Getting the Most Out of Roboflow Office Hours

Welcome To Our Office. Come with Questions, Please.

The Roboflow team has been inspired and impressed with what our users are building on top of Roboflow. From making models that improve workplace safety, interpret radiology scans to fight COVID-19, and simply have more fun in quarantine with Uno score keepers, we're excited for you.

To better assist our users with their projects, we're opening our (virtual) office to you with Roboflow Office Hours, an informal time to get help, suggest features, and more. (Subscription users: this does not replace your personalized advice sessions or ability to ask for help at any time.)

Join one of our founders, Joseph Nelson, any Wednesday from 3:00 - 4:00 PM Eastern US on a Zoom call to get the most out of Roboflow. This is a time to gain personalized tips for your problem, including preprocessing / augmentation recommendations, model architecture suggestions, and working through bugs.

To join, simply email joseph.nelson@roboflow.ai for invitation details.

Note, initially, Zoom calls will be open attendance to anyone. They are drop-in on a first-come, first-serve basis. We may record / share office hours with a broader ecosystem. We hope that by sharing the questions we're hearing from many Roboflow users, the community helps one another with their computer vision ideas.

How to Use Office Hours

Office hours are to be used for targeted questions related to computer vision and machine learning. If you have questions about, say, natural language processing, we may be able to offer insight, but your question may also be lower priority.

With that said, here are some tips to getting the most out of office hours:

  1. Attend with a targeted question in mind. For example, "What are the best times to use random crop augmentation?"
  2. Prove you've thought about and researched your question, too. "I've seen random crop is helpful for changing the scale and position of an image. Why does that help our model"
  3. Do not hog the time. If any single user(s) appear to be dominating the conversation to the detriment of other uses, we will not hesitate to provide a warning and, if necessary, ask you to leave office hours.
  4. "I was using Roboflow, and I was wondering how to handle unbalanced classes. What is your recommendation?"

We can't wait to see you there!


Want to be the first to know about new computer vision tutorials and content like our synthetic dataset creation guide? Subscribe to our updates 📬.

Roboflow accelerates your computer vision workflow through automated annotation quality assurance, universal annotation format conversion (like PASCAL VOC XML to COCO JSON and creating TFRecords ), team sharing and versioning, and easy integration with popular open source computer vision models. Getting started with your first 1GB of data is completely free.

Show Comments