Leveraging Embeddings and Clustering Techniques in Computer Vision

Explore the world of image embeddings in computer vision, as we dive into clustering, dataset assessment, and detecting image duplication. Discover dimensionality reduction techniques like t-SNE and UMAP. Use CLIP embeddings for analyzing image class distribution and identifying similar images.

Zero-Shot Image Annotation with Grounding DINO and SAM - A Notebook Tutorial

In this comprehensive tutorial, discover how to speed up your image annotation process using Grounding DINO and Segment Anything Model. Learn how to convert object detection datasets into instance segmentation datasets, and use these models to automatically annotate your images.

Top 5 Use Cases for Segment Anything Model (SAM)

In this guide, we walk through five use cases for Meta AI's new open-source Segment Anything Model (SAM).

Top 5 Artificial Intelligence Courses

Explore the top five artificial intelligence courses Roboflow recommends that will equip you with practical knowledge.

Grounding DINO : SOTA Zero-Shot Object Detection

Most object detection models are trained to identify a narrow predetermined collection of classes. Zero-shot detectors like Grounding DINO want to break this status quo by making it possible to detect new objects without re-training a model.

How to Build a Semantic Image Search Engine with Roboflow and CLIP

In this guide, you'll learn how to build a semantic search engine using the Roboflow API and CLIP.

Launch: Deploy Custom Model Weights with Roboflow

In this guide, you will learn how to deploy custom model weights on Roboflow.

Deploy YOLOv7 Instance Segmentation Models with Roboflow

Learn how to deploy a YOLOv7 instance segmentation model with custom weights to Roboflow.

Introducing Quickstart: Models in 2 Minutes on Your Machine

Learn how to use Roboflow Quickstart to start running inference on computer vision models in two minutes in a Jupyter Notebook.

Use CLIP Zero-Shot Classification with the Roboflow Inference Server

Learn how to use the CLIP endpoints on the Roboflow Inference Server for zero-shot classification.

Launch: Updated Roboflow Inference Server

In this guide, learn about the new features available in the Roboflow inference server through which you can run inference on computer vision models.

Build Computer Vision Applications Faster with Supervision

Learn how Supervision, a new Python package with utilities for building computer vision apps, can help you work through your computer vision projects faster than ever.

Resources to Build Computer Vision Applications Faster

Learn how Roboflow Utilities, Templates, Research, and Showcase can help you build computer vision applications faster.

How I Used Synthetic Data with Unity Perception to Minimize Annotation Time

Learn how a Roboflow user used synthetic data to minimize annotation time for a breadboard project.

Represent Chess Boards Digitally with Computer Vision

In this guide, learn how Shai Nisan used computer vision to translate a photo of a chess board into FEN notation.

Generate Image Augmentations with Roboflow

In this guide, you'll learn how to generate augmented images for your dataset on the Roboflow platform.

How to Use the Roboflow Fish Detection API

In this guide, we show how to use the Roboflow fish detection API to identify fish in image assets.

How to Send Roboflow Model Predictions to Zapier Webhooks

In this guide, we show how to send prediction data from a Roboflow model to Zapier via webhooks.

How to Use the Roboflow Bird Detection API

Learn how to use the Roboflow bird detection API to identify different species of birds.

How to Use the Roboflow People Detection API

Learn how to use the Roboflow people detection API to identify the locations of people in an image.

How to Use the Roboflow License Plate Detection API

Learn how to use the Roboflow license plate detection API in production using a range of deployment options.

Launch: Calculate Polygon Coordinates with PolygonZone

This guide shows how to use PolygonZone to draw polygons on an image and retrieve their coordinates for computer vision applications.

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.

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.

What is a Transformer?

In this guide, we explore what Transformers are, why Transformers are so important in computer vision, and how they work.