Back to blog

Roboflow Changelog: February 2023

Mohamed TraorePublished Mar 3, 2023
8 min read

Each month we share a recap of product and company updates; if you missed the last edition of the Roboflow Changelog, you can find it here.

A note on licensing: YOLOv8 is released under AGPL-3.0, which affects commercial use:

  • On Roboflow cloud: a commercial license is included for every user, including the free plan.
  • Self-hosted: you need an Enterprise license add-on, or you must open-source your application under AGPL-3.0.
  • Permissive alternative: RF-DETR (opens in a new tab) is Apache 2.0, free for commercial use anywhere.

Roboflow Upload, Organize and Annotate

Examples of some of the available statistics and dashboard views in Insights. Viewing images annotated; time spent annotating; boxes drawn; acceptance rate. Filter by dates and by labeler.
Examples of some of the available statistics and dashboard views in Insights
  • Image Comments added to Classification projects (now available on all project types)

Roboflow Train and Deploy

  • How to Deploy Computer Vision Models to Raspberry Pi with Docker
  • My First Jetson Nano Object Detection Inference Server

Roboflow Universe

Face Detection Dataset & API (Roboflow Universe)
Face Detection Dataset & API (Roboflow Universe) (opens in a new tab)
  • Created a new "Wall of Love" to highlight projects from Roboflow Users:
Showcase
Explore computer vision projects created using Roboflow across areas, from reducing food waste to selecting items from computer controls using gestures.
VentureBeat
  • TELS Turkish Earthquake Logistical Support Dataset
Building Finder Dataset and Pre-Trained Model by TELS Turkish Earthquake Logistical Support
1092 open source Buildings images plus a pre-trained Building Finder model and API. Created by TELS Turkish Earthquake Logistical Support
Roboflow
(opens in a new tab)

Roboflow 100

  • RF100 Challenge (opens in a new tab) created in partnership with Microsoft Research and Haotian Zhang of Apple for CVPR2023: "The 2nd Workshop on Computer Vision in the Wild," June 19, 2023.
Link to Tweet (opens in a new tab)
  • Roboflow 100 Eval Server

Tutorials, Open-Source Repositories and Case Studies

  • Launched supervision, a set of easy-to-use utils (e.g object counting and tracking, object tracking and counting in specified regions, video inference) that will come in handy in any Computer Vision project. Track and Count Objects Using YOLOv8
GitHub - roboflow/supervision: A set of easy-to-use utils that will come in handy in any Computer Vision project
A set of easy-to-use utils that will come in handy in any Computer Vision project - GitHub - roboflow/supervision: A set of easy-to-use utils that will come in handy in any Computer Vision project
GitHub | roboflow
(opens in a new tab)

Projects from Blog Contributors

  • AWS Machine Learning
AWS Machine Learning on LinkedIn: How to Use the Stable Diffusion Image-to-Image Pipeline
Learn how you can use the latest image-to-image technology, Stable Diffusion img2img pipeline, to generate more robust computer vision training data using the…
LinkedIn | AWS Machine Learning
(opens in a new tab)
AWS Machine Learning on LinkedIn: AWS Startup Showcase S3 E1
Join us at AWS Startup Showcase! Find out how startups are driving innovations with foundation models and generative AI on #AWS. Leading founders and…
LinkedIn | AWS Machine Learning
(opens in a new tab)
  • Paperspace
Training YOLOv8 on Custom Data
In this blog post, we examine what’s new in Ultralytics awesome new model, YOLOv8, take a peak under the hood at the changes to the architecture compared to YOLOv5, and then demo the new model’s Python API functionality by testing it to detect on our Basketball dataset.
Paperspace Blog | James Skelton
(opens in a new tab)
  • Nature
Annotated Datasets of Oil Palm Fruit Bunch Piles for Ripeness Grading Using Deep Learning - Scientific Data
Scientific Data - Annotated Datasets of Oil Palm Fruit Bunch Piles for Ripeness Grading Using Deep Learning
Nature | Suharjito
(opens in a new tab)

Partnerships

Other

  • Updates to the Roboflow Landing Page
  • Completed the second month of the new "Customer Sprint Weeks." The Roboflow Product Team selects a different customer every month to collect more detailed feedback and insights from, and implements as many of the features as possible in the span of 5-10 business days.
  • Conducted UXR sessions
  • Enhancements to the user onboarding experience (new login page, tutorial activation flow, and workspace plan options)
  • Updated the Roboflow Model Library (opens in a new tab) and Notebooks (opens in a new tab) tutorials repository on GitHub
  • New additions to the Computer Vision Templates and Computer Vision Utilities pages to help users with connecting computer vision models to their required personal or business application
  • New additions to the Roboflow Learn page to aid users with increasing knowledge in the field of computer vision
  • Celebrated 1-year anniversaries for 2 team members
  • Roboflow Lighthouse in Palm Springs, CA

User Projects and Shoutouts

More AboutProduct Updates

View all topicsView more
Get started

Build on the Platform

For developers, engineers, and technical founders who want to get hands on. Try the free tier; the docs are open.

Start buildingView docs (opens in a new tab)

Bring it into your operation

For heads of AI, operations leaders, and enterprise teams. Bring a known problem, or work with us to find the first one worth taking on.

Talk to an expertView customer stories