Even though the year was coming to a close and holidays gave us the chance to spend time with family and friends, we kept our focus right up to the end in order to make Roboflow even better. Each month, we share a recap of product and company updates to celebrate what we've accomplish and keep you informed; if you missed last month's edition of the Roboflow Changelog, you can find it here.

Roboflow Organize

  • Added an inference usage chart to workspace settings
  • Created a model monitoring framework
  • Added upload retry logic to Python library

Roboflow Train and Deploy

  • Added support for training a faster (smaller) model variant
  • Added multi-gpu training
  • Speed improvements to the backend
  • Integrated Zero Shot Object Tracking with Torch Hub YOLOv5

Roboflow Universe

Other