. Additionally, we welcomed new investment from leaders like Jack Altman,

15 Sep 2021 • 1 min read

Introducing the Roboflow pip package

We're ecstatic to announce the launch of our newest pip package, a way for you to natively interface with your Roboflow workspace through your Python scripts and Jupyter notebooks! Read the full package documentation here. Your API Key If you've ever used our Upload API or

9 Sep 2021 • 3 min read

What is TensorRT?

"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us. What is TensorRT (in 60 Seconds or Fewer)? TensorRT is a machine learning framework that is published by Nvidia to run inference that is machine learning inference

6 Sep 2021 • 3 min read

How to Implement Object Tracking for Computer Vision

This post is a comprehensive guide on how to implement object tracking with your object detection model to track your custom objects

2 Sep 2021 • 2 min read

Our New REST API

Today we're excited to announce the launch of our new REST API, a way for your code to interface with the information stored in your Roboflow workspace. Read the full API documentation here. We're launching with five read-only API routes (to access commonly used data about

2 Sep 2021 • 1 min read

Roboflow Changelog: September 2021

Welcome to another installment of the Roboflow Changelog where we summarize the improvements to Roboflow's product suite over the preceding month. You can find the last changelog (for August 2021) here. The biggest highlights from last month were celebrating the release of Roboflow Universe, our community space for

30 Aug 2021 • 1 min read

What is Amazon Rekognition?

"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us. What is Amazon Rekognition (in 60 Seconds or Fewer)? Amazon's Rekognition is Amazon's off-the-shelf computer vision API for understanding the contents of images.

29 Aug 2021 • 1 min read

Live Coding: Blackjack Basic Strategy

Follow along as I use a playing cards object detection model from Roboflow Universe to build a computer-vision powered Blackjack basic strategy web-app. In just two hours, we go from the boilerplate sample code to a working app you can try on your phone or computer's webcam. If

23 Aug 2021 • 3 min read

What is Zero Shot Object Tracking?

We are exciting to announce that you can now track objects frame over frame in video and camera stream using the Roboflow Inference API and the open source zero shot object tracking repository, without having to train a separate classifier for your object track features.

19 Aug 2021 • 5 min read

ImageNet contains naturally occurring NeuralHash collisions

NeuralHash is the perceptual hashing model that back's Apple's new CSAM (child sexual abuse material) reporting mechanism. It's an algorithm that takes an image as input and returns a 96-bit unique identifier (a hash) that should match for two images that are "the

18 Aug 2021 • 3 min read

Mitigating the Collision of Apple's CSAM NeuralHash

This morning, Hacker News was ablaze with several stories about vulnerabilities in Apple's CSAM NeuralHash algorithm. Researchers had found a way to convert the NeuralHash model to ONNX format and reverse engineer a hash collision (in other words: they created an artificial image with the same hash as

16 Aug 2021 • 1 min read

What is CoreML?

"ML in a Minute" is our conversational series on answering machine learning questions. Have questions you want answered? Tweet at us. What is CoreML (in 60 Seconds or Fewer)? CoreML is Apple's machine learning framework for doing on device inference. When you're doing on

11 Aug 2021 • 3 min read

Roboflow Universe: the Computer Vision Community

We’re excited to introduce Roboflow Universe, the new hub for computer vision datasets and pre-trained models.

7 Aug 2021 • 1 min read

Roboflow Changelog: August 2021

Each month we share a recap of our monthly updates and releases in the Roboflow Changelog. The previous Changelog is available here. In July, the product team's major emphasis was on a new product we'll be releasing at our Launch Party on Wednesday, August 11 -