Skip to content

Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.

Notifications You must be signed in to change notification settings

roboflow/notebooks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

👋 hello

Over the years we have created dozens of Computer Vision tutorials. This repository contains examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO, SAM, and GPT-4 Vision.

Curious to learn more about GPT-4 Vision? Check out our GPT-4V experiments 🧪 repository.

🚀 model tutorials (42 notebooks)

notebook open in colab / kaggle / sagemaker studio lab complementary materials repository / paper
Fine-Tune GPT-4o Colab Kaggle Roboflow YouTube
YOLO11 Object Detection Colab Kaggle Roboflow YouTube GitHub
YOLO11 Instance Segmentation Colab Kaggle YouTube GitHub
Segment Images with SAM2 Colab Kaggle Roboflow YouTube GitHub arXiv
Segment Videos with SAM2 Colab Kaggle Roboflow YouTube GitHub arXiv
RT-DETR Object Detection Colab Kaggle Roboflow GitHub arXiv
Fine-Tune Florence-2 on Object Detection Dataset Colab Kaggle Roboflow YouTube arXiv
Run Different Vision Tasks with Florence-2 Colab Kaggle Roboflow YouTube arXiv
Fine-Tune PaliGemma on Object Detection Dataset Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOv10 Object Detection Colab Kaggle Roboflow GitHub arXiv
Zero-Shot Object Detection with YOLO-World Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOv9 Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
RTMDet Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
Fast Segment Anything Model (FastSAM) Colab Kaggle Roboflow YouTube GitHub arXiv
YOLO-NAS Object Detection Colab Kaggle Roboflow YouTube GitHub
Segment Anything Model (SAM) Colab Kaggle Roboflow YouTube GitHub arXiv
Zero-Shot Object Detection with Grounding DINO Colab Kaggle Roboflow YouTube GitHub arXiv
DETR Transformer Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
DINOv2 Image Classification Colab Kaggle Roboflow GitHub arXiv
YOLOv8 Object Detection Colab Kaggle Roboflow YouTube GitHub
YOLOv8 Pose Estimation Colab Kaggle Roboflow GitHub
YOLOv8 Oriented Bounding Boxes Colab Kaggle Roboflow GitHub
YOLOv8 Instance Segmentation Colab Kaggle Roboflow YouTube GitHub
YOLOv8 Classification Colab Kaggle Roboflow GitHub
YOLOv7 Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOv7 Instance Segmentation Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOv7 Object Detection OpenVINO + TorchORT Colab Kaggle Roboflow GitHub arXiv
MT-YOLOv6 Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOv5 Object Detection Colab Kaggle Roboflow YouTube GitHub
YOLOv5 Classification Colab Kaggle Roboflow YouTube GitHub
YOLOv5 Instance Segmentation Colab Kaggle Roboflow YouTube GitHub
Detection2 Instance Segmentation Colab Kaggle Roboflow YouTube GitHub arXiv
SegFormer Instance Segmentation Colab Kaggle Roboflow YouTube GitHub arXiv
Vision Transformer Classification Colab Kaggle Roboflow YouTube GitHub arXiv
Scaled-YOLOv4 Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOS Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOR Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOX Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
Resnet34 fast.ai Classification Colab Kaggle Roboflow YouTube
OpenAI Clip Classification Colab Kaggle Roboflow YouTube GitHub arXiv
YOLOv4-tiny Darknet Object Detection Colab Kaggle Roboflow YouTube GitHub arXiv
Train a YOLOv8 Classification Model with No Labeling Colab Kaggle Roboflow GitHub

📸 computer vision skills (20 notebooks)

