Update events

_events/multi-modal-dl-frame.md

@@ -11,8 +11,8 @@ poster: assets/images/multi-modal-dl-frame.png
 <img style="width:100%" src="/assets/images/multi-modal-dl-frame.png" alt="Multi-Modal Tabular Deep Learning with PyTorch Frame">
 </a>
 
-In this talk, Akihiro introduces PyTorch Frame, a modular framework for multi-modal tabular deep learning. PyTorch Frame enables seamless integration with the PyTorch ecosystem, including PyTorch Geometric for graph-based message passing across relational data and Hugging Face Transformers for extracting rich text features. The talk also highlights its specialized data structures for efficiently handling sparse features, making PyTorch Frame an essential tool for modern tabular data.
+In this talk, Akihiro introduced PyTorch Frame, a modular framework for multi-modal tabular deep learning. PyTorch Frame enables seamless integration with the PyTorch ecosystem, including PyTorch Geometric for graph-based message passing across relational data and Hugging Face Transformers for extracting rich text features. The talk also highlights its specialized data structures for efficiently handling sparse features, making PyTorch Frame an essential tool for modern tabular data.
 
 Akihiro Nitta is a software engineer on the ML team at Kumo.ai and a core contributor to PyTorch Frame and PyTorch Geometric, with prior experience as a maintainer of PyTorch Lightning.
 
-[Register now to join the event](/multi-modal-dl-frame)
+[Learn more about the event](/multi-modal-dl-frame)

_events/pt-dinov2-multi-label-plant-species-classification.md

@@ -0,0 +1,18 @@
+---
+category: event
+title: "Using PyTorch and DINOv2 for Multi-label Plant Species Classification"
+date: March 27
+poster: assets/images/pt-dinov2-multi-label-plant-species-classification.png
+---
+
+**Date**: March 27th, 12 PM PST
+
+<a href="/pt-dinov2-multi-label-plant-species-classification">
+<img style="width:100%" src="/assets/images/pt-dinov2-multi-label-plant-species-classification.png" alt="Using PyTorch and DINOv2 for Multi-label Plant Species Classification">
+</a>
+
+Join us for an engaging webinar on our innovative transfer learning approach using self-supervised Vision Transformers (DINOv2) for multi-label plant species classification in the PlantCLEF 2024 challenge. We’ll cover how we efficiently extract feature embeddings from a dataset of 1.4 million images and utilize PyTorch Lightning for model training and Apache Spark for data management. Learn about our image processing techniques, including transforming images into grids of tiles and aggregating predictions to overcome computational challenges. Discover the significant performance improvements achieved and get insights into multi-label image classification. Perfect for PyTorch developers, this session will include a Q&A and access to our complete codebase at [github.com/dsgt-kaggle-clef/plantclef-2024](https://github.com/dsgt-kaggle-clef/plantclef-2024).
+
+Murilo Gustineli is a Senior AI Software Solutions Engineer at Intel, and is currently pursuing a Master’s in Computer Science at Georgia Tech focusing on machine learning. His work involves creating synthetic datasets, fine-tuning large language models, and training multi-modal models using Intel® Gaudi® Al accelerators as part of the Development Enablement team. He is particularly interested in deep learning, information retrieval, and biodiversity research, aiming to improve species identification and support conservation efforts.
+
+[Register now to join the event](/pt-dinov2-multi-label-plant-species-classification)

