Roboflow Changelog: February 2022

Even though it's the shortest month of the year, we accomplished a lot! Each month, we share a recap of product and company updates; if you missed last month's edition of the Roboflow Changelog, you can find it here.

Roboflow Organize

• Polished and improved the new collaborative annotation workflow
• Improvements to tutorial & invitation flow
• Inference Widget is now available to use on trained versions of your datasets
• Enabled annotation via API (opens in a new tab) to work with new annotation flow

Roboflow Train and Deploy

• Released an improved model for Roboflow Train (opens in a new tab)
• You can now select whether you want to optimize for Speed or Accuracy when training
• Our REST API & PIP package can now access public projects from Universe
• Improved Server Benchmark repo (opens in a new tab) to use the API for dataset loading and calculate mAP

Roboflow Universe (opens in a new tab)

• Enhanced loading speed
• Improved auth and inference flow for logged out users
• Added a form to request specific projects be created or added

Other

• Launched the Roboflow Forum (opens in a new tab) (join for great Roboflow and computer vision discussion daily!)
• Product team traveled to Minneapolis to do Q2 planning.
• Sales team had an on-site in Salt Lake City for training.
• Attended ProductCon (opens in a new tab).
• Added 2 new team members.
• Opened several positions in marketing and engineering (come help us democratize computer vision!)
• Improved our internal process for reporting and communicating bugs
• 28 bug fixes
• 4 new Universe projects (opens in a new tab)
• 6 blog posts
• 1 YouTube video (opens in a new tab)
• Featured in/by: YC Top Companies (opens in a new tab), Science Direct (opens in a new tab), Martian Chronicles (opens in a new tab), Tweet from CPO of Adobe (opens in a new tab), Nakashima (opens in a new tab), Mohammed Ismail (opens in a new tab)
• User projects: Counting Teslas (opens in a new tab), Thermal Images (opens in a new tab), Detecting and Counting Bacteria (opens in a new tab), Deep Learn Me (opens in a new tab), Deep Learning-Based Object Detection and Scene Perception under Bad Weather Conditions (opens in a new tab), Suspicious Object Detection in Environments with Tear Gas (opens in a new tab), Computer Vision with Deep Convolutional Neural Network Approach for Cold-Flow Casting Defect Detection (opens in a new tab), A Pipeline Approach to Context-Aware Handwritten Text Recognition (opens in a new tab), A Novel Road Maintenance Prioritization System Based on Computer Vision and Crowdsourced Reporting (opens in a new tab), DRONET: Multi-Tasking Framework for Real-Time Industrial Facility Aerial Surveillance and Safety (opens in a new tab), Localization and Edge-Based Segmentation of Lumbar Spine Vertebrae to Identify the Deformities Using Deep Learning Models (opens in a new tab), Object Detection on Custom Dataset in 3 Simple Steps Using YOLOv5 (opens in a new tab)