Computer Vision Meetup: Optimizing Dist Workloads for Stable Diffusion w/ Intel & PyTorch on AWS

preview_player
Показать описание
In this talk, we explore the use of the Intel Extension for PyTorch to optimize a vision generative AI workload. The vision workload focuses on the fine-tuning of a stable diffusion model, on the AWS cloud using Intel’s 4th Generation Xeon Processors. We leverage optimizations like Intel Advanced Matrix Extensions (AMX) and mixed-precision with BF16 and FP32, to speed up training. Attendees can expect (1) A technical dive into the workload and solution (2) a brief code walkthrough (3) workload setup on AWS, and (4) a short demo.

Eduardo Alvarez is a Senior AI Solutions Engineer at Intel.

Scroll down on this page and join the Computer Vision Meetup friendliest to your timezone:

Recorded on Sept 14, 2023 at the virtual Computer Vision Meetup.

#computervision #machinelearning #datascience #ai #artificialintelligence
  1. Voxel51
Рекомендации по теме
Computer Vision Meetup: 0:35:16

Computer Vision Meetup: Optimizing Dist Workloads for Stable Diffusion w/ Intel & PyTorch on AWS

Computer Vision Meetup: 0:40:07

Computer Vision Meetup: Breaking the Bottleneck of AI Deployment at the Edge with OpenVINO

Computer Vision Meetup: 0:40:41

Computer Vision Meetup: Machine Learning for Fast, Motion-Robust MRI

Computer Vision Meetup: 0:40:21

Computer Vision Meetup: Fast and Flexible Data Discovery & Mining at Petabyte Scale

Computer Vision Meetup: 0:41:22

Computer Vision Meetup: Using Similarity Learning to Improve Data Quality

Computer Vision Meetup: 0:36:06

Computer Vision Meetup: Strategies for Enhancing the Adoption of OSS: Albumentations.ai Case Study

Computer Vision Meetup: 0:33:51

Computer Vision Meetup: Retail Supply Chain Computer Vision Apps

Computer Vision Meetup: 0:49:19

Computer Vision Meetup: Leveraging Attention for Improved Accuracy and Robustness

Computer Vision Meetup: 0:30:01

Computer Vision Meetup: Adapting to Change: Foundation Models, APIs, Past, Present and Future of AI

Computer Vision Meetup: 0:36:15

Computer Vision Meetup: To Infer or To Defer: Hazy Oracles in Human+AI Collaboration

Computer Vision Meetup: 0:32:01

Computer Vision Meetup: Re-Annotating MS COCO, an Exploration of Pixel Tolerance

Computer Vision Meetup: 0:21:35

Computer Vision Meetup: Towards Resource Efficient Robust Text-to-Image Generative Models

Computer Vision Meetup: 0:34:50

Computer Vision Meetup: SyntStereo2Real: Edge-Aware GAN for Remote Sensing Image Translation

Computer Vision Meetup: 0:34:33

Computer Vision Meetup: Deci Diffusion - Triple the Speed of Stable Diffusion

Computer Vision MeetUp 0:36:00

Computer Vision MeetUp - Zero Tolerance for Error

Getting High-Quality Data 0:49:33

Getting High-Quality Data for Computer Vision Models

Computer Vision Meetup: 0:29:43

Computer Vision Meetup: Bridging Real-World Applications with Anomalib at the CVPR VAND Challenge

Computer Vision: How 0:19:30

Computer Vision: How to speed up ML deployment using data-centric AI practices

Computer Vision Meetup: 0:13:16

Computer Vision Meetup: Advancing Personalized Medicine and Radiotherapy through AI-Enabled CV

Computer Vision Meetup: 0:29:54

Computer Vision Meetup: Discover the Hidden Biases of an Image Classifier

Meetup: Automated Monitoring 0:47:53

Meetup: Automated Monitoring for Optimizing User Experience in Consumer Products

Neural Network Pruning 0:43:25

Neural Network Pruning in Computer Vision // Computer Vision Meetup // December 2020

Tricks in Computer 0:43:03

Tricks in Computer Vision and Ensembling

VeLO - Learning 1:17:06

VeLO - Learning to Optimize Training