GitHub - roboflow/notebooks: A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like YOLO11, RT-DETR, SAM 2, Florence-2, PaliGemma 2, and Qwen2.5VL.
Blog post from Roboflow
This repository provides a comprehensive collection of tutorials on state-of-the-art computer vision models, covering a wide range of tasks such as object detection, segmentation, pose estimation, and optical character recognition (OCR). Featuring models like YOLOv11, SAM 2, Florence-2, and others, it offers 55 notebooks that can be accessed via platforms like Colab, Kaggle, and SageMaker Studio Lab. The tutorials include step-by-step guides on fine-tuning models on custom datasets, zero-shot object detection, and segmenting images and videos. Additional resources include video content that explores model selection, dataset annotation, and the capabilities of Meta AI's Segment Anything Model (SAM). Users are encouraged to contribute by reporting bugs or suggesting new tutorials, ensuring the repository remains up-to-date with rapid advancements in computer vision technology.