Event box

Vision Transformers: Using the transformer neural network architecture with images - Data Hub Tech Talk

Note: the session will be recorded for registrants who cannot attend at the scheduled time.

The transformer architecture is the basis for ChatGPT and other large language models. Transformers can be used with computer vision tasks by serializing images into sequences of patches. This architecture is arguably superior to traditional convolutional neural networks (CNNs) in several ways. We will build and test a Vision Transformer (ViT) from scratch in Python and demonstrate powerful, existing ViT Python libraries.

Date:
Tuesday, April 9, 2024
Time:
12:30pm - 1:30pm
Location:
Data Hub presentation / collaboration space
Campus:
University of Idaho - Moscow campus
Presenter:
Lucas Sheneman, Director - Research Computing and Data Services
Categories:
Data Hub Library Workshop
Registration has closed.

Upcoming Workshops

Time Zone: Pacific Time - US & Canada (change)

Jan
24
3:30pm - 5:00pm, Team 2 (Room 132), University of Idaho - Moscow campus.
Feb
7
3:30pm - 5:00pm, Team 2 (Room 132), University of Idaho - Moscow campus.
Feb
21
3:30pm - 5:00pm, Team 2 (Room 132), University of Idaho - Moscow campus.
Mar
18
11:00am - 11:50am, Second Floor Classroom, University of Idaho - Moscow campus.
Mar
18
1:00pm - 1:50pm, Second Floor Classroom, University of Idaho - Moscow campus.