On-Demand Technical Sessions: Develop and Deploy AI Solutions in the Cloud Using NVIDIA NGC

At GTC ’21, experts presented a variety of technical talks to help people new to AI, or those just looking for tools to speed-up their AI development using the…

NVIDIA logo
NVIDIA
•
Chintan Patel
•2 min read•intermediate•
--
•View Original
AWSAzureDaskHelmMachine LearningTransfer Learning

Overview

The article discusses on-demand technical sessions from GTC '21 that focus on developing and deploying AI solutions in the cloud using NVIDIA NGC. It highlights various components of the NGC catalog, such as AI containers, pretrained models, and industry-specific AI SDKs, along with specific sessions that demonstrate practical applications.

What You'll Learn

1

How to build a Text-to-Speech model using pretrained models

2

How to analyze traffic video streams using NVIDIA A100 GPUs

3

How to deploy AI/ML applications in Azure Machine Learning with minimal commands

4

Why using the NGC catalog can speed up AI application development

Key Questions Answered

How can I build a Text-to-Speech service that mimics my voice?
You can build a Text-to-Speech (TTS) service that sounds like you by fine-tuning a pretrained model with your own speech samples. This allows for customization in speech performance and style transfer from other speakers, enabling the TTS service to reflect your unique voice.
What tools are needed to analyze traffic video streams at scale?
To analyze traffic video streams at scale, you can use the Transfer Learning Toolkit along with pretrained models. This setup allows you to run inference on over 1,000 live video feeds using a single AWS instance powered by NVIDIA A100 GPUs, showcasing the capability of handling large-scale video data.
How do I deploy AI applications in Azure Machine Learning?
Deploying AI applications in Azure Machine Learning can be done with just two commands. The session demonstrates how to set up a DASK cluster with multiple Azure virtual machines, mount data, and deploy GPU-optimized AI software from the NGC catalog to train models and make predictions.
What is the benefit of using the NGC catalog for AI development?
The NGC catalog provides a variety of optimized AI containers, pretrained models, and industry-specific AI SDKs that can significantly speed up AI application development. It offers a comprehensive suite of tools that developers can leverage to build and deploy AI solutions more efficiently.

Key Statistics & Figures

Live video feeds processed
over 1,000
This statistic highlights the capability of the Transfer Learning Toolkit when used with NVIDIA A100 GPUs on a single AWS instance.

Technologies & Tools

Some links below are affiliate links. We may earn a commission if you make a purchase.

AI/ML Platform
Nvidia Ngc
Used for providing optimized AI containers, pretrained models, and SDKs for AI development.
Cloud Computing
AWS
Used to run inference on traffic video streams using NVIDIA A100 GPUs.
Cloud Computing
Azure Machine Learning
Platform used for deploying AI/ML applications with minimal commands.

Key Actionable Insights

1
Leverage pretrained models from the NGC catalog to accelerate your AI development process.
Using pretrained models can save significant time and resources, allowing developers to focus on customizing models for their specific use cases rather than starting from scratch.
2
Utilize the Transfer Learning Toolkit for building computer vision applications.
This toolkit simplifies the process of creating and deploying models for real-time video analysis, making it easier to handle large datasets and complex tasks.
3
Explore the benefits of deploying applications on Azure Machine Learning with minimal setup.
By using the NGC-AzureML Quick Launch Toolkit, developers can quickly set up their environments, which is especially useful for those looking to streamline their deployment processes.