- Network event57 attendees from 12 groups hostingMay 29 - Getting Started with FiftyOne WorkshopCancelled
When
May 29, 2024 at 9 AM Pacific for 90 minutesWhere
Virtually over Zoom: https://voxel51.com/computer-vision-events/getting-started-with-fiftyone-workshop-may-29-2024/About the Workshop
Want greater visibility into the quality of your computer vision datasets and models? Then join Allen Lee, Machine Learning Engineer at Voxel51, for this free 90 minute, hands-on workshop to learn how to leverage the open source FiftyOne computer vision toolset.In the first part of the workshop we’ll cover:
- FiftyOne Basics (terms, architecture, installation, and general usage)
- An overview of useful workflows to explore, understand, and curate your data
- How FiftyOne represents and semantically slices unstructured computer vision data
The second half will be a hands-on introduction to FiftyOne, where you will learn how to:
- Load datasets from the FiftyOne Dataset Zoo
- Navigate the FiftyOne App
- Programmatically inspect attributes of a dataset
- Add new sample and custom attributes to a dataset
- Generate and evaluate model predictions
- Save insightful views into the data
Prerequisites are a working knowledge of Python and basic computer vision. All attendees will get access to the tutorials, videos, and code examples used in the workshop.
- Network event29 attendees from 3 groups hostingMay 30, 2024 AI, Machine Learning and Data Science MeetupGitHub, San Francisco, CA
Pre-registering for the event is mandatory. Sign up here:
https://voxel51.com/computer-vision-events/may-30-2024-ai-machine-learning-data-science-meetup/
Date and Time
May 30, 5:30 PM to 8:00 PM Pacific
Location
The Meetup will take place at GitHub’s offices in San Francisco. Note that pre-registration is mandatory.
88 Colin P Kelly Jr St, San Francisco, CA 94107
Lessons Learned fine-tuning Llama2 for Autonomous Agents
In this talk, Rahul Parundekar, Founder of A.I. Hero, Inc. does a deep dive into the practicalities and nuances of making LLMs more effective and efficient. He’ll share hard-earned lessons from the trenches of LLMOps on Kubernetes, covering everything from the critical importance of data quality to the choice of fine-tuning techniques like LoRA and QLoRA. Rahul will share insights into the quirks of fine-tuning LLMs like Llama2, the need for looking beyond loss metrics and benchmarks for model performance, and the pivotal role of iterative improvement through user feedback – all learned through his work on fine-tuning an LLM for retrieval-augmented generation and autonomous agents. Whether you’re a seasoned AI professional or just starting, this talk will equip you with the knowledge of when and why you should fine-tune, to the long-term strategies to push the boundaries of what’s possible with LLMs, to building a performant framework on top of Kubernetes for fine-tuning at scale.
Speaker: Rahul Parundekar is the founder of A.I. Hero, Inc., a seasoned engineer, and architect with over 15 years of experience in AI development, focusing on Machine Learning and Large Language Model Operations (MLOps and LLMOps). AI Hero automates mundane enterprise tasks through agents, utilizing a framework for fine-tuning LLMs with both open and closed-source models to enhance agent autonomy.
Multi-Modal Visual Question Answering (VQA) using UForm tiny models with Milvus vector database
UForm is a multimodal AI library that will help you understand and search visual and textual content across various languages. UForm not only supports RAG chat use-cases, but is also capable of Visual Question Answering (VQA). Compact custom pre-trained transformer models can run anywhere from your server farm down to your laptop. I’ll be giving a demo of RAG and VQA using Milvus vector database.
Speaker: Christy Bergman is a passionate Developer Advocate at Zilliz. She previously worked in distributed computing at Anyscale and as a Specialist AI/ML Solutions Architect at AWS.
Speaker: Ash Vardanian is the Founder of Unum Cloud. With a background in Astrophysics, his work today primarily lies in the intersection of Theoretical Computer Science, High-Performance Computing, and AI Systems Design.
Combining Hugging Face Transformer Models and Image Data with FiftyOne
Datasets and Models are the two pillars of modern machine learning, but connecting the two can be cumbersome and time-consuming. In this lightning talk, you will learn how the seamless integration between Hugging Face and FiftyOne simplifies this complexity, enabling more effective data-model co-development. By the end of the talk, you will be able to download and visualize datasets from the Hugging Face hub with FiftyOne, apply state-of-the-art transformer models directly to your data, and effortlessly share your datasets with others.
