Sunday, November 27, 2022
HomeSoftware DevelopmentMachine Studying Communities: Q3 ‘22 highlights and achievements

Machine Studying Communities: Q3 ‘22 highlights and achievements



Posted by Nari Yoon, Hee Jung, DevRel Group Supervisor / Soonson Kwon, DevRel Program Supervisor

Let’s discover highlights and accomplishments of huge Google Machine Studying communities over the third quarter of the yr! We’re enthusiastic and grateful about all of the actions by the worldwide community of ML communities. Listed here are the highlights!

TensorFlow/Keras

Load-testing TensorFlow Serving’s REST Interface

Load-testing TensorFlow Serving’s REST Interface by ML GDE Sayak Paul (India) and Chansung Park (Korea) shares the teachings and findings they realized from conducting load exams for a picture classification mannequin throughout quite a few deployment configurations.

TFUG Taipei hosted occasions (Python + Hugging Face-Translation+ tf.keras.losses, Python + Object detection, Python+Hugging Face-Token Classification+tf.keras.initializers) in September and helped neighborhood members discover ways to use TF and Hugging face to implement machine studying mannequin to resolve issues.

Neural Machine Translation with Bahdanau’s Consideration Utilizing TensorFlow and Keras and the associated video by ML GDE Aritra Roy Gosthipaty (India) explains the mathematical instinct behind neural machine translation.

Serving a TensorFlow image classification model as RESTful and gRPC based services with TFServing, Docker, and Kubernetes

Automated Deployment of TensorFlow Fashions with TensorFlow Serving and GitHub Actions by ML GDE Chansung Park (Korea) and Sayak Paul (India) explains how you can automate TensorFlow mannequin serving on Kubernetes with TensorFlow Serving and GitHub Motion.

Deploying 🤗 ViT on Kubernetes with TF Serving by ML GDE Sayak Paul (India) and Chansung Park (Korea) reveals how you can scale the deployment of a ViT mannequin from 🤗 Transformers utilizing Docker and Kubernetes.

Screenshot of the TensorFlow Forum in the Chinese Language run by the tf.wiki team

Lengthy-term TensorFlow Steering on tf.wiki Discussion board by ML GDE Xihan Li (China) gives TensorFlow steering by answering the questions from Chinese language builders on the discussion board.

photo of a phone with the Hindi letter 'Ohm' drawn on the top half of the screen. Hinidi Character recognition shows the letter Ohm as the Predicted Result below.

Hindi Character Recognition on Android utilizing TensorFlow Lite by ML GDE Nitin Tiwari (India) shares an end-to-end tutorial on coaching a customized laptop imaginative and prescient mannequin to acknowledge Hindi characters. In TFUG Pune occasion, he additionally gave a presentation titled Constructing Pc Imaginative and prescient Mannequin utilizing TensorFlow: Half 1.

Utilizing TFlite Mannequin Maker to Full a Customized Audio Classification App by ML GDE Xiaoxing Wang (China) reveals how you can use TFLite Mannequin Maker to construct a customized audio classification mannequin primarily based on YAMNet and how you can import and use the YAMNet-based customized fashions in Android initiatives.

SoTA semantic segmentation in TF with 🤗 by ML GDE Sayak Paul (India) and Chansung Park (Korea). The SegFormer mannequin was not out there on TensorFlow.

Textual content Augmentation in Keras NLP by ML GDE Xiaoquan Kong (China) explains what textual content augmentation is and the way the textual content augmentation function in Keras NLP is designed.

The biggest imaginative and prescient mannequin checkpoint (public) in TF (10 Billion params) by means of 🤗 transformers by ML GDE Sayak Paul (India) and Aritra Roy Gosthipaty (India). The underlying mannequin is RegNet, recognized for its skill to scale.

A simple TensorFlow implementation of a DCGAN to generate CryptoPunks

CryptoGANs open-source repository by ML GDE Dimitre Oliveira (Brazil) reveals easy mannequin implementations following TensorFlow finest practices that may be prolonged to extra advanced use-cases. It connects the utilization of TensorFlow with different related frameworks, like HuggingFace, Gradio, and Streamlit, constructing an end-to-end answer.

TFX

TFX Machine Learning Pipeline from data injection in TFRecord to pushing out Vertex AI

MLOps for Imaginative and prescient Fashions from 🤗 with TFX by ML GDE Chansung Park (Korea) and Sayak Paul (India) reveals how you can construct a machine studying pipeline for a imaginative and prescient mannequin (TensorFlow) from 🤗 Transformers utilizing the TF ecosystem.

