Skip to main content
search
Category

Blog

Nov 30
Love0

What Next After You Have Built a Catalog – Part 1

By Blog

Guest Author: Mandy Chessell

Update your calendars! The popular monthly Egeria Webinar program is here: https://wiki.lfaidata.foundation/display/EG/Egeria+Webinar+program.

The next session is on the 6th of December 2021 at 15:00 UTC and will describe the next steps you can take after you have basic cataloguing in place.

This session will use a fictitious company Coco Pharmaceuticals as a representative example on how to achieve this.    

Peter Profile from Coco Pharmaceuticals is responsible for cataloging the weekly incoming data from the hospitals that are involved in their latest clinical trial.  The data scientists that use the catalog to locate and work with this data are full of praise for Peter’s work. However, Peter is getting fed up with the repetitive, time-consuming nature of the cataloguing activity.  How can we help Peter to automate this cataloguing and extend the value of the catalog to the organization?

In this session, follow Peter’s journey from manual cataloging to using automated integration and templating to create business relevant catalog entries.  He also adds metadata discovery to extract profile information about the incoming data values and enables metadata governance features (such as deduplication) to improve the quality of the catalog.  Finally, he creates automated notifications to the stewards responsible for the data if any issues occur that need a human touch.

The result is that Peter is relieved of the tedious cataloguing tasks and Coco Pharmaceuticals sees increased value from their catalog. 

The session will cover:

Who is this for: Anyone interested in automating their cataloguing of metadata. 

What and Why:  An organization can put in place processes to automate cataloguing, so that metadata can be brought into an Egeria ecosystem consistently on an ongoing basis, allowing it to be coherently governed, with minimal human intervention.  

Zoom Conference https://zoom.us/j/523629111    

At the end of the session, you should have awareness of ways to automate the cataloguing of your metadata.

Be sure to put the other Webinar dates in your calendar. 

Egeria

LF AI & Data Resources

Nov 30
Love0

Adlik Deer Release (v0.4.0) Now Available!

By Blog

Adlik release bear

Adlik, an LF AI & Data Foundation Incubation-Stage Project, has released version 0.4.0, called Deer. Adlik is a toolkit for accelerating deep learning inference, which provides an overall support for bringing trained models into production and eases the learning curves for different kinds of inference frameworks. In Adlik, Model Optimizer and Model Compiler delivers optimized and compiled models for a certain hardware environment, and Serving Engine provides deployment solutions for cloud, edge and device.

In this release, Adlik made quite a lot of technical explorations, like multi-teacher distillation, Zen-NAS optimization. And it now becomes much easier for you to use Adlik with more runtime on more hardware. In Adlik’s inference optimization on Bert model, Ansor is used to search the optimal tensor scheduling solution globally, a special scheduler is provided to optimize dynamic shape inference, and we achieve a higher throughput on x86 CPUs than OpenVINO. A few highlights of the new release include the following:

Compiler

  1. Adlik compiler supports OpenVINO INT8 quantization.
  2. Adlik compiler supports TensorRT INT8 quantization. Supports extended quantization calibrator for TensorRT for reducing the accuracy drop caused by quantization.

Optimizer

  1. Support multi-teacher distillation method, which uses multi-teacher networks for distillation optimization.
  2. Support ZEN-NAS search enhancement features, including parallel training, optimization for search acceleration, fix the bugs of original implementation etc. The consumed search time is reduced by about 15%, when the search score is slightly improved, and the training accuracy of the searched model is increased by 0.2% ~1%.

Serving Engine

  1. Support Paddle Inference Runtime. When using Paddle-format model, converting model format through Onnx components is not needed, and users can directly perform model inference in the Adlik environment.
  2. Support Intel TGL-U i5 device inference, and complete benchmark tests with several models.
  3. Docker images for cloud native environments support newest version of inference components including:
    (1) OpenVINO: version 2021.4.582
    (2)TensorFlow: 2.6.2
    (3)TensorRT: 7.2.1.6
    (4) Tf-lite: 2.4.0
    (5) TVM: 0.7
    (6) Paddle Inference: 2.1.2
  4. Introduce C++ version of Client API, which supports cmake and bazel compilation, and is convenient for users to deploy in C/C++ scenarios.

Benchmark Test

  1. Complete Benchmark tests of Resnet-50, Yolo v3/v4, FastRCNN, MaskRCNN and other models on Intel TGL-U i5 equipment, including latency, throughput, and various performance indicators under GPU video decoding.

The Adlik Project invites you to adopt or upgrade to Deer, version 0.4.0, and welcomes feedback. To learn more about the Adlik 0.4.0 release, check out the full release notes. Want to get involved with Adlik? Be sure to join the Adlik-Announce and Adlik Technical-Discuss mailing lists to join the community and stay connected on the latest updates. 

Adlik Key Links

LF AI & Data Resources

Nov 10
Love0

International Conference AI for People: Towards Sustainable AI (CAIP’21)

By Blog

The LF AI & Data Foundation is pleased to announce the upcoming International Conference “AI for People: Towards Sustainable AI” (CAIP’21), to be held online 20-24 November.