Speaker: Jacob Marks, PhD is a Machine Learning Engineer and Developer Evangelist at Voxel51, where he leads open source efforts in vector search, semantic search, and generative AI for the FiftyOne data-centric AI toolkit.
Prior to joining Voxel51, Jacob worked at Google X, Samsung Research, and Wolfram Research.Strategies for Enhancing the Adoption of Open Source Libraries: A Case Study on Albumentations.ai
In this presentation, we explore key strategies for boosting the adoption of open-source libraries, using Albumentations.ai as a case study. We will cover the importance of community engagement, continuous innovation, and comprehensive documentation in driving a project’s success. Through the lens of Albumentations.ai’s growth, attendees will gain insights into effective practices for promoting their open source projects within the machine learning and broader developer communities.
Speaker: Vladimir Iglovikov, PhD is a co-creator of Albumentations.ai, a Kaggle Grandmaster.
- Network event11 attendees from 14 groups hostingVirtual Open Office Hours with Professor Jason Corso - June 3Link visible for attendees
Virtual Open Office Hours with Professor Jason Corso
Drop in on a weekly and informal chat with Professor Jason Corso!
When: Every Monday | 12 PM Eastern
Join the Zoom: https://us02web.zoom.us/j/85383168408
What are Open Office Hours?
These chats are for students, engineers, researchers, founders, open source contributors, coders, roboticists, authors, and sci-fi enthusiasts. Office Hours take place every Monday at noon Eastern Time for 60 minutes.
What topics are open for discussion?
In addition to your questions, Professor Corso would like to hear your perspectives, such as challenges and opportunities in your research or what robot you would choose to join you on a desert island and why.
About Dr. Jason Corso
Dr. Jason Corso is currently a Professor of Robotics and Electrical Engineering & Computer Science at the University of Michigan. He received his Ph.D. in Computer Science at The Johns Hopkins University in 2005. He is a recipient of the NSF CAREER award (2009), ARO Young Investigator award (2010), Google Faculty Research Award (2015) and the DARPA CSSG (2009).
He is also the Co-Founder and Chief Scientist of Voxel51, a computer vision startup that is building the state of the art platform for video and image based applications.
- Network event8 attendees from 12 groups hostingJune 5 - Developing FiftyOne Plugins WorkshopLink visible for attendees
When
June 5, 2024 at 9 AM Pacific for 90 minutesWhere
Virtually over Zoom: https://voxel51.com/computer-vision-events/developing-fiftyone-plugins-workshop-june-5-2024/About the Workshop
Are you ready to take your computer vision tooling to the next level? Open source FiftyOne is the most flexible computer vision toolkit on the planet. By tapping into its builtin Plugin framework, you can extend your FiftyOne experience and streamline your workflows, building Gradio-like applications with data at their core.From concept interpolation to image deduplication, optical character recognition, and even curating your own AI art gallery by adding generated images directly into a dataset, your imagination is the only limit. Join us to discover how you can unleash your creativity and interact with data like never before.
In the first part of the workshop we’ll cover:
- FiftyOne Plugins – what are they?
- Installing a plugin
- Creating your own Python plugin
- Python plugin tips
- Creating your own JavaScript plugin
- Publishing your plugin
Prerequisites
A working knowledge of Python and basic familiarity with FiftyOne. All attendees will get access to the tutorials, videos, and code examples used in the workshop.Resources
Check out some these popular plugins:
- VoxelGPT: AI Assistant for Computer Vision
- Image Quality Issues
- Image Deduplication
- AI Art Gallery
- Optical Character Recognition
- Visual Question Answering
Resources for the workshop:
- FiftyOne Plugins Documentation
- Python Operators API Docs
- FiftyOne Plugins Repo
- Plugins Channel in FiftyOne Community Slack
Videos:
- Network event4 attendees from 14 groups hostingVirtual Open Office Hours with Professor Jason Corso - June 10Link visible for attendees
Virtual Open Office Hours with Professor Jason Corso
Drop in on a weekly and informal chat with Professor Jason Corso!
When: Every Monday | 12 PM Eastern
Join the Zoom: https://us02web.zoom.us/j/85383168408
What are Open Office Hours?