First launch of TFX Addons Bundle by ML GDE Hannes Hapke (United States). The bundle has been downloaded just a few thousand instances (supply). Google and different builders keep it by means of bi-weekly conferences. Google’s Open Supply Peer Award has acknowledged the work.

TFUG São Paulo hosted TFX T1 | E4 & TFX T1 | E5. And ML GDE Vinicius Caridá (Brazil) shared how you can practice a mannequin in a TFX pipeline. The fifth episode talks about Pusher: publishing your fashions with TFX.

Semantic Segmentation mannequin inside ML pipeline by ML GDE Chansung Park (Korea) and Sayak Paul (India) reveals how you can construct a machine studying pipeline for semantic segmentation process with TFX and numerous GCP merchandise equivalent to Vertex Pipeline, Coaching, and Endpoints.

JAX/Flax

Screen shot of Tutorial 2 (JAX): Introduction to JAX+Flax with GitHub Repo and Codelab via university of Amseterdam

JAX Tutorial by ML GDE Phillip Lippe (Netherlands) is supposed to briefly introduce JAX, together with writing and coaching neural networks with Flax.

TFUG Malaysia hosted Introduction to JAX for Machine Studying (video) and Leong Lai Fong gave a chat. The attendees realized what JAX is and its elementary but distinctive options, which make it environment friendly to make use of when executing deep studying workloads. After that, they began coaching their first JAX-powered deep studying mannequin.

TFUG Taipei hosted Python+ JAX + Picture classification and helped folks be taught JAX and how you can use it in Colab. They shared information in regards to the distinction between JAX and Numpy, some great benefits of JAX, and how you can use it in Colab.

Introduction to JAX by ML GDE João Araújo (Brazil) shared the fundamentals of JAX in Deep Studying Indaba 2022.

A comparison of the performance and overview of issues resulting from changing from NumPy to JAX

Ought to I alter from NumPy to JAX? by ML GDE Gad Benram (Portugal) compares the efficiency and overview of the problems that will consequence from altering from NumPy to JAX.

Introduction to JAX: environment friendly and reproducible ML framework by ML GDE Seunghyun Lee (Korea) launched JAX/Flax and their key options utilizing sensible examples. He defined the pure perform and PRNG, which make JAX specific and reproducible, and XLA and mapping features which make JAX quick and simply parallelized.

Data2Vec Fashion pre-training in JAX by ML GDE Vasudev Gupta (India) shares a tutorial for demonstrating how you can pre-train Data2Vec utilizing the Jax/Flax model of HuggingFace Transformers.

Distributed Machine Studying with JAX by ML GDE David Cardozo (Canada) delivered what makes JAX totally different from TensorFlow.

Picture classification with JAX & Flax by ML GDE Derrick Mwiti (Kenya) explains how you can construct convolutional neural networks with JAX/Flax. And he wrote a number of articles about JAX/Flax: What’s JAX?, Methods to load datasets in JAX with TensorFlow, Optimizers in JAX and Flax, Flax vs. TensorFlow, and so on..

Kaggle

DDPMs – Half 1 by ML GDE Aakash Nain (India) and cait-tf by ML GDE Sayak Paul (India) have been introduced as Kaggle ML Analysis Highlight Winners.

Forward process in DDPMs from Timestep 0 to 100

More energizing on Random Variables, All you might want to find out about Gaussian distribution, and A deep dive into DDPMs by ML GDE Aakash Nain (India) clarify the basics of diffusion fashions.

In Grandmasters Journey on Kaggle + The Kaggle E book, ML GDE Luca Massaron (Italy) defined how Kaggle helps folks within the information science business and which expertise you have to concentrate on aside from the core technical expertise.

Cloud AI

How Cohere is accelerating language mannequin coaching with Google Cloud TPUs by ML GDE Joanna Yoo (Canada) explains what Cohere engineers have accomplished to resolve scaling challenges in giant language fashions (LLMs).

ML GDE Hannes Hapke (United States) chats with Fillipo Mandella, Customer Engineering Manager at Google

In Utilizing machine studying to rework finance with Google Cloud and Digits, ML GDE Hannes Hapke (United States) chats with Fillipo Mandella, Buyer Engineering Supervisor at Google, about how Digits leverages Google Cloud’s machine studying instruments to empower accountants and enterprise house owners with near-zero latency.

