Roboflow Courses

How to Train Object Detection Transformer on Custom Dataset

1 review

Learn to train Object Detection Transformers using DETR, from environment setup to custom dataset training and model evaluation. Covers PyTorch, COCO datasets, and PyTorch Lightning for efficient deep learning workflows.

• YouTube
• 23 minutes
• On-Demand
• Free Video

CLIP, T-SNE, and UMAP - Master Image Embeddings and Vector Analysis

Master image embeddings and vector analysis techniques like CLIP, T-SNE, and UMAP. Learn to cluster MNIST images, detect duplicates, and explore essential concepts in computer vision and data science through hands-on practice.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking

Learn real-time traffic analysis using YOLOv8 and ByteTrack for vehicle detection and tracking on aerial images. Explore zone assignment, movement direction, and traffic flow visualization with Python and Supervision.

• YouTube
• 23 minutes
• On-Demand
• Free Video

Accelerate Image Annotation with SAM and Grounding DINO - Python Tutorial

Learn to accelerate image annotation using Grounding DINO and Segment Anything Model (SAM). Convert object detection datasets to instance segmentation and explore automatic annotation for real-time detectors like YOLOv8.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Count People in Zone - Using YOLOv5, YOLOv8, and Detectron2 - Computer Vision

Learn to detect and count objects in polygon zones using YOLOv5, YOLOv8, and Detectron2. Explore real-world examples and leverage the Supervision library for advanced computer vision analytics.

• YouTube
• 21 minutes
• On-Demand
• Free Video

Track & Count Objects Using YOLOv8, ByteTrack & Supervision

Build an application to track and count objects using YOLOv8 for detection, ByteTrack for tracking, and Supervision for counting. Learn to set up the environment, create custom pipelines, and train models on custom datasets.

• YouTube
• 26 minutes
• On-Demand
• Free Video

Is Machine Learning Smarter Than a Toddler? - Roboflow + OpenCV Webinar

Explore how AI and ML compare to toddlers in object recognition, drawing, and writing. Gain insights into the current capabilities and limitations of machine learning technology.

• YouTube
• 59 minutes
• On-Demand
• Free Video

How to Use the Roboflow Upload API - Python

Learn to programmatically add images and annotations to datasets using Roboflow's Upload API, enabling active learning and continuous improvement of computer vision models.

• YouTube
• 21 minutes
• On-Demand
• Free Video

How to Build a Detectron2 Model with Roboflow and Paperspace Gradient

Learn to build a Detectron2 model using Roboflow for image preprocessing and Paperspace Gradient for GPU-backed training. Covers dataset access, image augmentation, and model development.

• YouTube
• 1 hour
• On-Demand
• Free Video

Intro to Computer Vision - Fireside

Explore computer vision fundamentals, from basic concepts to problem-solving approaches, model building, and ethical considerations in this comprehensive introduction.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Model Evaluation for Computer Vision - Precision, Recall, F1 Score, and Confusion Matrix

Explore key metrics for evaluating computer vision models, including precision, recall, F1 score, and confusion matrices, to enhance your understanding of model performance.

• YouTube
• 26 minutes
• On-Demand
• Free Video

Football AI Tutorial: From Basics to Advanced Stats with Python

Learn to build an AI system for advanced football analytics using computer vision and machine learning. Covers player tracking, team identification, and stats calculation like ball possession and speed.

• YouTube
• 1 hour 30 minutes
• On-Demand
• Free Video

Active Learning in Computer Vision

Discover techniques for creating active learning pipelines to leverage production data in training advanced computer vision models.

• YouTube
• 14 minutes
• On-Demand
• Free Video

Advanced Computer Vision Workflows with Foundation and Custom Models

Build computer vision applications by combining foundation models like Segment Anything 2 with custom trained models like YOLOv8, using Roboflow Workflows for efficient and powerful image processing pipelines.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Computer Vision Hardware Configuration - Cameras, Lenses, and GPUs for Vision AI

Explore essential hardware components for vision AI: cameras, lenses, and GPUs. Learn selection criteria and deployment options for optimal computer vision systems.

• YouTube
• 16 minutes
• On-Demand
• Free Video