These chats are for students, engineers, researchers, founders, open source contributors, coders, roboticists, authors, and sci-fi enthusiasts. Office Hours take place every Monday at noon Eastern Time for 60 minutes.
What topics are open for discussion?
In addition to your questions, Professor Corso would like to hear your perspectives, such as challenges and opportunities in your research or what robot you would choose to join you on a desert island and why.
About Dr. Jason Corso
Dr. Jason Corso is currently a Professor of Robotics and Electrical Engineering & Computer Science at the University of Michigan. He received his Ph.D. in Computer Science at The Johns Hopkins University in 2005. He is a recipient of the NSF CAREER award (2009), ARO Young Investigator award (2010), Google Faculty Research Award (2015) and the DARPA CSSG (2009).
He is also the Co-Founder and Chief Scientist of Voxel51, a computer vision startup that is building the state of the art platform for video and image based applications.
- Network event1 attendee from 14 groups hostingVirtual Open Office Hours with Professor Jason Corso - June 17Link visible for attendees
Virtual Open Office Hours with Professor Jason Corso
Drop in on a weekly and informal chat with Professor Jason Corso!
When: Every Monday | 12 PM Eastern
Join the Zoom: https://us02web.zoom.us/j/85383168408
What are Open Office Hours?
These chats are for students, engineers, researchers, founders, open source contributors, coders, roboticists, authors, and sci-fi enthusiasts. Office Hours take place every Monday at noon Eastern Time for 60 minutes.
What topics are open for discussion?
In addition to your questions, Professor Corso would like to hear your perspectives, such as challenges and opportunities in your research or what robot you would choose to join you on a desert island and why.
About Dr. Jason Corso
Dr. Jason Corso is currently a Professor of Robotics and Electrical Engineering & Computer Science at the University of Michigan. He received his Ph.D. in Computer Science at The Johns Hopkins University in 2005. He is a recipient of the NSF CAREER award (2009), ARO Young Investigator award (2010), Google Faculty Research Award (2015) and the DARPA CSSG (2009).
He is also the Co-Founder and Chief Scientist of Voxel51, a computer vision startup that is building the state of the art platform for video and image based applications.
- Network event4 attendees from 12 groups hostingJune 26 - Getting Started with FiftyOne WorkshopLink visible for attendees
Where
Virtually over Zoom: https://voxel51.com/computer-vision-events/getting-started-with-fiftyone-workshop-june-26-2024/About the Workshop
Want greater visibility into the quality of your computer vision datasets and models? Then join Harpreet Sahota, Machine Learning Engineer at Voxel51, for this free 90 minute, hands-on workshop to learn how to leverage the open source FiftyOne computer vision toolset.In the first part of the workshop we’ll cover:
- FiftyOne Basics (terms, architecture, installation, and general usage)
- An overview of useful workflows to explore, understand, and curate your data
- How FiftyOne represents and semantically slices unstructured computer vision data
The second half will be a hands-on introduction to FiftyOne, where you will learn how to:
- Load datasets from the FiftyOne Dataset Zoo
- Navigate the FiftyOne App
- Programmatically inspect attributes of a dataset
- Add new sample and custom attributes to a dataset
- Generate and evaluate model predictions
- Save insightful views into the data
Prerequisites are a working knowledge of Python and basic computer vision. All attendees will get access to the tutorials, videos, and code examples used in the workshop.
- Network event21 attendees from 14 groups hostingJune 27 - AI, Machine Learning and Computer Vision MeetupLink visible for attendees
When: June 27, 2024 – 10:00 AM Pacific / 1:00 PM Eastern
Register for the Zoom: https://voxel51.com/computer-vision-events/june-27-2024-ai-machine-learning-computer-vision-meetup/
Leveraging Pre-trained Text2Image Diffusion Models for Zero-Shot Video Editing
Text-to-image diffusion models demonstrate remarkable editing capabilities in the image domain, especially after Latent Diffusion Models made diffusion models more scalable. Conversely, video editing still has much room for improvement, particularly given the relative scarcity of video datasets compared to image datasets. Therefore, we will discuss whether pre-trained text-to-image diffusion models can be used for zero-shot video editing without any fine-tuning stage. Finally, we will also explore possible future work and interesting research ideas in the field.
