Video Analytics with AI | Live Coding & Q&A (Oct 9th) Roboflow 2024-10-11 | Let's build an object-tracking application using Supervision! I'll show you how to set up multiple lines for counting objects crossing in and out, use filters to focus on specific zones, and even count crossings per class. Join me for this live coding session where we'll build the app from start to finish. - ⭐ supervision: github.com/roboflow/supervisionStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
How to use OCR | Get Started with Optical Character Recognition Roboflow 2024-10-07 | Learn about different OCR models, see their performance on standard benchmarks, and follow a step by step guide on how to use OCR.Blog post: blog.roboflow.com/best-ocr-models-text-recognitionWorkflows: roboflow.com/workflows/build
GPT-4o: Fine-tune OpenAIs Multimodal Model | Live Coding & Q&A (Oct 3rd) Roboflow 2024-10-04 | Learn how to fine-tune GPT-4o with vision and improve its ability to understand images! This stream will cover the entire process, from preparing your image dataset to evaluating the results. We'll dive deep into real-world applications like enhanced visual search and object detection.- 📚 Written guide: blog.roboflow.com/gpt-4o-object-detection- 📓 GPT-4o fine-tuning API notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/openai-gpt-4o-fine-tuning.ipynb Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
YOLO11: How to Train for Object Detection | Live Coding & Q&A (Sep 30) Roboflow 2024-10-01 | Get started with YOLOv11! This video walks you through the setup and how to train YOLOv11 on your custom datasets for object detection and instance segmentation tasks. - 📓 object detection fine-tuning notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolo11-object-detection-on-custom-dataset.ipynb - 📓 instance segmentation fine-tuning notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolo11-instance-segmentation-on-custom-dataset.ipynbStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Using RTSP Streams for Computer Vision | Tracking & Counting Objects Roboflow 2024-09-27 | Learn how to use RTSP video streams as inputs for computer vision applications! Identify objects, count objects, monitor time in specific zones, and track entry/exit data.Roboflow: roboflow.comWorkflows: roboflow.com/workflows/buildDraw Polygonzones: polygonzone.roboflow.comCounting Workflow (single line): app.roboflow.com/workflows/embed/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ3b3JrZmxvd0lkIjoiTjBNbzh0RGJ2d3dOV0ZUNTVjeEkiLCJ3b3Jrc3BhY2VJZCI6ImtyT1RBYm5jRmhvUU1DZExPbGU0IiwidXNlcklkIjoiSW1GTElaU2tHYk55OXpiNFV1cWxNelBScHBRMiIsImlhdCI6MTcyNzQ1NDc2OH0.KRySRMBrL-tom8AoReDEeW44Nh-CPOypwWG7QblP9xoCounting Workflow (double line): app.roboflow.com/workflows/embed/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ3b3JrZmxvd0lkIjoicHJMY2wzRERPakVhczRxdHhvV0UiLCJ3b3Jrc3BhY2VJZCI6ImtyT1RBYm5jRmhvUU1DZExPbGU0IiwidXNlcklkIjoiSW1GTElaU2tHYk55OXpiNFV1cWxNelBScHBRMiIsImlhdCI6MTcyNzQ1NDc5OX0.NNO0p56BwJfkhwXqQeGP84HyiiCqd5NAbcAZJ6ORliATime in Zone Workflow: app.roboflow.com/workflows/embed/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ3b3JrZmxvd0lkIjoicHc4bDlPb3Z0RnZDSUE3OFhGSVMiLCJ3b3Jrc3BhY2VJZCI6ImtyT1RBYm5jRmhvUU1DZExPbGU0IiwidXNlcklkIjoiSW1GTElaU2tHYk55OXpiNFV1cWxNelBScHBRMiIsImlhdCI6MTcyNzQ1NDgyMH0.UgQ4Y7ZeDsmbv1GBPAqfwwR0Su5rL1ggHRQ7NxfRjU4
Model Evaluation for Computer Vision Roboflow 2024-09-11 | Learn about computer vision metrics like precision, recall, f1 score, how to and how to use a confusion matrix!ResourcesPrecision and recall: blog.roboflow.com/precision-and-recallMean average precision: blog.roboflow.com/mean-average-precisionConfusion matrix: blog.roboflow.com/what-is-a-confusion-matrixModel evaluation in Roboflow: blog.roboflow.com/evaluate-roboflow-models
Active Learning in Computer Vision Roboflow 2024-09-10 | Learn how to create active learning pipelines to use production data for training your next computer vision model!Blogpost: blog.roboflow.com/active-learning-workflow
Advanced Computer Vision Workflows Roboflow 2024-09-10 | Learn how to build computer vision workflows that use foundation models, like Segment Anything 2, and connect them with custom trained models, like YOLOv8, to build computer vision applications!ResourcesRoboflow Workflows: roboflow.com/workflows/buildWorkflows Templates: roboflow.com/workflows/templatesSmall Objects Workflow: app.roboflow.com/workflows/embed/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ3b3JrZmxvd0lkIjoiMWU4bkNOb2Jtdm0wOGtIb2Q1OWQiLCJ3b3Jrc3BhY2VJZCI6ImtyT1RBYm5jRmhvUU1DZExPbGU0IiwidXNlcklkIjoiSW1GTElaU2tHYk55OXpiNFV1cWxNelBScHBRMiIsImlhdCI6MTcyNDgwNzE0MX0.gqXArEVUQ0tBE7Ja5LMv3pwLY_gtlaPDrA9C_d1RmuASegment Anything 2 Workflow: app.roboflow.com/workflows/embed/eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ3b3JrZmxvd0lkIjoiV0tpN0F5YnV3NEtnRjFLN1ZDOTYiLCJ3b3Jrc3BhY2VJZCI6ImtyT1RBYm5jRmhvUU1DZExPbGU0IiwidXNlcklkIjoiSW1GTElaU2tHYk55OXpiNFV1cWxNelBScHBRMiIsImlhdCI6MTcyNDgwNjk2M30.e146HOZSWEbXoZGXxGzI2_EsNcs05kOh-09xIT6w3u4
Football AI | Community Q&A (Aug 29) Roboflow 2024-08-30 | Join me live as I dive deeper into Football AI! I'll answer your burning questions about the video tutorial, from fine-tuning object detection to calculating ball possession. Whether you're a beginner or an experienced coder, this is your chance to get expert insights and take your sports analytics skills to the next level. Don't miss out on this interactive session where we'll explore the limitless possibilities of AI in football!- 🎬 Football AI video: youtu.be/aBVGKoNZQUw- ⚽ Roboflow Sports repository: github.com/roboflow/sports - 🏞️ ball, players, and referees detection dataset: universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc - 🏞️ pitch keypoints detection dataset: universe.roboflow.com/roboflow-jvuqo/football-field-detection-f07vi - 📓 ball, players, and referees detection model training notebook: colab.research.google.com/github/roboflow/sports/blob/main/examples/soccer/notebooks/train_player_detector.ipynb - 📓 pitch keypoints detection model training notebook: colab.research.google.com/github/roboflow/sports/blob/main/examples/soccer/notebooks/train_pitch_keypoint_detector.ipynb- 📓 football AI notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/football-ai.ipynb- ⚽ Ball Tracking in Sports with Computer Vision blog post: blog.roboflow.com/tracking-ball-sports-computer-vision - ⚽ Camera Calibration in Sports with Keypoints blog post: blog.roboflow.com/camera-calibration-sports-computer-vision Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Football AI Tutorial: From Basics to Advanced Stats with Python Roboflow 2024-08-22 | Let's build a Football AI system to dig deeper into match stats! We'll use computer vision and machine learning to track players, determine which team is which, and even calculate stuff like ball possession and speed. This tutorial is perfect if you want to get hands-on with sports analytics and see how AI can take your football analysis to the next level.Chapters: - 00:00:00 Football (Soccer) AI: The Next Level- 00:00:58 Architectural Blueprint: Models & Tools for Football AI- 00:03:14 YOLOv8 Fine-Tuning: Optimizing for Football Object Detection- 00:12:22 Deploying YOLOv8 with Inference- 00:27:37 ByteTrack: Robust Multi-Object Tracking- 00:29:38 Embedding Analysis: Clustering Players with SigLIP & UMAP- 00:51:46 