What we're about

This virtual group (until it is safe to meet in person) is for data scientists, machine learning developers, MLOps engineers and open source enthusiasts who want to expand their knowledge of Kubeflow, the machine learning toolkit for Kubernetes.

- Are you interested in speaking at a future Meetup?
- Is your company interested in sponsoring a Meetup?
- Would you like to be a co-organizer of a local Meetup?

Contact the Meetup organizers!

This Meetup is sponsored by Arrikto, a leading Kubeflow contributor and developer of MLOps tools.

To learn more, visit their website: https://www.arrikto.com/

Upcoming events (4)

Cross Post: December '22 Computer Vision Meetup (Virtual)

Network event

Link visible for attendees

Zoom Link
https://us02web.zoom.us/webinar/register/9016698245637/WN_8u6oFjU7QN2StaQSWTw7HQ

Agenda

  • Housekeeping
  • Lightning Talk: Wearable Vision Sensors - Kris Kitani (Carnegie Mellon University)
  • The Future of Data Annotation: Trends, Problems & Solutions - Anna Petrovicheva (CVAT.AI)
  • Using Similarity Learning to Improve Data Quality - Kacper Łukawski (Qdrant)

Lightning Talk: Wearable Vision Sensors
Can wearable cameras be used to better understand human activity? This talk will introduce several new projects that show the potential of wearable cameras for measuring 3D human pose even when the full body is not visible in the camera view.

Kris M. Kitani is an associate research professor of the Robotics Institute at Carnegie Mellon University. His research projects span the areas of computer vision, machine learning and human computer interaction.

The Future of Data Annotation: Trends, Problems & Solutions
The data annotation market is growing at 26% per year. This rapid growth rate reflects the importance of categorizing and labeling data in the AI-driven world. Anna will discuss the current state of tools and techniques related to data annotation and what innovations we can expect in the upcoming years - including decentralization, Web3, and AI-based annotation.

Anna Petrovicheva is the CEO at CVAT.ai and CTO at OpenCV.ai. A computer vision leader with 12 years of experience in the field leading consulting teams working Fortune 500 companies in the medical, AR, sports, retail and security industries.

Using Similarity Learning to Improve Data Quality
Real-world data is a living structure, it grows day by day, changes a lot and becomes harder to work with. The process of splitting or labelling is error-prone and these errors can prove to be very costly. Similarity Learning is not only a great tool for data classification, even in the case of extreme classification, but also a surprisingly good way to improve the quality of your data. In this talk, Kacper will present how to approach quality assurance with deep neural networks in practice.

Kacper Łukawski is a Developer Advocate at Qdrant - an open-source neural search engine. Recently he’s been exploring the world of similarity learning and vector search.

Don't Forget

* Voxel51 will make a donation on behalf of the Meetup members to the charity that gets the most votes this month
* Can't make the date and time? No problem! Just make sure to register for the Zoom so we can send you links to the playbacks

About the Meetup Sponsor
Voxel51 is the maintainer of the open source FiftyOne computer vision project

Cross Post: January '23 Computer Vision Meetup (Virtual)

Network event

Link visible for attendees

Zoom Link
https://us02web.zoom.us/webinar/register/3816698250095/WN_XQIZlMP2RQuCFBwBylyRqA

Agenda
* Housekeeping
* Lightning Talk - Voxel51
* Hyperparameter Scheduling for Computer Vision - Cameron Wolfe (Alegion/Rice University)
* An Introduction to Computer Vision with Hugging Face transformers - Julien Simon (Hugging Face)
* Closing Remarks

Hyperparameter Scheduling for Computer Vision
Nearly all state-of-the-art results on computer vision benchmarks rely upon curated hyperparameter schedules. Though hyperparameter tuning may at times seem like a dark art, extensive empirical analysis of the topic has revealed countless numbers of best practices that are of incredible use to practitioners. In this talk, Cameron will overview these findings with an emphasis on practical applications, aiming to provide the listener with a better understanding of how to properly approach the tuning of hyperparameters.

Cameron Wolfe is a a PhD student in Computer Science at Rice University in Houston, TX and a research scientist at Alegion, a software startup based in Austin, TX

An Introduction to Computer Vision with Hugging Face Transformers
In this code-level talk, we'll show you how to quickly build and deploy computer vision applications based on Transformer models. Along the way, you'll learn about the portfolio of open source and commercial Hugging Face solutions, and how they can help you deliver high-quality solutions faster than ever before.

Julien Simon is currently Chief Evangelist at Hugging Face. He previously spent 6 years at Amazon Web Services where he was the Global Technical Evangelist for AI & Machine Learning. Prior to joining AWS, Julien served for 10 years as CTO/VP Engineering in large-scale startups.

