Online
May 26 & June 2, 2022
9:00 am - 12:00 pm EDT
Instructors: Fernando Cervantes Sanchez
Helpers:
Some adblockers block the registration window. If you do not see the registration box below, please check your adblocker settings.
Computer vision aims to understand visual content such as images, often to make predictions through classification, segmentation, objects detection and other applications. Deep Learning for Image Analysis with PyTorch will explore computer vision in a hands-on training on May 26 and June 2. PyTorch is an open source Python library designed to provide flexibility to researchers as a deep learning development platform.
Who: The course is aimed at Jackson Laboratory researchers who want to analyze large-scale image data. For IT security reasons, external participants cannot be admitted. You need to have Python programming experience to get the most from this workshop.
Where: This training will take place online. The instructors will provide you with the information you will need to connect to this meeting.
When: May 26 & June 2, 2022. Add to your Google Calendar.
Requirements: Participants must have access to a computer with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.). They should have a few specific software packages installed (listed below).
Accessibility: We are dedicated to providing a positive and accessible learning environment for all. Please notify the instructors in advance of the workshop if you require any accommodations or if there is anything we can do to make this workshop more accessible to you.
Contact: Please email fernando.cervantes@jax.org or susan.mcclatchy@jax.org for more information.
Roles: To learn more about the roles at the workshop (who will be doing what), refer to our Workshop FAQ.
Please be sure to complete these surveys before and after the workshop.
| 09:00 | Introduction |
| 09:50 | Getting started with PyTorch |
| 10:20 | Morning break |
| 10:30 | Implement a deep neural network |
| 11:50 | Wrap-up |
| 12:00 | END |
| 09:00 | Define the optimization problem |
| 09:30 | Implement the training loop pt 1 |
| 10:20 | Morning break |
| 10:30 | Implement the training loop pt 2 |
| 11:00 | Saving and loading PyTorch models |
| 11:10 | Monitoring and logging the training process |
| 11:45 | Post-workshop Survey |
| 11:50 | Wrap-up |
| 12:00 | END |
To participate in a workshop, you will need access to software as described below. In addition, you will need an up-to-date web browser.
We maintain a list of common issues that occur during installation as a reference for instructors that may be useful on the Configuration Problems and Solutions wiki page.