Perspective Transformation: Homography Fundamentals- 00:53:03 YOLOv8x-pose Training: Precise Pitch Landmark Detection- 01:01:24 Keypoint Inference: Real-Time Pitch Understanding- 01:06:27 Homography Application: Virtual Lines & Field Overlay- 01:13:23 Top-Down Projection: Creating a Tactical Radar View- 01:22:04 Spatial Analysis: Ball Territory- 01:26:34 Implementation Challenges- 01:28:29 Beyond the Basics: What Else is Possible?Resources: - Roboflow: roboflow.com 🔴 Community Session Aug 29th, 2024 at 08:00 AM PST / 11:00 AM EST / 05:00 PM CET: youtube.com/watch?v=Xwou5qO--vY- ⚽ Roboflow Sports repository: github.com/roboflow/sports - 🏞️ ball, players, and referees detection dataset: universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc - 🏞️ pitch keypoints detection dataset: universe.roboflow.com/roboflow-jvuqo/football-field-detection-f07vi - 📓 ball, players, and referees detection model training notebook: colab.research.google.com/github/roboflow/sports/blob/main/examples/soccer/notebooks/train_player_detector.ipynb - 📓 pitch keypoints detection model training notebook: colab.research.google.com/github/roboflow/sports/blob/main/examples/soccer/notebooks/train_pitch_keypoint_detector.ipynb- 📓 football AI notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/football-ai.ipynb- ⚽ Ball Tracking in Sports with Computer Vision blog post: blog.roboflow.com/tracking-ball-sports-computer-vision - ⚽ Camera Calibration in Sports with Keypoints blog post: blog.roboflow.com/camera-calibration-sports-computer-vision Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Computer Vision Hardware Configuration | Cameras, lenses, and GPUs for vision AI Roboflow 2024-08-20 | ...
AI-Assisted Data Labeling | Weekly Roboflow Product Session Roboflow 2024-08-14 | Join Roboflow team members and users every Tuesday at 11am EST to learn about the latest Roboflow features!Sign up for a future session: https://lu.ma/roboflow
Segment Anything 2 (SAM 2): Meta AIs Newest Model | Community Q&A (Jul 30) Roboflow 2024-07-31 | Segment Anything Model 2 (SAM 2) is a foundation model designed to address promptable visual segmentation in both images and videos. The model extends its functionality to video by treating images as single-frame videos. Its design, a simple transformer architecture with streaming memory, enables real-time video processing. A model-in-the-loop data engine, which enhances the model and data through user interaction, was built to collect the SA-V dataset, the largest video segmentation dataset to date. SAM 2, trained on this extensive dataset, delivers robust performance across diverse tasks and visual domains.- 📓 SAM2 notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-segment-images-with-sam-2.ipynb- 🗞 SAM2 overview blog post: blog.roboflow.com/what-is-segment-anything-2Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Master different vision tasks with pre-trained Florence-2 | Community Q&A (Jul 3) Roboflow 2024-07-04 | Master different vision tasks with pre-trained Florence-2 in this live coding community Q&A.Resources:- Roboflow: roboflow.com- 📓 Florence notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-florence-2-on-detection-dataset.ipynb - 🗞 Florence-2 arXiv paper: arxiv.org/abs/2311.06242 - 🗞 Florence-2 overview blog post: blog.roboflow.com/florence-2 - 🗞 Florence-2 fine-tuning blog post: blog.roboflow.com/fine-tune-florence-2-object-detection - 🔗 Florence-2 HF Space: huggingface.co/spaces/gokaygokay/Florence-2 Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Florence-2: Fine-tune Microsoft’s Multimodal Model Roboflow 2024-07-01 | Learn how to fine-tune Microsoft's Florence-2, a powerful open-source Vision Language Model, for custom object detection tasks. This in-depth tutorial guides you through setting up your environment in Google Colab, preparing datasets, and optimizing the model using LoRA.Chapters: - 00:00 Introduction: Unlock the Power of Florence-2- 01:09 Getting Started: Prepare for VLM Fine-Tuning- 03:55 Florence-2 in Action: Explore Pre-trained Capabilities- 07:00 Dataset Deep Dive: PyTorch Data Loading for Florence-2- 13:02 LoRA: Optimize Your VLM Training- 14:21 Fine-Tuning: Unleash Florence-2's Custom Object Detection- 17:30 Model Evaluation: Measure Your VLM's Success- 21:37 Florence-2 vs Other Computer Vision Models- 24:09 Conclusion and Next StepsResources: - Roboflow: roboflow.com- 🔴 Community Session July 3th, 2024 at 08:00 AM PST / 11:00 AM EST / 05:00 PM CET: https://roboflow.stream - ⭐ Notebooks GitHub: github.com/roboflow/notebooks - 📓 Florence notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-florence-2-on-detection-dataset.ipynb - 🗞 Florence-2 arXiv paper: arxiv.org/abs/2311.06242 - 🗞 Florence-2 overview blog post: blog.roboflow.com/florence-2 - 🗞 Florence-2 fine-tuning blog post: blog.roboflow.com/fine-tune-florence-2-object-detection - 🔗 Florence-2 HF Space: huggingface.co/spaces/gokaygokay/Florence-2 - 🗞 Mean Average Precision (mAP) blog post: blog.roboflow.com/mean-average-precision - 🗞 Confusion Matrix blog post: blog.roboflow.com/what-is-a-confusion-matrix Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
How good is YOLOv10? | Hacking Googles new VLM, PaliGemma | Community Q&A (Jun 6) Roboflow 2024-06-07 | Learn more about PaliGemma and YOLOv10 models from this live community Q&A.Resources:- Roboflow: roboflow.com- 🎬 PaliGemma by Google: Train Model on Custom Detection Dataset: youtu.be/OMBmVInx68M- ⭐ Notebooks GitHub: github.com/roboflow/notebooks - ⭐ Supervision GitHub: github.com/roboflow/supervision - 📓 PaliGemma notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma-on-detection-dataset.ipynb- 🗞 PaliGemma blog post: blog.roboflow.com/how-to-fine-tune-paligemma- 🗞 YOLOv10 blog post: blog.roboflow.com/yolov10-how-to-trainStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
PaliGemma by Google: Train Model on Custom Detection Dataset Roboflow 2024-06-03 | Learn how to fine-tune PaliGemma, Google's open-source Vision-Language Model, for custom object detection tasks. This step-by-step tutorial walks you through modifying Google's notebook to train PaliGemma on your dataset. We'll use the handwritten digits and math operations dataset from RF100, explore the JSONL format, and demonstrate how to deploy your fine-tuned model for real-world inference. Discover the power of PaliGemma for image captioning, VQA, and object detection, and overcome its limitations.Chapters: - 00:00 PaliGemma Capabilities- 02:03 Environment Setup- 05:25 Dataset Format- 09:07 Downloading Pre-trained Model- 11:27 Loading Dataset- 13:45 Training and Evaluating the Model- 15:19 Deploying the Model- 17:37 Important Considerations- 20:02 OutroResources: - Roboflow: roboflow.com- 🔴 Community Session June 6th, 2024 at 08:00 AM PST / 11:00 AM EST / 05:00 PM CET: https://roboflow.stream - ⭐ Notebooks GitHub: github.com/roboflow/notebooks - ⭐ Supervision GitHub: github.com/roboflow/supervision - 📓 PaliGemma notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma-on-detection-dataset.ipynb - 🗞 Gemma arXiv paper: arxiv.org/pdf/2403.08295 - 🗞 SigLIP arXiv paper: arxiv.org/pdf/2303.15343 - 🗞 PaliGemma blog post: blog.roboflow.com/how-to-fine-tune-paligemma- 🔗 RF100: rf100.org- 🔗 PaliGemma model card: kaggle.com/models/google/paligemma - 🔗 PaliGemma fine-tuned checkpoints: huggingface.co/collections/google/paligemma-ft-models-6643b03efb769dad650d2dda - 🔗 PaliGemma HF Space: huggingface.co/spaces/big-vision/paligemma Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Dwell Time Analysis | Real-Time Stream Processing | Community Q&A (April 11) Roboflow 2024-04-12 | Learn more about dwell time analysis and real-time stream processing from this live community Q&A.Resources:- Roboflow: roboflow.com- 🎬 Dwell Time Analysis with Computer Vision | Real-Time Stream Processing: youtu.be/hAWpsIuem10- ⭐ Inference GitHub: github.com/roboflow/inference - ⭐ Supervision GitHub: github.com/roboflow/supervision - 💻 Time in Zone Code: github.com/roboflow/supervision/tree/develop/examples/time_in_zone - 🌇 MS COCO Dataset on Roboflow Universe: universe.roboflow.com/microsoft/coco/dataset/5 - 📙Detect and Annotate Supervision Guide: supervision.roboflow.com/develop/how_to/detect_and_annotate/#annotate-image-with-segmentations - 🎬 Source Checkouts Video: youtube.com/watch?v=-8zyEwAa50Q - 🎬 Source Traffic Video: youtube.com/watch?v=MNn9qKG2UFI Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Dwell Time Analysis with Computer Vision | Real-Time Stream Processing Roboflow 2024-04-04 | Learn how to use computer vision to analyze wait times and optimize processes. This tutorial covers object detection, tracking, and calculating time spent in designated zones. Use these techniques to improve customer experience in retail, traffic management, or other scenarios.Chapters: - 00:00 Intro- 00:41 Static File Processing vs. Stream Processing: Time Calculation Explained- 04:29 Time Calculation Methods: FPS vs. ClockTime- 06:54 Project Setup- 08:39 Object Detection and Tracking- 12:57 Defining Zones: How to Filter Objects- 16:33 Measuring Time- 17:44 Why Naive Stream Processing Fails- 21:02 Efficient Stream Processing- 24:19 Important Considerations- 26:07 OutroResources: - Roboflow: roboflow.com- 🔴 Community Session April 11 2024 at 08:00 AM PST / 11:00 AM EST / 05:00 PM CET: youtube.com/watch?v=u7XUC-3TqY8 - ⭐ Inference GitHub: github.com/roboflow/inference - ⭐ Supervision GitHub: github.com/roboflow/supervision - 💻 Time in Zone Code: github.com/roboflow/supervision/tree/develop/examples/time_in_zone - 🌇 MS COCO Dataset on Roboflow Universe: universe.roboflow.com/microsoft/coco/dataset/5 - 📙Detect and Annotate Supervision Guide: supervision.roboflow.com/develop/how_to/detect_and_annotate/#annotate-image-with-segmentations - 🎬 Source Checkouts Video: youtube.com/watch?v=-8zyEwAa50Q - 🎬 Source Traffic Video: youtube.com/watch?v=MNn9qKG2UFI Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
YOLOv9 Live Coding & Community Q&A (March 14) Roboflow 2024-03-15 | Learn more about YOLOv9, a new state-of-the-art real-time object detection model from this live community Q&A.Resources:- Roboflow: roboflow.com- 🎬 YOLOv9 Tutorial: Train Model on Custom Dataset: youtu.be/XHT2c8jT3Bc- ⭐ Inference GitHub: github.com/roboflow/inference - ⭐ Notebooks GitHub: github.com/roboflow/notebooks - ⭐ Supervision GitHub: github.com/roboflow/supervision - ⭐ YOLOv9 GitHub: github.com/WongKinYiu/yolov9 - 🗞 YOLOv9 arXiv paper: arxiv.org/abs/2402.13616 - 🗞 YOLOv9 blog post: blog.roboflow.com/train-yolov9-model- 📓 YOLOv9 notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov9-object-detection-on-custom-dataset.ipynb?ref=blog.roboflow.com- ⚽ Football Players Detection dataset: universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc?ref=blog.roboflow.com- 🤗 YOLO ARENA Space: huggingface.co/spaces/SkalskiP/YOLO-ARENA- 🤗 YOLO-World + EfficientSAM HF Space: huggingface.co/spaces/SkalskiP/YOLO-WorldStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
YOLOv9 Tutorial: Train Model on Custom Dataset | How to Deploy YOLOv9 Roboflow 2024-03-04 | Description:Get hands-on with YOLOv9! This video dives into the architecture, setup, and how to train YOLOv9 on your custom datasets.Chapters:- 00:00 Intro- 00:36 Setting Up YOLOv9- 03:29 YOLOv9 Inference with Pre-Trained COCO Weights- 06:35 Training YOLOv9 on Custom Dataset- 10:44 YOLOv9 Model Evaluation- 13:53 YOLOv9 Inference with Fine-Tuned Model- 15:18 Model Deployment with Inference Package- 17:37 Important Considerations for Using YOLOv9- 19:00 Demo: Build Self-Service Checkout with YOLOv9- 19:50 OutroResources:Object Detection Model Leaderboard: roboflow.com/models/leaderboard- Roboflow: roboflow.com- Roboflow Universe: universe.roboflow.com - 🔴 Community Session March 14 2024 at 09:00 AM PST / 12:00 PM EST / 06:00 PM CET: https://roboflow.stream - ⭐ Inference GitHub: github.com/roboflow/inference - ⭐ Notebooks GitHub: github.com/roboflow/notebooks - ⭐ Supervision GitHub: github.com/roboflow/supervision - ⭐ YOLOv9 GitHub: github.com/WongKinYiu/yolov9 - 🗞 YOLOv9 arXiv paper: arxiv.org/abs/2402.13616 - 🗞 YOLOv9 blog post: blog.roboflow.com/train-yolov9-model - 📓 YOLOv9 notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolov9-object-detection-on-custom-dataset.ipynb - ⚽ Football Players Detection dataset: universe.roboflow.com/roboflow-jvuqo/football-players-detection-3zvbc - 🤗 YOLO ARENA Space: huggingface.co/spaces/SkalskiP/YOLO-ARENA- 🤗 YOLO-World + EfficientSAM HF Space: huggingface.co/spaces/SkalskiP/YOLO-WorldStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
YOLO-World Live Coding & Community Q&A (Feb 27) Roboflow 2024-02-28 | Learn more about YOLO-World, a cutting-edge zero-shot object detection model from this live community Q&A.Resources:- Roboflow: roboflow.com- ⭐ YOLO-World GitHub: github.com/AILab-CVC/YOLO-World - 🗞 YOLO-World arXiv paper: arxiv.org/abs/2401.17270- 🗞 YOLO-World blog post: blog.roboflow.com/what-is-yolo-world- 📓 YOLO-World notebook: supervision.roboflow.com/develop/notebooks/zero-shot-object-detection-with-yolo-world- 🤗 YOLO-World + EfficientSAM HF Space: huggingface.co/spaces/SkalskiP/YOLO-World- ⭐ Inference GitHub: github.com/roboflow/inference - ⭐ Supervision GitHub: github.com/roboflow/supervision Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
YOLO-World: Real-Time, Zero-Shot Object Detection Explained Roboflow 2024-02-21 | In this video, you’ll learn how to use YOLO-World, a cutting-edge zero-shot object detection model. We'll cover its speed, compare it to other models, and run a live code demo for image AND video analysis.Chapters:- 00:00 Intro- 00:42 YOLO-World vs. Traditional Object Detectors: Speed and Accuracy- 02:26 YOLO-World Architecture - prompt-then-detect- 03:59 Setting Up and Running YOLO-World- 05:33 Prompt Engineering and Detections Post-Processing- 09:20 Video Processing with YOLO-World- 13:16 Important Considerations for Using YOLO-World- 15:08 Beyond the Basics: Advanced use cases and future potential- 16:37 OutroResources:- Roboflow: roboflow.com- 🔴 Community Session February 27 2024 at 08:00 AM PST / 11:00 AM EST / 05:00 PM CET: youtube.com/live/lF1BtQL16l4?si=f9sPd4DrX8tnDtc1- ⭐ Inference GitHub: github.com/roboflow/inference - ⭐ Supervision GitHub: github.com/roboflow/supervision - ⭐ YOLO-World GitHub: github.com/AILab-CVC/YOLO-World - 🗞 YOLO-World arXiv paper: arxiv.org/abs/2401.17270- 🗞 YOLO-World blog post: blog.roboflow.com/what-is-yolo-world- 📓 YOLO-World notebook: supervision.roboflow.com/develop/notebooks/zero-shot-object-detection-with-yolo-world- 🤗 YOLO-World + EfficientSAM HF Space: huggingface.co/spaces/SkalskiP/YOLO-World- 🗞 GroundingDINO blog post: blog.roboflow.com/grounding-dino-zero-shot-object-detection - 🗞 Non-Max Suppression blog