Summary
π» Register for Poll
π»Welcome to Alta3 Live
Learning Your Environment
π» Using Vim
π» Tmux
π» VScode Integration
π» Revision Control with GitHub
The Visual Transformer Model
π¬ What is Intelligence?
π¬ Generative AI
π¬ The Transformer Model
π¬ Feed Forward Neural Networks
Computer Vision
π¬ Introduction to Computer Vision
π¬ NLP to ViT: Key Modifications
π» Patch Embedding
π» Positional Encoding in Vison Transformer
π¬ CNN vs ViT - A Comparison
Pre-trained ViT
π¬ Preparing A100 for Server Operations
π¬ Selecting a Pre-Trained ViT Model
π» Operating Google ViT Model for Face Recognition
π» Operating Microsoft BEiT Model for Scene Segmentation
Data Curation for Road Surface ViT
π¬ Curating Data for ViT
π» Gathering Raw Data
π» Data Cleaning and Preparation
π» Data Labeling
π» Data Organization
π¬ Premade Datasets for Fine Tuning
π» Obtain and Prepare Premade Datasets
Fine Tuning for Road Surface Image Classification
π¬ Fine-Tuning a Pre-Trained ViT
π¬ PyTorch
π» Fine Tuning ViT with PyTorch
π» Operating our Road Surface Image Classification ViT Model