• 6 min read
Narrate the Contents of a Room with Computer Vision
In this guide, learn how to use text-to-speech with computer vision models to narrate the objects in a room.
• 8 min read
How to Deploy a YOLOv8 Model to a Raspberry Pi
In this article, you'll learn how to deploy a YOLOv8 model onto a Raspberry Pi.
• 4 min read
How to Blur a Bounding Box in Python
SUMMARY
Blurring the region inside a detection bounding box is a practical privacy technique for cases where a computer vision model captures sensitive content alongside its target. This tutorial shows how to use OpenCV's cv2.GaussianBlur to extract the region of interest from prediction coordinates and replace it
• 3 min read
How to Draw a Bounding Box Prediction Label with Python
In this article, we show how to use the cv2 library to draw bounding box prediction labels in Python.
• 4 min read
Recap: Roboflow's 12 Days of #Shipmas
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.
• 8 min read
Collective Communication in Distributed Systems with PyTorch
SUMMARY
Multi-GPU neural network training requires moving tensors between processes, and PyTorch's torch.distributed module provides six collective communication strategies to handle this: reduce, all reduce, scatter, gather, all gather, and broadcast. This post covers each strategy with code examples and diagrams, explaining when to use each
• 10 min read
What is an Activation Function? A Complete Guide.
In this article, we discuss what an activation function is, why they are used, and what types of activation functions are commonly used.
• 3 min read
Launch: YOLOv8 Models on Roboflow Universe
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.
• 5 min read
Launch: Deploy YOLOv8 with Roboflow
In this tutorial, we show how to upload your own YOLOv8 model weights to deploy on the Roboflow platform.
• 4 min read
Roboflow Collaborates with Intel to Deliver Next Generation Computer Vision Pipeline for Enterprises
SUMMARY
Roboflow joined the Intel Disruptor Initiative to jointly optimize computer vision software pipelines for Intel hardware, aiming to make production computer vision deployable to more locations and use cases. The collaboration produced RF100, an open-source object detection benchmark spanning 100 projects, 7 imagery domains, 224,714 images, and
• 9 min read
What Is Zero Shot Learning in Computer Vision?
In this article, we discuss what zero-shot learning is, how it works, and when zero-shot learning is and is not useful.
• 4 min read
Launch: Version, Export, and Train Models in the Roboflow Python Package
In this article, we discuss the new version, export, and train model features in the Roboflow pip package.
• 7 min read
How Artificial Intelligence is Influencing Video Production
In this article, learn how Artificial Intelligence is and could create more powerful tools for the video production industry to use.
• 5 min read
Roboflow Changelog: December 2022
Each month, we share a recap of product and company updates. In this post, we detail Roboflow's updates from December 2022.
• 6 min read
HPU vs GPU - Benchmarking the Frontier of AI Hardware
When you are training machine learning models, it is essential to pick hardware that optimizes your models performance relative to cost. In training, the name of the game is speed per epoch – how fast can your hardware run the calculations it needs to train your model on your data.
• 6 min read
Launch: Use Universe Models for Label Assist and Training
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.
• 11 min read
How to Train YOLOv7 Instance Segmentation on a Custom Dataset
In this article, we're going to walk through how to detect concrete cracks using instance segmentation.
• 6 min read
Intel Ice Lake vs Sapphire Rapids on AWS
This guide compares the Intel c6i Ice Lake and Sapphire Rapids AWS Instance against three other common AWS GPU instances.
• 17 min read
Monitor Movement in Retail Stores with Computer Vision
In this article, we walk through how to monitor movement in areas of a retail store using computer vision
• 4 min read
Launch: Collaborative Annotation Updates
SUMMARY
Roboflow's Collaborative Annotation platform has reached over 100,000 users and 100 million annotated images, and this launch adds several features that reduce manual overhead for large teams. New capabilities include API endpoints for uploading batches and assigning annotation jobs programmatically, aggregate batch metrics in the Board
• 7 min read
What is Semi-Supervised Learning? A Guide for Beginners.
In this post, we discuss what semi-supervised learning is and walk through the techniques used in semi-supervised learning.
• 8 min read
Computer Vision Assisted Structural Damage Inspection Using Drones
In this post, Timothy Malche walks through how to inspect structural damage with computer vision and drones.
• 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
SUMMARY
Roboflow and Ultralytics HUB now support a direct integration that connects dataset management with model training and model-assisted labeling. Users can export any Roboflow dataset to Ultralytics HUB for custom YOLOv5 training, then bring the trained model weights back into Roboflow to power Label Assist for annotating under-
Stay Connected