post: blog.roboflow.com/how-to-code-non-maximum-suppression-nms-in-plain-numpyStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Speed Estimation & Vehicle Tracking | Computer Vision | Open Source Roboflow 2024-01-10 | Learn how to track and estimate the speed of vehicles using YOLO, ByteTrack, and Roboflow Inference. This comprehensive tutorial covers object detection, multi-object tracking, filtering detections, perspective transformation, speed estimation, visualization improvements, and more. Use this knowledge to enhance traffic control systems, monitor road conditions, and gain valuable insights into vehicle behavior.Chapters: - 00:00 Intro- 00:36 Object Detection- 03:43 Multi-Object Tracking- 05:11 Filtering Detections with Polygon Zone- 06:39 Math Behind Perspective Transformation- 14:35 Perspective Transformation in Code- 16:46 Math Behind Speed Estimation- 18:42 Speed Estimation in Code- 21:29 Visualization Improvements- 22:45 Final ResultsResources: - Roboflow: roboflow.com- 💻 Speed Estimation Open-Source Code: github.com/roboflow/supervision/tree/develop/examples/speed_estimation - 📚 "How to Estimate Speed with Computer Vision" blog.roboflow.com/estimate-speed-computer-vision- 📓Colab Notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-estimate-vehicle-speed-with-computer-vision.ipynb?ref=blog.roboflow.com- ⭐ Supervision GitHub: github.com/roboflow/supervision - ⭐ Inference GitHub: github.com/roboflow/inference - 📚 “How to Track Objects” Supervision Docs: supervision.roboflow.com/how_to/track_objects- 📚 “Annotators” Supervision Docs: supervision.roboflow.com/annotators - 🎬 “Track & Count Objects using YOLOv8 ByteTrack & Supervision” YouTube video: youtu.be/OS5qI9YBkfk- 🎬 “Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking” YouTube video: youtu.be/4Q3ut7vqD5oRemember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
GPT-4V Alternative (Self-Hosted): Deploy CogVLM on AWS Roboflow 2023-12-21 | Deploy CogVLM, a powerful GPT-4V alternative, on AWS with this step-by-step technical guide. Learn how to set up and run a self-hosted AI model, gaining independence from standard APIs and enhancing your computer vision capabilities.Chapters: - 00:00 Intro- 00:40 Introduction to CogVLM- 01:43 Setting Up the AWS Infrastructure- 03:56 Configuring the Inference Server- 05:41 Running Inference and Testing the Model- 09:08 OutroResources: - Roboflow: roboflow.com- Roboflow Universe: universe.roboflow.com- How to Deploy CogVLM on AWS blog post: blog.roboflow.com/how-to-deploy-cogvlm-in-aws- GPT-4 Vision Alternatives blog post: blog.roboflow.com/gpt-4-vision-alternatives - Inference Server code: github.com/roboflow/inference - CogVLM Client code: github.com/roboflow/cog-vlm-client - CogVLM: Visual Expert for Pretrained Language Models arXiv paper: arxiv.org/abs/2311.03079 - CogVLM code: github.com/THUDM/CogVLM - Multimodal Maestro GitHub: github.com/roboflow/multimodal-maestro - Multimodal Maestro: Advanced LMM Prompting blog post: blog.roboflow.com/multimodal-maestro-advanced-lmm-prompting Remember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
AI.engineer 2023: Live Coding a Multimodal Game, paint.wtf Roboflow 2023-10-13 | Roboflow's CEO re-creates our hit drawing game, paint.wtf, powered by the OpenAI CLIP model which attracted over 100,000 players in its first week live on stage in 5 minutes at the 2023 AI.engineer conference.paint.wtf: https://paint.wtfInference: roboflow.com/inference
Top Object Detection Models in 2023 | Model Selection Guide sponsored by Intel Roboflow 2023-10-02 | Description:Discover the top object detection models in 2023 in this comprehensive video. We compare models like YOLOv8, YOLOv7, RTMDet, DETA, DINO, and GroundingDINO based on metrics like Mean Average Precision, community support, packaging, and licensing for you to decide which is best for your production AI applications. The video also details the challenges in comparing model speed and highlights important nuances within the realm of object detection, like choosing the right model for the right hardware and use case. It's an essential watch for anyone interested in computer vision and model selection. This research was sponsored by Intel.#ObjectDetection #ComputerVisionChapters: - 00:00 Introduction- 00:35 Object Detection- 01:42 Mean Average Precision- 02:28 Speed- 03:40 Paper, Packaging, and License- 04:35 YOLOv8- 05:21 YOLOv7- 06:06 YOLOv6-v3- 07:01 RTMDet- 07:46 RT-DETR- 08:50 DETA- 10:02 GroundingDINO- 10:37 Model Community Comparison- 11:46 ConclusionResources: Object Detection Model Leaderboard: roboflow.com/models/leaderboard- 🌏 Roboflow: roboflow.com - 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 🌌 Roboflow Universe: universe.roboflow.com - 📈GPU vs Intel HPU (new hardware options for AI): blog.roboflow.com/gpu-vs-hpuStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐ Remember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀
Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking Roboflow 2023-09-06 | In this video, we explore real-time traffic analysis using YOLOv8 and ByteTrack to detect and track vehicles on aerial images. Harnessing the power of Python and Supervision, we delve deep into assigning cars to specific entry zones and understanding their direction of movement. By visualizing their paths, we gain insights into traffic flow across bustling roundabouts. All resources, including our open-source project, are accessible via Roboflow's GitHub.Chapters: - 00:00 Introduction - 01:16 Vehicle detection on aerial images using YOLOv8- 05:03 Tracking objects using ByteTrack and Supervision- 06:46 Defining entry and exit zones- 10:28 Assigning vehicles to specific entry zones- 16:22 Drawing the path of moving objects- 17:18 Analysing traffic flow - 22:23 ConclusionsResources: - 🌏 Roboflow: roboflow.com - 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 🌌 Roboflow Universe: universe.roboflow.com- 💻 Supervision GitHub repository: github.com/roboflow/supervision- 🖼️ Detecting Vehicles on Aerial Images dataset: universe.roboflow.com/roboflow-jvuqo/detecting-vehicles-on-aerial-images- 🎬 YOLOv8: How to Train for Object Detection on a Custom Dataset YouTube video: youtu.be/wuZtUMEiKWY?si=iYpuHlGcFTJIzl4c- 🎬 Track & Count Objects using YOLOv8 ByteTrack & Supervision YouTube video: youtu.be/OS5qI9YBkfk?si=3oNbVxB0m66VTO75 🎬 Count People in Zone | Using YOLOv5, YOLOv8, and Detectron2 | Computer Vision YouTube video: youtu.be/l_kf9CfZ_8M?si=nHJIzu2R2vVQXj2vRemember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
