Team Roboflow decided to end 2022 strong and kick off 2023 with a bang by shipping 12 new features in 12 days. Updates were made to model-assisted labeling, model training, annotation tools, the REST API, Python SDK, and more.
Pre-trained YOLOv8 models are available for testing and deployment on Roboflow Universe. Test and Deploy YOLOv8 Object Detection models in the app through the Models page.
In this guide, learn how to use public models on Roboflow Universe to assist you with labeling and to speed up the process of building an accurate model.
Roboflow’s Collaborative Annotation
[https://blog.roboflow.com/annotation-workflow/] and Label Only User
[https://blog.roboflow.com/labeler-access/] features have helped over 100,000
users annotate more than 100 million
The Roboflow Notebooks GitHub repo [https://github.com/roboflow-ai/notebooks]
contains over 20 open source computer vision notebooks with step-by-step guides
on using 13 different computer vision model architectures. Along
Ultralytics, the creators of YOLOv5, and Roboflow now support an integration making it easier to import YOLOv5 models from HUB to Roboflow, export datasets to Ultralytics HUB from Roboflow, and
The Roboflow CLI will improve workflows and the ability to use Roboflow when
building computer vision applications.
You can use the new Roboflow CLI to access information about your workspaces
Roboflow now supports semantic segmentation projects end-to-end allowing you to use Roboflow Annotate to label data, Roboflow Train to build models, and Roboflow Deploy for inference.
This release, alongside support
Since its launch in August 2021, Roboflow Universe has become the largest
collection of open source datasets and pre-trained computer vision models
[https://blog.roboflow.com/computer-vision-datasets-and-apis/]. Our goal is
When building a computer vision application from scratch, two of the most time
consuming parts of the process are finding data to train the model and quickly
testing the performance
Roboflow Annotate [https://roboflow.com/annotate] now offers automated polygon
labeling for all users. With as few as one click, you can apply a polygon
annotation to objects in your
Roboflow has extensive deployment options [https://roboflow.com/deploy] for
getting your model into production. But, sometimes, you just want to get
something simple running on your development machine.
If
Roboflow Annotate has been used to manage and label 90,000 datasets containing 66 million images and starting today you can now use text based search queries to better understand
💡Roboflow Inference, which you can use to deploy models to a Raspberry Pi, is now available as an open source project.
We recommend following the Roboflow Inference documentation to set
Answering the question "how do I deploy a computer vision model?" can be
difficult. There are so many options. Which one should you choose? How do you
deploy to the
Roboflow supports tiling during training as a pre-processing step to train
models to detect small objects in large images
[https://blog.roboflow.com/detect-small-objects/], and now you can also use