CAIP’21 aims to provide a platform for people to present, learn, and discuss the use of Artificial Intelligence for the societal good, addressing its benefits as well as its risks. In this year’s edition, the main topic will be Sustainable AI as a movement to foster change towards greater ecological integrity and social justice in the entire life cycle of AI systems.

One of the conference’s goals is to bring together Academics and the general public to discuss Sustainable AI. As such, the event is free to attend and registration is now open until the 13th of November at: https://aiforpeople.org/conference/

The conference program will include keynote sessions, workshops, discussion panels and paper presentation sessions. It can be found here: https://aiforpeople.org/conference/program.php

The following keynote speakers are confirmed:

LF AI & Data Resources

Nov 05
Love0

Please Join Us for the Next Egeria Webinar – November 8th

By Blog

Guest Authors: Mandy Chessell and ING Bank

Update your calendars! The popular monthly Egeria Webinar program is here: https://wiki.lfaidata.foundation/display/EG/Egeria+Webinar+program.

The next session is on the 8th of November 2021 at 15:00 UTC and will describe the purpose of lineage, what type of information needs to be collected and how this information is managed and used in an enterprise with Egeria. The session will cover:

Who is this for: anyone interested in understanding lineage, including governance teams and their auditors.  

What and Why: The session will cover Open Lineage services – a historical reporting warehouse for lineage and also the https://openlineage.io/blog/joining-lfai/. 

How: How Egeria works with lineage will be covered (https://odpi.github.io/egeria-docs/features/lineage-management/overview/?h=lineage) in detail. 

At the end of the session, you should have awareness of purpose of Lineage, the information that needs to be collected and how to manage and use this information in Egeria. 

Be sure to put the other Webinar dates in your calendar. 

Egeria

LF AI & Data Resources

Oct 28
Love0

Thank You ONNX for Hosting a Great LF AI & Data Day!

By Blog

The LF AI & Data Foundation would like to thank ONNX for hosting a great virtual meetup! The LF AI & Data Day ONNX Community Virtual Meetup was held on October 21, 2021 and was a great success with over 100 attendees joining for part of the three hour event.

The meetup included ONNX Community updates, partner/end-user stories, and SIG/WG updates. The virtual meetup was an opportunity to connect with and hear from people working with ONNX across a variety of groups. A special thank you to Rajeev Nalawadi for working closely with the ONNX Technical Steering Committee, SIGs, and ONNX community to curate the content. 

Missed the meetup? Check out all of the presentations and recordings here.

This meetup took on a virtual format but we look forward to connecting again at another event in person soon. LF AI & Data Day is a regional, one-day event hosted and organized by local members with support from LF AI & Data, its members, and projects. If you are interested in hosting an LF AI & Data Day please email info@lfai.foundation to discuss.

ONNX, an LF AI & Data Foundation Graduated Project, is an open format to represent deep learning models. With ONNX, AI developers can more easily move models between state-of-the-art tools and choose the combination that is best for them.  Be sure to join the ONNX-Announce mailing list to join the community and stay connected on the latest updates. You can join technical discussions on GitHub and more conversations with the community on LF AI & Data ONNX Slack channels.

ONNX Resources

LF AI & Data Resources

Oct 15
Love0

AI for Good Summit: Open Source, Accelerate AI Innovation Webinar – October 21 Virtual Event

By Blog, Uncategorized

The LF AI & Data Foundation is pleased to share that the Open Source, Accelerating AI Innovation webinar of ITU AI for Good Summit, will be held online on October 21, 2021. 

The “Open Source Accelerating AI Innovation” session will bring together several experts from the AI open source community to bring to light the state-of-the art breakthroughs in their open source exploration. It’s known that the development of open source technologies is the key driver of sustainable AI innovation and this webinar is a great opportunity for you to hear fantastic thoughts and opinions about why open source is so important to AI and how open source can power AI.

Registration is now open and the event is free to attend. Please see the agenda below and register right now.

LF AI & Data Resources

Oct 11
Love0

Thank You for a Great OSS+ELC 2021!

By Blog, Uncategorized
lfaidata-horizontal-color.png

The LF AI & Data Foundation would like to take this opportunity to thank all of the attendees, speakers/presenters, and booth staff volunteers for a great experience at OSS+ELC 2021. Of course none of this would be possible without the amazing Events Team at The Linux Foundation and all of the Program Committee members and their hard work. With the ongoing COVID-19 situation, we were thrilled to be able to participate in this hybrid onsite/virtual event. 

The AI & Data Track during the conference was successful, with a great showing of attendees and great subject matter experts as speakers. If you didn’t get a chance to visit our Bronze booth in the onsite or virtual exhibit hall, please take a moment to explore our resources below. 

Be sure to look for us at our next events, KubeCon+CloudNativeCon+OSS China (December 9th & 10th) and OSS Japan (December 14th & 15th) at our virtual booth. Thank you and we look forward to connecting again soon!