multi-modal-dl-frame.html

@@ -25,15 +25,14 @@ <h2>Multi-Modal Tabular Deep Learning with PyTorch Frame</h2>
           <br/>
           <strong>Speaker</strong>: Akihiro Nitta, Software Engineer, Kumo.ai
           <br/>
-          <strong>Location</strong>: Online
+          <a href="https://www.youtube.com/live/zPjLHf0X78w?feature=shared">Link to session video</a>
           <br/>
+          <a href="/assets/pytorch-frame-expert-exchange.pdf">Download slides</a>
           <br/>
-          In this talk, Akihiro introduces PyTorch Frame, a modular framework for multi-modal tabular deep learning. PyTorch Frame enables seamless integration with the PyTorch ecosystem, including PyTorch Geometric for graph-based message passing across relational data and Hugging Face Transformers for extracting rich text features. The talk also highlights its specialized data structures for efficiently handling sparse features, making PyTorch Frame an essential tool for modern tabular data.
+          <br/>
+          In this talk, Akihiro introduced PyTorch Frame, a modular framework for multi-modal tabular deep learning. PyTorch Frame enables seamless integration with the PyTorch ecosystem, including PyTorch Geometric for graph-based message passing across relational data and Hugging Face Transformers for extracting rich text features. The talk also highlights its specialized data structures for efficiently handling sparse features, making PyTorch Frame an essential tool for modern tabular data.
           <br/><br/>
           Akihiro Nitta is a software engineer on the ML team at Kumo.ai and a core contributor to PyTorch Frame and PyTorch Geometric, with prior experience as a maintainer of PyTorch Lightning.
-          <br/><br/>
-          <strong>Register now to attend this event.</strong>
-          <div style="width:100%;position:relative;padding-bottom:56.25%;min-height:550px;"><iframe src="https://streamyard.com/watch/wqmSrhffEigi?embed=true"  width="100%" height="100%" frameborder="0" allow="autoplay; fullscreen" style="width:100%;height:100%;position:absolute;left:0px;top:0px;overflow:hidden;"></iframe></div>
         </p>
       </div>
     </div>

pt-dinov2-multi-label-plant-species-classification.html

@@ -0,0 +1,39 @@
+---
+layout: default
+title: "Using PyTorch and DINOv2 for Multi-label Plant Species Classification"
+body-class: announcement
+background-class: announcement-background
+permalink: /pt-dinov2-multi-label-plant-species-classification
+---
+
+<div class="container">
+  <div class="row hero-content">
+    <div class="col-md-10">
+      <h1>PyTorch Webinars</h1>
+    </div>
+  </div>
+</div>
+
+<div class="container-fluid light-background-section">
+  <div class="container">
+    <div class="row content">
+      <div class="col-md-10 body-side-text">
+        <img style="width:100%; max-width:600px; margin-bottom: 40px; display: block; margin-left: auto; margin-right: auto;" src="/assets/images/pt-dinov2-multi-label-plant-species-classification.png" alt="Using PyTorch and DINOv2 for Multi-label Plant Species Classification">            
+        <h2>Using PyTorch and DINOv2 for Multi-label Plant Species Classification</h2>
+        <p class="lead">
+          <strong>Date</strong>: March 27th, 12 PM PST
+          <br/>
+          <strong>Speaker</strong>: Murilo Gustineli
+          <br/>
+          <br/>
+          Join us for an engaging webinar on our innovative transfer learning approach using self-supervised Vision Transformers (<a href="https://dinov2.metademolab.com/">DINOv2</a>) for multi-label plant species classification in the PlantCLEF 2024 challenge. We’ll cover how we efficiently extract feature embeddings from a dataset of 1.4 million images and utilize PyTorch Lightning for model training and Apache Spark for data management. Learn about our image processing techniques, including transforming images into grids of tiles and aggregating predictions to overcome computational challenges. Discover the significant performance improvements achieved and get insights into multi-label image classification. Perfect for PyTorch developers, this session will include a Q&A and access to our complete codebase at <a href="https://github.com/dsgt-kaggle-clef/plantclef-2024">github.com/dsgt-kaggle-clef/plantclef-2024</a>.
+          <br/><br/>
+          Murilo Gustineli is a Senior AI Software Solutions Engineer at <a href="https://www.intel.com/">Intel</a>, and is currently pursuing a Master’s in Computer Science at <a href="https://www.gatech.edu/">Georgia Tech</a> focusing on machine learning. His work involves creating synthetic datasets, fine-tuning large language models, and training multi-modal models using Intel® Gaudi® Al accelerators as part of the Development Enablement team. He is particularly interested in deep learning, information retrieval, and biodiversity research, aiming to improve species identification and support conservation efforts. <a href="https://github.com/murilogustineli">Visit Murilo on GitHub</a>.
+          <br/><br/>
+          <strong>Register now to attend this event.</strong>
+          <div style="width:100%;position:relative;padding-bottom:56.25%;min-height:550px;"><iframe src="https://streamyard.com/watch/n3VHFdzXfCae?embed=true"  width="100%" height="100%" frameborder="0" allow="autoplay; fullscreen" style="width:100%;height:100%;position:absolute;left:0px;top:0px;overflow:hidden;"></iframe></div>
+        </p>
+      </div>
+    </div>
+  </div>
+</div>