Computer Vision

Businesses worldwide are using artificial intelligence to solve their greatest challenges.

Build and train a classification data set and model with the NVIDIA Jetson Nano.

Deploy a deep learning model to automate disaster management use cases.

Learn how deep learning works through hands-on exercises in computer vision and natural language processing.

Learn the skills you need to enable real-time transformation of raw video data from widely-deployed camera sensors into deep learning-based insights.

Build and train a classification data set and model with the NVIDIA Jetson Nano.

The notebook explores the biological inspiration for early neural networks.

Whether companies are manufacturing semiconductor chips, airplanes, automobiles, smartphones, or food or beverages, quality and throughput are key benefits of optimization.

In this course you'll learn the end-to-end development workflow for generating synthetic data using Transformers, including data preprocessing, model pre-training, fine-tuning, inference, and evaluation.

About This Course Very large deep neural networks (DNNs), whether applied to natural language processing (e.g., GPT-3), computer vision (e.g., huge Vision Transformers), or speech AI (e.g., Wave2Vec 2) have certain properties that set them apart from their smaller counterparts. As DNNs become larger and are trained on progressively larger datasets, they can adapt to new tasks with just a handful of training examples, accelerating the route toward general artificial intelligence. Training models that contain tens to hundreds of billions of parameters on vast datasets isn’t trivial and requires a unique combination of AI, high-performance computing (HPC), and systems knowledge. In this workshop, participants will learn how to: Train neural networks across multiple servers Use techniques such as activation checkpointing, gradient accumulation, and various forms of model parallelism to overcome the challenges associated with large-model memory footprint Capture and understand training performance characteristics to optimize model architecture Deploy very large multi-GPU models to production using NVIDIA Triton™ Inference Server The goal of this course is to demonstrate how to train the largest of neural networks and deploy them to production. Requirements Familiarity with: Good understanding of PyTorch Good understanding of deep learning and data parallel training concepts Practice with deep learning and data parallel are useful, but optional Tools, libraries, frameworks used: PyTorch, Megatron-LM, DeepSpeed, Slurm, Triton Inference Server Related Training Building Transformer-Based Natural Language Processing Applications Learn how to use Transformer-based natural language processing models for text classification tasks, such as categorizing documents. Fundamentals of Deep Learning for Multi-GPUs echniques for training deep neural networks on multi-GPU technology to shorten the training time required for data-intensive applications. For additional hands-on training through the NVIDIA Deep Learning Institute, visit www.nvidia.com/dli .

Build foundational skills in robotics simulation and control with Isaac Sim, the first step in the Isaac Sim Learning Path.

Learn to import robotic assets, add sensors, and run simple simulations.

Learn to train and deploy perception models using synthetic data generation (SDG), applying domain randomization and simulation for real-world robotics.

Learn the fundamentals of Software in the Loop (SIL) using NVIDIA Isaac Sim and ROS 2 to test, validate, and develop robotics software in simulated environments.

Bridge the gap between simulation and real-world robotics using ROS 2, Isaac Sim, and NVIDIA Jetson with HIL.

An introduction to autonomous robots and robotic systems.

Assemble a virtual environment with robots and simulate and validate their basic movements with ROS (Robot Operating System) commands.

Learn how to accelerate ROS 2 workloads using NVIDIA’s latest GPU-powered libraries for AI and robotics.

Gain hands-on experience with Cosmos WFMs and tools to generate data to train physical AI.

Build, deploy, and scale domain-agnostic AI-enabled sensor processing applications.

Accelerate your robotics innovation with this hands-on workshop focused on simulation-first development, AI-powered perception, and synthetic data generation using NVIDIA Isaac.

Introducing reinforcement learning for robotics with Isaac Lab.

Going further with reinforcement learning for robotics with Isaac Lab.

This course provides a practical, end-to-end guide to building, training, and deploying autonomous medical robots using NVIDIA’s Isaac Sim and Isaac for Healthcare.