• 7 min read
How to Build a Stable Diffusion Image-to-Image Pipeline
In this article, we discuss how to build a Stable Diffusion image generation pipeline using SageMaker Studio Labs, Hugging Face, and Roboflow.
• 16 min read
What is a Convolutional Neural Network?
In this guide, we discuss what a Convolutional Neural Network (CNN) is, how they work, and discuss various different applications of CNNs in computer vision models.
• 13 min read
What is a Transformer?
In this guide, we explore what Transformers are, why Transformers are so important in computer vision, and how they work.
• 6 min read
Deploy Models from Roboflow with the Luxonis DepthAI SDK
The new Luxonis DepthAI SDK Roboflow Integration gives users the option to deploy Roboflow models to OAK devices with more functionality and out-of-the-box options for customization of inferences.
• 6 min read
Roboflow Changelog: January 2023
Each month, we share a recap of product and company updates. In this post, we detail Roboflow's updates from January 2023.
• 4 min read
Track and Count Objects Using YOLOv8
Counting moving objects is one of the most popular use cases in computer vision. It is used, among other things, in traffic analysis and as part of the automation of manufacturing processes. That is why understanding how to do it well is crucial for any CV engineer.
• 6 min read
How to Deploy YOLOv5 Models with Roboflow
In this article, learn how to deploy a computer vision model using custom YOLOv5 weights to Roboflow.
• 7 min read
How to Save Computer Vision Predictions to a Google Sheet
In this guide, we walk through how to save predictions from a computer vision model to a Google Sheet.
• 8 min read
How to Deploy a YOLOv8 Model Using Roboflow and Repl.it
In this guide, we walk through how to train and deploy a YOLOv8 model using Roboflow, Google Colab, and Repl.it.
• 6 min read
Deploy Computer Vision Models to Raspberry Pi with Docker
To follow along with this tutorial, you will need a Raspberry Pi 4 or 400. You will need to run the 64-bit Ubuntu operating system.
Roboflow supports deploying custom computer vision models to Raspberry Pi devices with a performance optimized Docker container. A Raspberry Pi is often used as an
• 4 min read
How to Count Objects in an Image Using Python
In this article, we show how to count occurrences of objects in an image using Python.
• 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
Consider a scenario where you are building a model to detect cars on a street. If a car is parked on a street designated with no parking, you want to take a photo so that you can track the license plate of the car.
But, taking a photo would include
• 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
The full code for this article is on GitHub
Today, we will explore the use of PyTorch's distributed collective communication feature. When working with multiple GPUs, it is necessary to share tensors across them, which is where torch.distributed comes in. It provides a set of APIs to
• 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.
• 9 min read
How to Train YOLOv8 Object Detection on a Custom Dataset
In this article, we walk through how to train a YOLOv8 object detection model using a custom dataset.
• 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
• 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.
Stay Connected