About the Speaker
Bariscan Kurtkaya is a KUIS AI Fellow and a graduate student in the Department of Computer Science at Koc University. His research interests lie in exploring and leveraging the capabilities of generative models in the realm of 2D and 3D data, encompassing scientific observations from space telescopes.
Improved Visual Grounding through Self-Consistent Explanations
Vision-and-language models that are trained to associate images with text have shown to be effective for many tasks, including object detection and image segmentation. In this talk, we will discuss how to enhance vision-and-language models’ ability to localize objects in images by fine-tuning them for self-consistent visual explanations. We propose a method that augments text-image datasets with paraphrases using a large language model and employs SelfEQ, a weakly-supervised strategy that promotes self-consistency in visual explanation maps. This approach broadens the model’s working vocabulary and improves object localization accuracy, as demonstrated by performance gains on competitive benchmarks.
About the Speakers
Dr. Paola Cascante-Bonilla received her Ph.D. in Computer Science at Rice University in 2024, advised by Professor Vicente Ordóñez Román, working on Computer Vision, Natural Language Processing, and Machine Learning. She received a Master of Computer Science at the University of Virginia and a B.S. in Engineering at the Tecnológico de Costa Rica. Paola will join Stony Brook University (SUNY) as an Assistant Professor in the Department of Computer Science.
Ruozhen (Catherine) He is a first-year Computer Science PhD student at Rice University, advised by Prof. Vicente Ordóñez, focusing on efficient algorithms in computer vision with less or multimodal supervision. She aims to leverage insights from neuroscience and cognitive psychology to develop interpretable algorithms that achieve human-level intelligence across versatile tasks.
- Network event4 attendees from 14 groups hostingJuly 3 - AI, Machine Learning and Computer Vision MeetupLink visible for attendees
When: July 3, 2024 – 9 AM Eastern / 2 PM BST / 6:30 PM IST
Register for the Zoom: https://voxel51.com/computer-vision-events/ai-machine-learning-computer-vision-meetup-july-3-2024/
Performance Optimization for Multimodal LLMs
In this talk we’ll delve into Multi-Modal LLMs, exploring the fusion of language and vision in cutting-edge models. We’ll, highlight the challenges in handling diverse data heterogeneity, its architecture design, strategies for efficient training, and optimization techniques to enhance both performance and inference speed. Through case studies and future outlooks, we’ll illustrate the importance of these optimizations in advancing applications across various domains.
About the Speaker
Neha Sharma has a rich background in digital products and technology services, having delivered successful projects for industry giants like IBM and launching innovative products for tech startups. As a Product Manager at Ori, Neha specializes in developing cutting-edge AI solutions by actively engaging on various AI-based use cases centered around latest/popular LLMs, demonstrating her commitment to staying at the forefront of AI technology.
Stay tuned! More speakers will be announced shortly.
- Network event1 attendee from 14 groups hostingDeveloping FiftyOne Plugins Workshop - July 10Link visible for attendees
Are you ready to take your computer vision tooling to the next level? Open source FiftyOne is the most flexible computer vision toolkit on the planet. By tapping into its builtin Plugin framework, you can extend your FiftyOne experience and streamline your workflows, building Gradio-like applications with data at their core.
Register for the Zoom: https://voxel51.com/computer-vision-events/developing-fiftyone-plugins-workshop-july-10/
From concept interpolation to image deduplication, optical character recognition, and even curating your own AI art gallery by adding generated images directly into a dataset, your imagination is the only limit. Join us to discover how you can unleash your creativity and interact with data like never before.
In the workshop we’ll cover:
- FiftyOne Plugins – what are they?
- Installing a plugin
- Creating your own Python plugin
- Python plugin tips
- Creating your own JavaScript plugin
- Publishing your plugin
Prerequisites
A working knowledge of Python and basic familiarity with FiftyOne. All attendees will get access to the tutorials, videos, and code examples used in the workshop.
Check out some these popular plugins
- VoxelGPT: AI Assistant for Computer Vision
- Image Quality Issues
- Image Deduplication
- AI Art Gallery
- Optical Character Recognition
- Visual Question Answering
Resources for the workshop
- FiftyOne Plugins Documentation
- Python Operators API Docs
- FiftyOne Plugins Repo
- Plugins Channel in FiftyOne Community Slack
Videos