How to Use MMDetection | Train RTMDet on a Custom Dataset Roboflow 2023-08-24 | Dive into the world of computer vision with this comprehensive tutorial on training the RTMDet model using the renowned MMDetection library. Whether you're just starting out or looking to refine your skills, this guide offers a deep dive into the OpenMMLab ecosystem, hands-on installation steps, and practical insights into training on custom datasets.Chapters: - 00:00 Introduction - 00:29 What is MMDetection and RTMDet - 01:24 OpenMMLab Libraries Installation- 04:54 Inference with Pre-trained COCO Model- 08:14 Downloading a Dataset from Roboflow Universe- 10:02 Preparing Custom MMDetection Configuration File - 11:30 Train RTMDet and Analyze the Metrics - 13:08 Evaluating the RTMDet Model with Supervision - 14:24 ConclusionsResources: - 🌏 Roboflow: roboflow.com - 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 🌌 Roboflow Universe: universe.roboflow.com- 📓 RTMDet Object Detection Google Colab: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-rtmdet-object-detection-on-custom-data.ipynb - 🗞️ RTMDet: An Empirical Study of Designing Real-Time Object Detectors Arxiv paper: arxiv.org/pdf/2212.07784.pdf - 🗞️How to Train RTMDet on a Custom Dataset blog post: blog.roboflow.com/how-to-train-rtmdet-on-a-custom-dataset - 💻 MMDetection GitHub repository: github.com/open-mmlab/mmdetection- 🖼️ Double Twelve Dominoes object detection dataset: universe.roboflow.com/pip-tracker/double-twelve-dominoesRemember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Open Source Computer Vision Deployment with Roboflow Inference Roboflow 2023-08-17 | Description:Today, we are open-sourcing the Roboflow Inference Server: our battle-hardened solution for using and deploying computer vision models in production, and announcing Roboflow Inference, an opinionated framework for creating standardized APIs around computer vision models. Roboflow Deploy powers millions of daily inferences across thousands of models for hundreds of customers (including some of the world’s largest companies), and now we’re making the core technology available to the community under a permissive, Apache 2.0 license.Chapters: - 00:00 Introduction- 01:17 Docker- 03:24 Image Client- 08:14 Video Client- 09:58 Models- 11:19 OutroResources: - 🌏 Roboflow: roboflow.com - 🖼️ Roboflow Inference Repository: github.com/roboflow/inference- 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 🌌 Roboflow Universe: universe.roboflow.com- 🗞️ Open Source Computer Vision Deployment with Roboflow Inference Blog Post: blog.roboflow.com/open-source-inference-server- 🚀 Inference Client Examples Repository: github.com/roboflow/inference-client Remember to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Fast Segment Anything (FastSAM) vs SAM | Is it 50x faster? Roboflow 2023-07-07 | Description:We compare Segment Anything (SAM) and FastSAM, highlighting their differences in performance and application. We take you through the installation process, inference modes, and deep comparison of these two models, offering insightful observations about their strengths and limitations. This video serves as a comprehensive guide, packed with valuable resources for FastSAM and SAM, ideal for AI enthusiasts, developers, and researchers alike. Don't miss the opportunity to deepen your understanding of AI, computer vision, and the latest tech breakthroughs!Chapters: - 00:00 Introduction- 01:07 Fast SAM- 02:10 Installation- 04:35 Everything Prompt- 07:36 Box Prompt- 09:01 Point Prompt- 09:42 Text Prompt- 11:05 SAM vs FastSAM- 13:06 Conclusions- 15:28 OutroResources: - 🌏 Roboflow: roboflow.com - 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 🌌 Roboflow Universe: universe.roboflow.com- 🗞️How to Use FastSAM blogpost:blog.roboflow.com/how-to-use-fastsam - 🗞️What is FastSAM? The Ultimate Guide. blogpost: blog.roboflow.com/what-is-fastsam - 🗞️Fast Segment Anything (FastSAM) paper: arxiv.org/abs/2306.12156 - 📓Fast Segment Anything Model (FastSAM) notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-segment-anything-with-fast-sam.ipynb - 🌌 SA-1B dataset: segment-anything.com/dataset/index.html Complementary SAM resources:On July 29th, 2024, Meta AI released Segment Anything 2 (SAM 2), a new image and video segmentation foundation model. According to Meta, SAM 2 is 6x more accurate than the original SAM model at image segmentation tasks. Learn more: blog.roboflow.com/what-is-segment-anything-2- 🗞️How to Use the Segment Anything Model (SAM) blog post: blog.roboflow.com/how-to-use-segment-anything-model-sam - 🎬 Segment Anything Model (SAM) YouTube video: youtu.be/D-D6ZmadzPE - 🎬 Accelerate Image Annotation with SAM and Grounding DINO YouTube video: youtu.be/oEQYStnF2l8 Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
CVPR 2023 - Top Papers & Highlights (My first time!) Roboflow 2023-07-04 | Description:Experience CVPR 2023 like never before! As a first-time attendee, I bring you an in-depth review and highlights from one of the most significant events in the Computer Vision community. This video gives you an overview of the conference, intriguing workshops, and a rundown of top papers that have made waves in the field this year. With over 9000 papers submitted and around 2300 accepted, CVPR 2023 was an event packed with insightful presentations, innovative ideas, and cutting-edge AI technology discussions. Whether you're an AI enthusiast, a practitioner, or a researcher, this video will provide you with the key takeaways from the conference. Don't miss the chance to virtually meet some of the authors behind your favorite models like GroundingDINO, SAM, and OneFormer. Stay tuned till the end to hear some engaging interviews and final thoughts.Chapters: 00:00 Introduction00:58 Conference Overview02:20 Workshops03:39 Papers Overview04:44 Top Papers08:13 Final Thoughts08:48 InterviewsResources: - 🌏 Roboflow: roboflow.com - 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 🌌 Roboflow Universe: universe.roboflow.com - 🗞️ CVPR 2023 Highlights blogpost: blog.roboflow.com/cvpr-2023-highlights - 🗞️ Roboflow 100 blogpost: blog.roboflow.com/roboflow-100 - 🗞️ List of Accepted CVPR 2023 papers: cvpr2023.thecvf.com/Conferences/2023/AcceptedPapers- 🗞️ Computer Vision in the Wild CVPR 2023 workshop overview: computer-vision-in-the-wild.github.io/cvpr-2023 - 🎬 Grounding DINO YouTube video: youtu.be/cMa77r3YrDk - 🎬 Segment Anything Model (SAM) YouTube video: youtu.be/D-D6ZmadzPE - 🎬 OneFormer YouTube video: youtu.be/_Zr1pOi7Chw - 🎬 RF100 YouTube video: youtu.be/i8amBaHrhqY - 🗞️ ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models paper: arxiv.org/abs/2303.04803- 🗞️ OneFormer: One Transformer to Rule Universal Image Segmentation paper: arxiv.org/abs/2211.06220- 🗞️ PACO: Parts and Attributes of Common Objects paper: arxiv.org/abs/2301.01795- 🗞️ DynIBaR Neural Dynamic Image-Based Rendering paper: arxiv.org/abs/2211.11082- 🗞️ SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields paper: arxiv.org/abs/2211.12254- 🗞️ InstructPix2Pix: Learning to Follow Image Editing Instructions paper: arxiv.org/abs/2211.12254- 🗞️ DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation paper: arxiv.org/abs/2208.12242 Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐ #CVPR2023 #ComputerVision #CVPRHighlights #PatternRecognition #ObjectDetection #InstanceSegmentation #CVPRPapers
Autodistill: Label and Train a Computer Vision Model in Under 20 Minutes Roboflow 2023-06-23 | Autodistill is a new library for creating computer vision models without labeling any training data. In this video, we evaluate the speed and efficiency of Autodistill by auto-labeling, training a model, and running inference in under 20 minutes!- Google Colab: drive.google.com/file/d/1uWPISt3teYe2VAq05gcxoUIXah3_xBJQ/view?usp=sharingChapters: 00:00 Autodistill Overview00:50 Setup and Installation01:50 Import Dataset03:00 Initialize Base Model and Autolabel04:50 Initialize Target Model and Train07:10 Visualize the ResultsResources: - Autodistill Repository: github.com/autodistill/autodistill- Autodistill Overview: blog.roboflow.com/autodistill- Roboflow: roboflow.com - Roboflow Universe: universe.roboflow.com - Roboflow Notebooks Repository: github.com/roboflow/notebooksDon't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest in ML! Stay updated with the projects I'm working on at github.com/roboflow and github.com/artyaltanzaya