Don't Forget

* Voxel51 will make a donation on behalf of the Meetup members to the charity that gets the most votes this month
* Can't make the date and time? No problem! Just make sure to register for the Zoom so we can send you links to the playbacks

About the Meetup Sponsor
Voxel51 is the maintainer of the open source FiftyOne computer vision project

Cross Post: February '23 Computer Vision Meetup (Virtual)

Network event

Link visible for attendees

Zoom Link
https://us02web.zoom.us/webinar/register/7916698252681/WN_P8UHtAZGQWOx_A2HM1dcPA

Agenda
* Housekeeping
* Lightning Talk - Voxel51
* Breaking the Bottleneck of AI Deployment at the Edge - Paula Ramos, PhD (Intel)
* Understanding Speech Recognition with OpenAI's Whisper Model - Vishal Rajput (AI-Vision Engineer)
* Closing Remarks

Breaking the Bottleneck of AI Deployment at the Edge
In this workshop, you will learn how to use less data for performant AI models. You will see this in action through real-world computer vision implementations, such as object detection and anomaly detection use cases, optimization processes, and deployment at the edge. And, you will learn how the open source OpenVINO toolkit can help reduce the gap between theoretical models and real-world implementations.

Key Takeaways:

  • Train & optimize for the edge with less data
  • Improve the performance of your model regardless of hardware
  • Learn how OpenVINO can accelerate AI models

Paula Ramos, PhD is an AI Evangelist at Intel. She has been working on developing novel integrated engineering technologies, mainly in the field of Computer Vision, robotics and Machine Learning applied to agriculture, since the early 2000s in Colombia. During her PhD and postgrad research, she deployed multiple low-cost, smart edge & IoT computing technologies that could be operated without expertise in computer vision systems.

Understanding Speech Recognition using OpenAI's Whisper Model
With the recent release of OpenAI's Whisper model there has been a huge shift in the field of speech recognition. This new system was able to beat humans in translating and transcribing the audio samples even in very noisy condition. In this talk we'll explore the paper, model card, and code to learn how to get started with OpenAI's Whisper model.

Vishal Rajput works as an AI-Vision Engineer for a drone company where he heads up AI development. He's authored several research papers and has 5 years of experience in Deep Learning. He is also a 2 time top-50 writer on Medium in the Artificial Intelligence category.

Don't Forget

  • Voxel51 will make a donation on behalf of the Meetup members to the charity that gets the most votes this month
  • Can't make the date and time? No problem! Just make sure to register for the Zoom so we can send you links to the playbacks

About the Meetup Sponsor
Voxel51 is the maintainer of the open source FiftyOne computer vision project

Cross Post: March '23 Computer Vision Meetup (Virtual)

Network event

Link visible for attendees

Zoom Link
https://us02web.zoom.us/webinar/register/1016698256055/WN_mTdNXxTSR-e7bDG5EkH1XQ

Agenda
* Housekeeping
* Lightning Talk - Jacob Marks (Voxel51)
* Lighting up Images in the Deep Learning Era - Soumik Rakshit (Weights & Biases)
* Training and Fine Tuning Vision Transformers Efficiently with Colossal AI - Sumanth P (ML Engineer)
* Closing Remarks

Lighting up Images in the Deep Learning Era
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in photography, security, medical imaging, and remote sensing. Recently, convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration tasks. We would discuss some of these state-of-the-art approaches to image restoration and would also discuss not only how we can improve the performance of such models, but also make them smaller and faster.

Soumik Rakshit is a Machine Learning Engineer working on end-to-end deep learning pipelines as part of the Growth team at Weights & Biases. My research and development interests include Generative Machine Learning Models, Video Enhancement Systems, Neural Radiance Fields, and NLP-based solutions to improve and automate student evaluation in the education sector. I enjoy implementing research papers in machine learning and computer graphics and communicating such ideas using end-to-end notebooks, and articles. I’m also working on training machine learning models on TPUs using Jax, Flax, Tensorflow, and Keras.

Training and Fine Tuning Vision Transformers Efficiently with Colossal AI

In the recent years we have seen the flourish of large AI Models but unfortunately, training and even fine-tuning those models are usually unaffordable, requiring huge computational resources. Existing deep learning frameworks like PyTorch and Tensorflow may not offer a satisfactory solution for very large AI models. In this talk we will go deep dive into Vision Transformers and see how to train and fine-tune the models more efficiently with Colossal AI that can perform complicated distributed training. The best part of this is, it is completely open source.

Sumanth P is a developer advocate, ML Engineer, ML content creator, and Founder of the Community (C4ML)

Don't Forget

  • Voxel51 will make a donation on behalf of the Meetup members to the charity that gets the most votes this month
  • Can't make the date and time? No problem! Just make sure to register for the Zoom so we can send you links to the playbacks

About the Meetup Sponsor
Voxel51 is the maintainer of the open source FiftyOne computer vision project

Past events (46)

Introduction to Kubeflow: Pipeline Fundamentals

This event has passed

Photos (104)