Tutorial

Table of Contents Synthetic Data Generation Using the BLIP and PaliGemma Models Why VLM-as-Judge and Synthetic VQA Configuring Your Development Environment Set Up and Imports Download Images Locally Inference with the Salesforce BLIP Model Convert JSON File to the Hugging…

Table of Contents Fine Tuning SmolVLM for Human Alignment Using Direct Preference Optimization What Is Preference Optimization? Types of Techniques Reinforcement Learning from Human Feedback (RLHF) Reinforcement Learning from AI Feedback (RLAIF) Direct Preference Optimization (DPO) Identity Preference Optimization (IPO)…

Table of Contents Run YOLO Model in the Browser with ONNX, WebAssembly, and Next.js What Is Browser-Based Inference and Why Does It Matter? Why Run YOLO in the Browser? No Server Required Instant Demos and Prototypes Low Latency and High…

Table of Contents Training YOLOv12 for Detecting Pothole Severity Using a Custom Dataset Introduction Dataset and Task Overview About the Dataset What Are We Detecting? Defining Pothole Severity Can the Pothole Severity Logic Be Improved? Configuring Your Development Environment Training…

Table of Contents People Tracker with YOLOv12 and Centroid Tracker Introduction Why People Tracker Monitoring Matters How YOLOv12 Enables Real-Time Applications Configuring Your Development Environment Downloading the Input Video Install gdown Download the Video Visualizing the Inference and Tracking Pipeline…

Table of Contents Breaking the CNN Mold: YOLOv12 Brings Attention to Real-Time Object Detection The YOLO Evolution (Quick Recap) YOLOv8: Introducing the C2f Module and OBB Support YOLOv9: Programmable Gradient Information and GELAN YOLOv10: NMS-Free Training and Dual Assignments YOLOv11:…

Table of Contents Generating Video Highlights Using the SmolVLM2 Model Configuring Your Development Environment Setup and Imports Setup Logger Get Video Duration in Seconds Load Model and Processor Analyze Video Content Determine Highlights Process Video Segment Concatenating Video Scenes into…

Table of Contents SmolVLM to SmolVLM2: Compact Models for Multi-Image VQA SmolVLM 1: A Compact Yet Capable Vision-Language Model What Is SmolVLM? Why SmolVLM? The Three Variants of SmolVLM Architecture Overview Vision Encoder: SigLIP Variants Pixel Shuffle (Space-to-Depth) for Image…

Table of Contents Video Understanding and Grounding with Qwen 2.5 Enhanced Video Comprehension Ability in Qwen 2.5 Models Dynamic Frame Rate (FPS) and Absolute Time Encoding Multimodal Rotary Position Embedding (MRoPE) Robustness Through Training Innovations Hands-On Qwen2.5 for Video Understanding…