Applied AI | PyTorch From Research to Production | Nvidia GTC 2020

Опубликовано: 19 Март 2026
на канале: DSAI by Dr. Osbert Tay
877
38

Join the channel membership:
   / aipursuit  

Subscribe to the channel:
https://www.youtube.com/c/AIPursuit?s...

Support and Donation:
Paypal ⇢ https://paypal.me/tayhengee
Patreon ⇢   / hengee  

The video is reposted for educational purposes and encourages involvement in the field of research.
Video Source: https://resources.nvidia.com/events/G...

Video Title: GTC2020 PyTorch from Research to Production


Grzegorz Karch, NVIDIA
GTC 2020
Learn how to get your neural network from the PyTorch framework into production. Explore ways to handle complex neural network architectures during deployment. We'll show how to transform a neural network developed in PyTorch into a model ready for a production environment and exemplify the workflow on a conversational AI system. For full understanding, you should be familiar with PyTorch framework and have some interest in model deployment for inference. Well demonstrate the neural network system on TensorRT Inference Server (TRTIS).

Slides: https://developer.nvidia.com/gtc/2020...

Nvidia has a lot of essential tutorials, research talks and cutting edge hardwares for deep learning. They also provide their own custom pretrained models for various tasks. To find out more, you can check these site:

1. NVIDIA GPU Cloud (NGC): https://ngc.nvidia.com/catalog/collec...
2. Transfer Learning Toolkit: https://developer.nvidia.com/transfer...
3. Training with Custom Pretrained Models Using the NVIDIA Transfer Learning Toolkit: https://developer.nvidia.com/blog/tra...

Connect with Experts
https://resources.nvidia.com/events/G...
We will talk about the latest Deep Learning developments. We will also discuss how to increase training/inference performance by taking advantage of Tensor Cores.