A tour of Vertex AI by TFUG Chennai for ML, cloud, and DevOps engineers who’re working in MLOps. This session was in regards to the introduction of Vertex AI, dealing with datasets and fashions in Vertex AI, deployment & prediction, and MLOps.

TFUG Abidjan hosted two occasions with GDG Cloud Abidjan for college students {and professional} builders who need to put together for a Google Cloud certification: Introduction session to certifications and Q&A, Certification Research Group.

Flow chart showing shows how to deploy a ViT B/16 model on Vertex AI

Deploying 🤗 ViT on Vertex AI by ML GDE Sayak Paul (India) and Chansung Park (Korea) reveals how you can deploy a ViT B/16 mannequin on Vertex AI. They cowl some essential points of a deployment equivalent to auto-scaling, authentication, endpoint consumption, and load-testing.

Photo collage of AI generated images

TFUG Singapore hosted The World of Diffusion – DALL-E 2, IMAGEN & Secure Diffusion. ML GDE Martin Andrews (Singapore) and Sam Witteveen (Singapore) gave talks named “How Diffusion Works” and “Investigating Immediate Engineering on Diffusion Fashions” to convey folks up-to-date with what has been happening on the planet of picture era.

ML GDE Martin Andrews (Singapore) have accomplished three initiatives: GCP VM with Nvidia set-up and Comfort Scripts, Containers inside a GCP host server, with Nvidia pass-through, Putting in MineRL utilizing Containers – with linked code.

Jupyter Providers on Google Cloud by ML GDE Gad Benram (Portugal) explains the variations between Vertex AI Workbench, Colab, and Deep Studying VMs.

Google Cloud's Two Towers Recommender and TensorFlow

Practice and Deploy Google Cloud’s Two Towers Recommender by ML GDE Rubens de Almeida Zimbres (Brazil) explains how you can implement the mannequin and deploy it in Vertex AI.

Analysis & Ecosystem

WOMEN DATA SCIENCE, LA PAZ Club de lectura de papers de Machine Learning Read, Learn and Share the knowledge #MLPaperReadingClubs, Nathaly Alarcón, @WIDS_LaPaz #MLPaperReadingClubs

The primary session of #MLPaperReadingClubs (video) by ML GDE Nathaly Alarcon Torrico (Bolivia) and Girls in Knowledge Science La Paz. Nathaly led the session, and the neighborhood members participated in studying the ML paper “Zero-shot studying by means of cross-modal switch.”

In #MLPaperReadingClubs (video) by TFUG Lesotho, Arnold Raphael volunteered to guide the primary session “Zero-shot studying by means of cross-modal switch.”

Screenshot of a screenshare of Zero-shot learning through cross-modal transfer to 7 participants in a virtual call

ML Paper Studying Golf equipment #1: Zero Shot Studying Paper (video) by TFUG Agadir launched a mannequin that may acknowledge objects in photographs even when no coaching information is on the market for the objects. TFUG Agadir ready this occasion to make folks all for machine studying analysis and supply them with a broader imaginative and prescient of differentiating good contributions from nice ones.

Opening of the Machine Studying Paper Studying Membership (video) by TFUG Dhaka launched ML Paper Studying Membership and the group’s plan.

EDA on SpaceX Falcon 9 launches dataset (Kaggle) (video) by TFUG Mysuru & TFUG Chandigarh organizer Aashi Dutt (presenter) walked by means of exploratory information evaluation on SpaceX Falcon 9 launches dataset from Kaggle.

Screenshot of ML GDE Qinghua Duan (China) showing how to apply the MRC paradigm and BERT to solve the dialogue summarization problem.

Introduction to MRC-style dialogue summaries primarily based on BERT by ML GDE Qinghua Duan (China) reveals how you can apply the MRC paradigm and BERT to resolve the dialogue summarization drawback.

Plant illness classification utilizing Deep studying mannequin by ML GDE Yannick Serge Obam Akou (Cameroon) talked on plant illness classification utilizing deep studying mannequin : an finish to finish Android app (open supply undertaking) that diagnoses plant ailments.

TensorFlow/Keras implementation of Nystromformer

Nystromformer Github repository by Rishit Dagli gives TensorFlow/Keras implementation of Nystromformer, a transformer variant that makes use of the Nyström technique to approximate customary self-attention with O(n) complexity which permits for higher scalability.

RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Popular

Recent Comments