William Guimont-Martin is a computer science researcher working on robotics, artificial intelligence, 3D perception, point clouds, and software. Zola 2023-03-23T00:00:00+00:00 https://willguimont.com/tags/transformers/atom.xml 2023-03-23T00:00:00+00:00 2023-03-23T00:00:00+00:00 William Guimont-Martin https://willguimont.com/blog/transformers/ <p>Here’s a small library I made to explain the Transformer architecture in PyTorch: <a class="external" href="https://github.com/willGuimont/transformers" target="_blank">willGuimont/transformers</a>. The code is heavily commented and should be easy to follow.</p> <p>This repository also contains some popular transformer-based models, such as Vision Transformer.</p> <p>This was made while developping new practical exercises for <a class="external" href="https://github.com/ulaval-damas/glo4030-labs" target="_blank">GLO-7030 at Université Laval</a>.</p> 2021-09-02T00:00:00+00:00 2021-09-02T00:00:00+00:00 William Guimont-Martin https://willguimont.com/blog/transformers-in-cv/ <p>On September 2nd 2021, I gave a talk on transformer-based neural network architectures for computer vision. I gave the in University Laval’s <a class="external" href="https://norlab.ulaval.ca/" target="_blank">Norlab</a>.</p> <p>Here are the slides: <a href="TransformersInComputerVision.pdf" target="_blank">Transformers in Computer Vision</a></p> <p>And here is the recording of the event:</p> <iframe class="youtube-embed" src="https://www.youtube-nocookie.com/embed/eaWXeXs8dh0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" referrerpolicy="strict-origin-when-cross-origin" allowfullscreen> </iframe>