Autodistill: Train YOLOv8 with ZERO Annotations Roboflow 2023-06-08 | Description:Autodistill is a ground-breaking tool revolutionizing the world of computer vision! In this video, we will show you how to use a new library to train a YOLOv8 model to detect bottles moving on a conveyor line. Yes, that's right - zero annotation hours are required! We dive deep into Autodistill's functionality, covering topics from setting up your Python environment and preparing your images, to the thrilling automatic annotation of images. What makes Autodistill a game-changer is its ability to distill knowledge from large foundational models like GroundedSAM, transferring this knowledge into highly-optimized computer vision models. We're ecstatic to showcase how this library can turn hours of tedious manual annotation into a fully automated process, without compromising the accuracy of your models. Chapters: 00:00 Autodistill Overview02:03 Project Overview03:16 Setup Python Environment04:46 Prepare Images06:22 Autoannotate Images07:50 Train YOLOv8 Model08:28 Run Inference on Video09:16 ConclusionResources: - 🌏 Roboflow: roboflow.com - 🧪 Autodistill Repository: github.com/autodistill/autodistill - 🌌 Roboflow Universe: universe.roboflow.com - 📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks- 📓 How to Auto Train YOLOv8 Model with Autodistill Google Colab: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-auto-train-yolov8-model-with-autodistill.ipynb- 🗞️ Autodistill blogpost: blog.roboflow.com/autodistill- 🎬 How to Train YOLOv8 Object Detection Model on a Custom Dataset YouTube video: youtu.be/wuZtUMEiKWY - 🎬 How to Train YOLOv8 Instance Segmentation Model on Custom Dataset YouTube video: youtu.be/pFiGSrRtaU4 - 🎬 Detect Anything You Want with Grounding DINO YouTube video: youtu.be/cMa77r3YrDk - 🎬 SAM - Segment Anything Model Overview YouTube video: youtu.be/D-D6ZmadzPE - 🎬 Accelerate Image Annotation with SAM and Grounding DINO YouTube video: youtu.be/oEQYStnF2l8 Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
How to Choose the Best Computer Vision Model for Your Project Roboflow 2023-05-25 | 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. Whether you're planning to develop an app for counting commuters in public transport or analyzing medical images, we guide you on the critical factors that should inform your model selection. We even explore specific models like YOLOv5, YOLO-NAS, and Detectron2 in context. Don't forget to like, subscribe, and stay tuned for more computer vision content!Chapters:00:00 Introduction00:40 Overthinking Model Selection01:36 Different Project Contexts (Counting People vs Analyzing Medical Images)03:15 Hardware Considerations04:04 mAP vs Latency05:33 Benchmarking and the Importance of Preliminary Testing06:00 Understanding mAP Values in the Context of Custom Datasets08:27 Library Packaging09:46 Model Integration and the Role of SDKs10:52 Importance of Active Project Support11:27 Understanding Project Licenses12:31 ConclusionResources: Object Detection Model Leaderboard: roboflow.com/models/leaderboard🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks🎬 YOLOv8: How to Train for Object Detection on a Custom Dataset: youtu.be/wuZtUMEiKWYStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀#ComputerVision #ObjectDetection #InstanceSegmentation #DeepLearning #YOLO #Detectron2 #Dataset #ModelSelection #AI #YOLOv8
Train YOLO-NAS - SOTA Object Detection Model - on Custom Dataset Roboflow 2023-05-11 | Discover the power of YOLO-NAS, Deci's next-generation object detection model, in this comprehensive guide. We'll walk you through the Python setup, installing YOLO-NAS, running inferences with the pre-trained COCO model, and even training YOLO-NAS on your custom dataset. Dive into the superior real-time object detection capabilities of this game-changing model and learn how to use it to optimize your own AI projects.Chapters:00:00 Introduction and Model Overview01:57 Python Environment Setup and Installing YOLO-NAS04:56 Inference with pre-trained COCO model07:21 YOLO-NAS Inference Output Format09:06 Finding Open-source Datasets10:19 Training YOLO-NAS on Custom Dataset16:34 Evaluate Trained Model17:28 Inference with Trained Model18:39 ConclusionResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📚 Roboflow Notebooks Repository: github.com/roboflow/notebooks📚 How to Train YOLO-NAS on a Custom Dataset blog post: blog.roboflow.com/yolo-nas-how-to-train-on-custom-dataset📓 How to Train YOLO-NAS on a Custom Dataset notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-yolo-nas-on-custom-dataset.ipynb❓ Why do we need to restart Google Colab? github.com/obss/sahi/discussions/781🎬 YOLOv8: How to Train for Object Detection on a Custom Dataset: youtu.be/wuZtUMEiKWYStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀#YOLO_NAS #Deci #ObjectDetection #NeuralArchitectureSearch #Python #COCO #MachineLearning #ArtificialIntelligence #CustomDataset #Inference #ModelEvaluation #OpenSource #Datasets
CLIP, T-SNE, and UMAP - Master Image Embeddings & Vector Analysis Roboflow 2023-04-28 | Description:Start your Data Science and Computer Vision adventure with this comprehensive Image Embedding and Vector Analysis guide. Explore OpenAI CLIP embeddings for image clustering and duplicate detection, and learn essential concepts like T-SNE, UMAP, and MNIST. Follow our beginner-friendly Google Colab notebook to master the basics and kickstart your journey in Computer Vision!Chapters:00:00 Introduction01:23 Python Environment Setup01:58 Clustering MNIST images using pixel brightness09:00 T-SNE vs. UMAP10:40 Clustering images using OpenAI CLIP embeddings17:22: Using OpenAI CLIP embeddings to detect duplicates or close duplicates20:05 Conclusions Resources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📓 "Image Embeddings Analysis notebook": colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/image_embeddings_analysis_part_1.ipynb📚 "What is OpenAI's CLIP and how to use it?" blog post: blog.roboflow.com/openai-clip🎬 "CLIP: OpenAI's amazing new zero-shot image classifier" video: youtu.be/8o701AEoZ8IStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀ComputerVision #DataScience #ImageEmbeddings #OpenAICLIP #TSNE #UMAP #MNIST
Accelerate Image Annotation with SAM and Grounding DINO | Python Tutorial Roboflow 2023-04-20 | Description: In this comprehensive tutorial, 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. Stay tuned for the upcoming release of a Python library that will make this process even more effortless.Chapters:00:00 Introduction00:58 Python Environment Setup04:13 Load Grounding DINO and Segment Anything Models05:42 Single Image Mask Autoannotation08:24 Full Dataset Mask Autoannotation09:58 Save Labels to Pascal VOC XML14:17 Upload Annotations to Roboflow15:23 Review and Refine Annotations in Roboflow UI17:11 Convert Object Detection to Instance Segmentation Dataset22:35 Conclusions23:28 AnnouncementResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📓 Automated Dataset Annotation and Evaluation with Grounding DINO and SAM notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/automated-dataset-annotation-and-evaluation-with-grounding-dino-and-sam.ipynb📚 Grounding DINO blog post: blog.roboflow.com/grounding-dino-zero-shot-object-detection🎬 Detect Anything You Want with Grounding DINO | Zero-Shot Object Detection SOTA video: youtu.be/cMa77r3YrDk📚 How to Use the Segment Anything Model (SAM) blog post: blog.roboflow.com/how-to-use-segment-anything-model-sam🎬 SAM - Segment Anything Model by Meta AI: Complete Guide | Python Setup & Applications video: youtu.be/D-D6ZmadzPEStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀#MetaAI #SegmentAnythingModel #SAM #ImageSegmentation #Python #FoundationModels #ComputerVision #ZeroShot #GroundingDINO #ObjectDetection #DataLabeling
