• 2 min read
Microsoft Research and Roboflow Partner for CVPR 2023 Workshop and Challenge
Roboflow will be partnering with Microsoft to run a challenge oriented around the Roboflow 100 benchmark and a workshop at CVPR.
Blog
Trevor Lynn
Trevor leads Marketing at Roboflow. He focuses on sharing insights from Roboflow customers to inspire the broader AI community and help advance visual AI.
Latest Posts by Trevor Lynn
• 3 min read
Roboflow Collaborates with Intel to Deliver Next Generation Computer Vision Pipeline for Enterprises
Roboflow joined the Intel Disruptor Initiative to push the limits of innovation in real-world computer vision applications. Roboflow and Intel are working together to democratize access to computer vision by optimizing computer vision software pipelines to operate at the highest level of performance with Intel hardware.
Collaborative Engineering and Technology
• 4 min read
Launch: Collaborative Annotation Updates
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 images and today we are excited to share
new updates that will help teams speed up their annotation and data
• 2 min read
Launch: Roboflow Notebooks Repo Integration with SageMaker Studio Labs
Learn how to use notebooks in the Roboflow Notebooks repository with AWS SageMaker Studio Lab.
• 3 min read
Launch: Roboflow Integration with Ultralytics HUB
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 use custom trained model weights for model-assisted data labeling in Roboflow.
This integration builds on the established relationship of Roboflow
• 7 min read
School Bus Detection Using YOLOv5 (Tutorial – Part 2)
Learn how to detect school buses using YOLOv5.
• 4 min read
Launch: Semantic Segmentation for Labeling, Training, Deployment
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 of instance segmentation, offers users an additional image segmentation project type to build computer vision pipelines with Roboflow.
What is
• 3 min read
Launch: Cloning Images from Open Source Datasets
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 to
democratize access to computer vision and when it comes to building vision
applications, gathering data for training vision models
• 2 min read
Roboflow Joins AWS Global Startup Program and Becomes AWS ISV Accelerate Partner
Roboflow is on a mission to democratize computer vision and Amazon Web Services
(AWS) powers Roboflow’s model pipeline, which allows us to put computer vision
into the hands of all developers. Roboflow is available in the AWS Marketplace
[https://blog.roboflow.com/roboflow-aws-marketplace/] and committed to serving
enterprise customers
• 3 min read
Launch: Use YouTube Videos for Training Data and Inference Testing
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 of the model.
As of today, Roboflow is making that easier for all users by supporting YouTube
video links for
• 3 min read
Launch: Smart Polygon Labeling
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 datasets.
Polygon annotations [https://blog.roboflow.com/polygon-annotation-labeling/] are
critical to prepare datasets for training instance segmentation
[https://blog.roboflow.
• 9 min read
How to Train YOLOv5 Instance Segmentation on a Custom Dataset
Learn how to train a YOLOv5 instance segmentation model on a custom dataset.
• 2 min read
Roboflow now available in the AWS Marketplace
Roboflow’s end-to-end computer vision platform [https://roboflow.com/] is
transforming the way businesses use computer vision and now you can get
Roboflow
through the AWS Marketplace
[https://aws.amazon.com/marketplace/pp/prodview-ic7o6cr7dmp3k?sr=0-1&ref_=beagle&applicationId=AWSMPContessa]
, making it easier to purchase for AWS customers.
• 7 min read
WTF COCO - The Weird Images that Underpin Modern Computer Vision Models
COCO [https://blog.roboflow.com/coco-dataset/] is an industry standard dataset
for benchmarking the performance of object detection models. The dataset was
created by "gathering images of complex everyday scenes containing common
objects in their natural context" and contains image annotations in 91
categories, with over 1.5
• 8 min read
How to Train YOLOv5-Classification on a Custom Dataset
Learn how to train a YOLOv5 classification model on a custom dataset.
• 6 min read
Launch: Dataset Search
Learn how to search image datasets using Roboflow.
• 1 min read
What is TensorFlow Lite?
TensorFlow Lite [https://www.tensorflow.org/lite], often referred to as TFLite,
is an open source library developed by Google
[https://developers.googleblog.com/2017/11/announcing-tensorflow-lite.html] for
deploying machine learning models to edge devices. Examples of edge deployments
would be mobile (iOS/Android), embedded, and on-device. You can
• 3 min read
Launch: Search Datasets and Assign Jobs
Roboflow Annotate [https://docs.roboflow.com/annotate] has been used to label
over 66 million images and as teams collaborate to manage large datasets
[https://blog.roboflow.com/annotation-workflow/], it’s important to find the
right data for labeling and improving your model.
Teams using active learning [https://blog.roboflow.
• 1 min read
What is TensorFlow?
Learn what TensorFlow is and how it can be used for computer vision.
• 4 min read
Open source datasets and pre-trained models for computer vision
90,000 Datasets and 7,000 Pre-trained Models Available
Roboflow Universe [https://universe.roboflow.com/] launched in August 2021 with
50 open source datasets and opened our computer vision infrastructure products
for free with a Public plan [https://roboflow.com/pricing]. Universe now has
90,000+ datasets with 66+ million
• 1 min read
What is cuDNN?
NVIDIA CUDA Deep Neural Network (cuDNN) is a GPU-accelerated library of
primitives for deep neural networks. cuDNN [https://developer.nvidia.com/cudnn]
is built on top of the CUDA [https://blog.roboflow.com/what-is-cuda/] framework
which is how you use NVIDIA GPUs for general purpose computing tasks. High
performance GPU
• 3 min read
Launch: Label Only Role-based Access Control
Roboflow Annotate [https://roboflow.com/annotate] has been used to label over 66
million images and teams have been able to label more images with our recent
release of collaborative workflows
[https://blog.roboflow.com/annotation-workflow/] for managing labeling in
real-time across distributed teams. Market researchers believe that by 2028,
Stay Connected