LF AI & Data Resources

Oct 06
Love0

LF AI & Data Day ONNX Community Virtual Meetup – October 2021

By Blog

The LF AI & Data Foundation is pleased to announce the upcoming LF AI & Data Day* – ONNX Community Virtual Meetup – October 2021, to be held via Zoom on October 21st.

ONNX, an LF AI & Data Foundation Graduated Project, is an open format to represent deep learning models. With ONNX, AI developers can more easily move models between state-of-the-art tools and choose the combination that is best for them. 

The virtual meetup will cover ONNX Community updates, partner/end-user stories, and SIG/WG updates. Check out the schedule of events here. If you are using ONNX in your services and applications, building software or hardware that supports ONNX, or contributing to ONNX, you should attend! This is a great opportunity to connect with and hear from people working with ONNX across many companies. 

Registration is now open and the event is free to attend. Capacity will be 500 attendees. For up to date information on this virtual meetup, please visit the event website. 

Want to get involved with ONNX? Be sure to join the ONNX-Announce mailing list to join the community and stay connected on the latest updates. You can join technical discussions on GitHub and more conversations with the community on LF AI & Data Slack’s ONNX channels.

Note: In order to ensure the safety of our event participants and staff due to the Novel Coronavirus situation (COVID-19) the ONNX Steering Committee decided to make this a virtual-only event via Zoom.

*LF AI & Data Day is a regional, one-day event hosted and organized by local members with support from LF AI & Data and its Projects. Learn more about the LF AI & Data Foundation here.

ONNX Key Links

LF AI & Data Resources

Oct 01
Love0

NNStreamer 2.0 Release Now Available

By Blog

LF AI & Data Foundation is proud to support the release of NNStreamer 2.0, one of our incubation-stage projects. NNStreamer is a set of Gstreamer plugins that support ease and efficiency for Gstreamer developers adopting neural network models and neural network developers managing neural network pipelines and their filters. Features of the new release include Edge-AI capabilities and new stream types. With this new release, NNStreamer 2.0 achieved the CII Best Practices passing badge last month. This recognizes that the community maintains high-quality code, documentation, testing, and of course, a high level of security as one of the best practices in Open Source. With the new release, NNStreamer now clears all of  the 19 detected security vulnerabilities from LGTM analysis since this month.

Key Features of 2.0.y LTS 

With Edge-AI capabilities, users may connect independent and remote pipelines with NNStreamer-provided protocols designed for AI data streams. In other words, a lightweight IoT device may offload its AI workloads to its neighbor devices with GStreamer/NNStreamer pipeline descriptions, and an AI service may publish its output data streams for other AI pipelines easily. Several features and optimizations are scheduled to follow with subsequent version releases.

As new stream types are introduced with this release, the “single tensor” stream type is becoming obsolete in NNStreamer 2.0, however compatibility will remain with possible warning messages in subsequent releases. The single tensor stream type with “other/tensor” MIME will be obsolete with the NNStreamer 2.0 release. Users are recommended to use “other/tensors” instead. The standard tensor data streams may have different data types: static (default), dynamic, and sparse. The conventional and default tensor streams are static. A dynamic tensor stream may have different dimensions with each data frame. A sparse tensor stream assumes that most elements are zeros.  As new stream types are introduced with this release, the “single tensor” stream type is becoming obsolete in NNStreamer 2.0, however compatibility will remain with possible warning messages in subsequent releases. The single tensor stream type with “other/tensor” MIME will be obsolete with the NNStreamer 2.0 release. Users are recommended to use “other/tensors” instead. The standard tensor data streams may have different data types: static (default), dynamic, and sparse. The conventional and default tensor streams are static. A dynamic tensor stream may have different dimensions with each data frame. A sparse tensor stream assumes that most elements are zeros.  

  Other major features include:

  • New hardware accelerators and AI frameworks supported: TVM, TensorRT, NNTrainer, Tensorflow-lite delegation (GPU/NNAPI/XNNPACK), 
  • Tensor-converter/decoder support subplugins and custom functions.
  • New elements: stream branch (Tensor-if), stream join (Join), crop (Tensor-crop), rate and QoS control (Tensor-rate)

NNStreamer Key Links

LF AI & Data Resources

Sep 30
Love0

The Value Egeria Brings to an Organization

By Blog

Guest Author : Mandy Chessell

Update your calendars! The popular monthly Egeria Webinar program continues. The next session is on the 4th of October 2021 at 15:00 UTC via Zoom and will focus on understanding the value of Egeria.

The session will cover anyone interested in understanding how Egeria brings value to your data and how you manage it; enabling data centric, metadata driven integration. The session will start with the core Egeria constructs including entities, and will explain the principles behind them. We will then go through the layers and aspects of the Egeria architecture, at each stage talking about the applicability to solving real world problems.

The session will explain the benefits of solving the main integration problem organizations face; the solution being to use the Egeria eco-system. It will then talk about how you can use this coherent view of the your information to add value and save time for your organization.   

At the end of the session, you should have awareness of the parts of Egeria at a high level, why they have been implemented as they are and the value that each of the pieces bring.   

Be sure to put the other Webinar dates in your calendar. 

Egeria Key Links

LF AI & Data Resources

Close Menu