Label Data with Segment Anything Model (SAM) in Roboflow Roboflow 2023-04-14 | We are excited to release support for zero-shot segmentation labeling in Roboflow Annotate using Meta AI’s Segment Anything Model (SAM).Using the Smart Polygon feature, you’re accessing a cloud-hosted Segment Anything model enabling you to apply polygon annotations faster, easier, and more accurately than ever before, right inside the Roboflow UI. No setup. No servers. No integrations. Create annotations with one click.Chapters:00:00 - Introduction00:35 - Concrete Cracks Annotation with Smart Polygon03:06 - Converting Bounding Box Blueberry Object Detection Dataset into Polygons06:43 - Annotating Low-Resolution Blood Cells Images with Smart Polygon08:47 - ConclusionResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📚 Launch: Label Data with Segment Anything in Roboflow blog: blog.roboflow.com/label-data-segment-anything-model-sam🔥 Automated Data Labeling with SAM: youtu.be/oEQYStnF2l8On July 29th, 2024, Meta AI released Segment Anything 2 (SAM 2), a new image and video segmentation foundation model. According to Meta, SAM 2 is 6x more accurate than the original SAM model at image segmentation tasks. Learn more: blog.roboflow.com/what-is-segment-anything-2Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest breakthroughs in technology! 🚀#MetaAI #SegmentAnythingModel #SAM #ImageSegmentation #ComputerVision
SAM - Segment Anything Model by Meta AI: Complete Guide | Python Setup & Applications Roboflow 2023-04-11 | Description:Discover the incredible potential of Meta AI's Segment Anything Model (SAM) in this comprehensive tutorial! 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 competitive with or even superior to prior fully supervised results.🔍 Explore this in-depth guide as we walk you through setting up your Python environment, loading SAM, generating segmentation masks, and much more. Master the art of converting object detection datasets into segmentation masks and learn how to leverage this powerful tool for your projects.Chapters:00:00 - Introduction and Overview of SAM by Meta AI01:00 - Setting up Your Python Environment02:46 - Loading the Segment Anything Model03:09 - Automated Mask Generation with SAM06:36 - Generate Segmentation Mask with Bounding Box10:02 - Convert Object Detection Dataset into Segmentation Masks12:01 - OutroResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com✏️ Roboflow Annotate power by SAM: blog.roboflow.com/label-data-segment-anything-model-sam📚 How to Use the Segment Anything Model (SAM) blog post: blog.roboflow.com/how-to-use-segment-anything-model-sam📓 How to Segment Anything with SAM notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-segment-anything-with-sam.ipynb🎬 Segment Anything Model (SAM) Breakdown YouTube video: youtu.be/umurJ8GsuH0🔥 Automated Data Labeling with SAM: youtu.be/oEQYStnF2l8💻 Segment Anything Model repository: github.com/facebookresearch/segment-anything🌌 Access the Segment Anything Model (SAM) and corresponding dataset (SA-1B) of 1B masks and 11M images: segment-anything.com/dataset/index.html📚 Segment Anything arXiv paper: arxiv.org/pdf/2304.02643.pdfOn July 29th, 2024, Meta AI released Segment Anything 2 (SAM 2), a new image and video segmentation foundation model. According to Meta, SAM 2 is 6x more accurate than the original SAM model at image segmentation tasks. Learn more: blog.roboflow.com/what-is-segment-anything-2Stay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest breakthroughs in technology! 🚀#MetaAI #SegmentAnythingModel #SAM #ImageSegmentation #Python #FoundationModels #ComputerVision #ZeroShot
AWS Startup Showcase - AI/ML Top Startups: Roboflow sponsored by Intel Roboflow 2023-04-08 | S3 E1 | "Enabling Developers to Build with Computer Vision" presented by AWS and sponsored by Intel
Segment Anything Model (SAM) Breakdown | Computer Vision Breakthrough Roboflow 2023-04-07 | Facebook released the Segment Anything model showcasing impressive zero-shot inference capabilities and comes with the promise of becoming a new foundational model for computer vision applications.Accompanying blog post: blog.roboflow.com/segment-anything-breakdownUse SAM in Roboflow to label data: blog.roboflow.com/label-data-segment-anything-model-samAutomated data labeling with SAM: youtu.be/oEQYStnF2l8Interactive Segment Anything Experience: segment-anything.comGithub repo: github.com/facebookresearch/segment-anythingarXiv paper: arxiv.org/abs/2304.02643How to use SAM: blog.roboflow.com/how-to-use-segment-anything-model-samOn July 29th, 2024, Meta AI released Segment Anything 2 (SAM 2), a new image and video segmentation foundation model. According to Meta, SAM 2 is 6x more accurate than the original SAM model at image segmentation tasks. Learn more: blog.roboflow.com/what-is-segment-anything-2
Grounding DINO: Automated Dataset Annotation and Evaluation | SOTA Zero-Shot Object Detector Roboflow 2023-04-06 | Description: Dive deeper into Grounding DINO, the state-of-the-art zero-shot object detector, as we automate dataset annotation and evaluation. Learn how to set up the Python environment, load the model, and evaluate Grounding DINO on custom datasets from Roboflow Universe. This is Part 2 of our series, building on our previous video "Detect Anything You Want with Grounding DINO". #GroundingDINO #ObjectDetection #DatasetAnnotation #AIModel #LanguageModelChapters:00:00 Introduction01:06 Notebook Overview01:34 Setting up the Python environment02:35 Load Grounding DINO model03:48 Download Dataset from Roboflow Universe04:44 Single Image Model Evaluation05:35 Evaluate Grounding DINO on Custom Dataset10:30 Dataset Auto Annotation with Grounding DINO13:18 OutroResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📓 Automated Dataset Annotation and Evaluation with Grounding DINO notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/automated-dataset-annotation-and-evaluation-with-grounding-dino.ipynb🔥 Automated Dataset Annotation with Segment Anything and Grounding DINO: youtu.be/oEQYStnF2l8🗞 Grounding DINO blog post: blog.roboflow.com/grounding-dino-zero-shot-object-detection🗞 Grounding DINO arXiv paper: arxiv.org/abs/2303.05499💻 Grounding DINO repository: github.com/IDEA-Research/GroundingDINO🎬 Detect Anything You Want with Grounding DINO | Zero-Shot Object Detection SOTA: youtu.be/cMa77r3YrDk🎬 GPT 4: Will We Ever Train Again?: youtu.be/aNLl0wEdMq4🎬 CLIP: OpenAI's amazing new zero-shot image classifier: youtu.be/8o701AEoZ8IStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
ROAST: Computer Vision Projects Roboflow 2023-04-01 | There are a lot of BAD computer vision datasets out there. Let's learn by taking one and making it better. Livestream with Roboflow's SDR for a Day: Brad Dwyer.