notebook open in colab / kaggle / sagemaker studio lab complementary materials repository / paper
Football AI Colab Kaggle Roboflow YouTube GitHub
Automated Dataset Annotation with GroundedSAM 2 Colab Kaggle Roboflow GitHub
How to Estimate Vehicle Speed Colab Kaggle Roboflow YouTube GitHub
Detect and Count Objects in Polygon Zone with YOLOv5 / YOLOv8 / Detectron2 + Supervision Colab Kaggle Roboflow YouTube GitHub
Track and Count Vehicles with YOLOv8 + ByteTRACK + Supervision Colab Kaggle Roboflow YouTube GitHub arXiv
Football Players Tracking with YOLOv5 + ByteTRACK Colab Kaggle Roboflow YouTube GitHub arXiv
Auto Train YOLOv8 Model with Autodistill Colab Kaggle Roboflow YouTube GitHub
Image Embeddings Analysis - Part 1 Colab Kaggle YouTube GitHub arXiv
Automated Dataset Annotation and Evaluation with Grounding DINO and SAM Colab Kaggle Roboflow YouTube GitHub arXiv
Automated Dataset Annotation and Evaluation with Grounding DINO Colab Kaggle YouTube GitHub arXiv
Roboflow Video Inference with Custom Annotators Colab Kaggle Roboflow GitHub
DINO-GPT-4V Object Detection Colab Kaggle Roboflow
Train a Segmentation Model with No Labeling Colab Kaggle Roboflow GitHub
DINOv2 Image Retrieval Colab Kaggle GitHub arXiv
Vector Analysis with Scikit-learn and Bokeh Colab Kaggle Roboflow
RF100 Object Detection Model Benchmarking Colab Kaggle Roboflow YouTube GitHub arXiv
Create Segmentation Masks with Roboflow Colab Kaggle Roboflow
How to Use PolygonZone and Roboflow Supervision Colab Kaggle Roboflow
Train a Package Detector With Two Labeled Images Colab Kaggle Roboflow GitHub
Image-to-Image Search with CLIP and faiss Colab Kaggle Roboflow

🎬 videos

Almost every week we create tutorials showing you the hottest models in Computer Vision. 🔥 Subscribe, and stay up to date with our latest YouTube videos!

How to Choose the Best Computer Vision Model for Your Project How to Choose the Best Computer Vision Model for Your Project

Created: 26 May 2023 | Updated: 26 May 2023

In this video, we will dive into the complexity of choosing the right computer vision model for your unique project. From the importance of high-quality datasets to hardware considerations, interoperability, benchmarking, and licensing issues, this video covers it all...


Accelerate Image Annotation with SAM and Grounding DINO Accelerate Image Annotation with SAM and Grounding DINO

Created: 20 Apr 2023 | Updated: 20 Apr 2023

Discover how to speed up your image annotation process using Grounding DINO and Segment Anything Model (SAM). Learn how to convert object detection datasets into instance segmentation datasets, and see the potential of using these models to automatically annotate your datasets for real-time detectors like YOLOv8...


SAM - Segment Anything Model by Meta AI: Complete Guide SAM - Segment Anything Model by Meta AI: Complete Guide

Created: 11 Apr 2023 | Updated: 11 Apr 2023


Discover the incredible potential of Meta AI's Segment Anything Model (SAM)! We dive into SAM, an efficient and promptable model for image segmentation, which has revolutionized computer vision tasks. With over 1 billion masks on 11M licensed and privacy-respecting images, SAM's zero-shot performance is often superior to prior fully supervised results...

💻 run locally

We try to make it as easy as possible to run Roboflow Notebooks in Colab and Kaggle, but if you still want to run them locally, below you will find instructions on how to do it. Remember don't install your dependencies globally, use venv.

# clone repository and navigate to root directory
git clone [email protected]:roboflow-ai/notebooks.git
cd notebooks

# setup python environment and activate it
python3 -m venv venv
source venv/bin/activate

# install and run jupyter notebook
pip install notebook
jupyter notebook

☁️ run in sagemaker studio lab

You can now open our tutorial notebooks in Amazon SageMaker Studio Lab - a free machine learning development environment that provides the compute, storage, and security—all at no cost—for anyone to learn and experiment with ML.

Stable Diffusion Image Generation YOLOv5 Custom Dataset Training YOLOv7 Custom Dataset Training
SageMaker SageMaker SageMaker

🐞 bugs & 🦸 contribution

Computer Vision moves fast! Sometimes our notebooks lag a tad behind the ever-pushing forward libraries. If you notice that any of the notebooks is not working properly, create a bug report and let us know.

If you have an idea for a new tutorial we should do, create a feature request. We are constantly looking for new ideas. If you feel up to the task and want to create a tutorial yourself, please take a peek at our contribution guide. There you can find all the information you need.

We are here for you, so don't hesitate to reach out.