Detect Anything You Want with Grounding DINO | Zero Shot Object Detection SOTA Roboflow 2023-03-28 | Discover Grounding DINO, a groundbreaking AI model that seamlessly locates objects in images and matches them with corresponding textual labels. Learn how Grounding DINO revolutionizes object detection and text recognition tasks. #GroundingDINO #ObjectDetection #AIModel #LanguageModel Chapters:00:00 Introduction01:29 Setting up the Python environment03:11 Loading GroundingDINO model04:38 Multimodal deep learning05:23 Running GroundingDINO on custom images06:21 Prompt engineering and object detection language constraints07:36 Multiclass detection09:12 More object detection language constraints11:19 Dataset auto labeling with Roboflow and GroundingDINO12:48 OutroResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com📓 Grounding DINO notebook: github.com/roboflow/notebooks/blob/main/notebooks/zero-shot-object-detection-with-grounding-dino.ipynb🗞 Grounding DINO blog post: blog.roboflow.com/grounding-dino-zero-shot-object-detection🗞 Grounding DINO arXiv paper: arxiv.org/abs/2303.05499💻 Grounding DINO repository: github.com/IDEA-Research/GroundingDINO🎬 GPT 4: Will We Ever Train Again?: youtu.be/aNLl0wEdMq4🎬 CLIP: OpenAI's amazing new zero-shot image classifier: youtu.be/8o701AEoZ8IStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
Build Computer Vision Applications Faster with Supervision Roboflow 2023-03-27 | Do you feel like every time you start a new computer vision project, you write lots of code that you’ve already written before?Writing the same code over and over again is exhausting. That’s why we decided to create Supervision, an open-source toolkit for any computer vision project. Whether you want to process a video, draw a detection on a frame, or convert labels from one format to another; we’ve got you covered!Chapters:00:00 Introduction01:06 Documentation and Examples02:13 Supervision Roadmap03:17 OutroResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com⭐ Supervision repository: github.com/roboflow/supervision📄 Supervision documentation: roboflow.github.io/supervision🎬 Track & Count Objects using YOLOv8 ByteTrack & Supervision: youtu.be/OS5qI9YBkfk🎬 Count People in Zone | Using YOLOv5, YOLOv8, and Detectron2 | Computer Vision: youtu.be/l_kf9CfZ_8M🎬 YOLOv8 Object Counting in Real-time with Webcam, OpenCV and Supervision: youtu.be/QV85eYOb7gkStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
GPT 4: Will We Ever Train Again? Roboflow 2023-03-16 | Are general models going to obviate the need to label images and train models? Has YOLO only lived once? How soon will general models be adopted throughout the industry? What tasks will benefit the most from general model inference and what tasks will remain difficult?Here, we share initial speculations on the answers to these questions and reflect on where the industry is heading. Let’s dive in!
Roboflow 6 Minute Intro | Build a Coin Counter with Computer Vision Roboflow 2023-03-15 | Create a dataset and train a model that can see individual coins, sum their value, and run in real-time (or via API). This step-by-step video demonstrates an overview of how Roboflow accelerates building vision capabilities, including from image collection to annotation and training to deployment and improvement. For a deeper dive, reference our docs: docs.roboflow.comProject available on Universe: universe.roboflow.com/corn-counting/money-counter/health
YOLOv8 native tracking | Step-by-step tutorial | Tracking with Live Webcam Stream Roboflow 2023-03-10 | The YOLOv8 team just released (March 9, 2023) native support for object tracking algorithms (ByteTrack and BoT-SORT): docs.ultralytics.com/tasks/trackingThe video will show you how to use the new YOLOv8 object tracking functionality using a live webcam stream.Whether you're an experienced developer or a beginner in the field of computer vision, this video covers everything you need to know to get started with object tracking using YOLOv8. With step-by-step instructions, you'll learn how to use state-of-the-art deep-learning models to track objects in videos and live streams.Chapters:00:00 Introduction00:44 Setup Python environment01:28 Real-time object tracking in the terminal with YOLOv8 CLI02:17 Bulk video tracking with YOLOv8 SDK04:56 Setting up inference loop with YOLOv8 SDK06:11 Bounding box annotation with Supervision08:18 YOLOv8 tracking ⭐10:26 Real-time object counting with Supervision12:57 ConclusionResources: ⭐ GitHub repository with demo project: github.com/SkalskiP/yolov8-native-tracking🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com⭐ Supervision repository: github.com/roboflow/supervision🎬 Track & Count Objects using YOLOv8 ByteTrack & Supervision: youtu.be/OS5qI9YBkfk🎬 Count People in Zone | 3 Models: YOLOv5, YOLOv8 and Detectron2: youtu.be/l_kf9CfZ_8M🎬 YOLOv8 Object Counting in Real-time with Webcam, OpenCV, and Supervision: youtu.be/QV85eYOb7gk🎬 YOLOv8: How to Train for Object Detection on a Custom Dataset: youtu.be/wuZtUMEiKWY📓 Learn more about YOLOv8 and other Computer Vision models with Roboflow Notebooks: github.com/roboflow/notebooksStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
How to Train DETR Object Detection Transformer on Custom Dataset Roboflow 2023-03-03 | In this tutorial, we'll show you how to train Object Detection Transformers using DETR as an example. We'll guide you through every step of the process, starting with setting up your Python environment and demonstrating DETR model inference on example images.Next, we'll show you how to download custom datasets from Roboflow Universe and build custom PyTorch COCO Detection datasets. We'll also cover how to visualize COCO dataset entries and build custom PyTorch data loaders.At the core of this tutorial, we'll demonstrate how to build a custom PyTorch Lightning DETR module for training your own object detection model. We'll then guide you through training DETR on your custom dataset, followed by custom DETR model inference and evaluation.Chapters:0:00 Introduction1:06 Setting up the Python environment3:19 DETR model inference on example images8:40 Download custom dataset from Roboflow Universe10:31 Building custom PyTorch COCO Detection datasets12:25 Visualising COCO datasets entry13:15 Building custom PyTorch Data Loaders15:59 Building custom PyTorch Lightning DETR Module18:50 Training DETR on custom dataset20:06 Custom DETR model inference22:07 Evaluating custom DETR model22:40 OutroResources: 🌏 Roboflow: roboflow.com🌌 Roboflow Universe: universe.roboflow.com🗒️ How to Train DETR with 🤗 Transformers on a Custom Dataset notebook: colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/train-huggingface-detr-on-custom-dataset.ipynb🤗 Transformers DETR documentation: huggingface.co/docs/transformers/model_doc/detr🎬 Exploring The COCO Dataset YouTube video: youtu.be/B4gNml3V2cc⌛ PyTorch Data Loader documentation: pytorch.org/docs/stable/data.html#torch.utils.data.DataLoader⚡PyTorch Lightning Module documentation: pytorch-lightning.readthedocs.io/en/stable/common/lightning_module.htmlStay updated with the projects I'm working on at github.com/roboflow and github.com/SkalskiP! ⭐
