Amazon Interactive Video Service (Amazon IVS) announces its first point of presence (PoP) in Colombia. The new edge location will enable streamers and viewers based in Colombia to enjoy lower latency, better video quality, and increased capacity.
The AWS Serverless Application Model (SAM) announces general availability of AWS SAM Accelerate. The AWS SAM Command Line Interface (CLI) is a developer tool that makes it easier to build, locally test, package, and deploy serverless applications. AWS SAM Accelerate is a new capability of AWS SAM CLI that makes it easier for developers to test code changes against a cloud-based environment, reducing the time from local iteration to production-readiness.
El espacio de almacenamiento asignado a su clúster de Amazon DocumentDB (con compatibilidad con MongoDB) ahora se reduce en forma dinámica cuando elimina datos del clúster. Amazon DocumentDB es un servicio de base de datos creado específicamente para la administración de datos JSON a escala, completamente administrado e integrado con AWS, y ofrece una gran durabilidad a las empresas. Antes, cuando se eliminaban datos de Amazon DocumentDB, por ejemplo, al suprimir una colección, el espacio total asignado se mantenía igual. El espacio liberado se reutilizaba automáticamente cuando el volumen de datos aumentaba más adelante.
Starting today, Amazon AppStream 2.0 introduces support for streaming over UDP, when using the Windows native client. Amazon AppStream 2.0 is a fully managed service that provides non-persistent desktops, and application streaming products to end-users. Previously, you were able to stream over TCP via Windows native client. With your end users now working from home or in different countries compared to your corporate offices, they may operate in sub-optimal network conditions you are unable to control. These network conditions can impact your end users experience and productivity. With UDP streaming your end users will experience a more responsive streaming quality in sub-optimal network conditions, with higher round trip latency.
Amazon QuickSight now enables authors to setup rolling date to dynamically generate dashboard for end users. The rolling date functionality is now available for both date & time range filters and datetime parameters. Users will be able to set up rolling rules to fetch a date, such as today, yesterday, or different combinations of (start/end) of (this/previous/next) (year/quarter/month/week/day) and dynamically update the dashboard content based on when the dashboard is loaded. This feature brings flexibility and simplicity for users to build time-related dashboards. Without rolling date, users have to set up a static date and manually change it as needed. For further details, visit here.
Posted by Hee Jung, Developer Relations Community Manager / Soonson Kwon, Developer Relations Program Manager
ML in Action is a virtual event to collect and share cool and useful machine learning (ML) use cases that leverage multiple Google ML products. This is the first run of an ML use case campaign by the ML Developer Programs team.
Let us announce the winners right now, right here. They have showcased practical uses of ML, and how ML was adapted to real life situations. We hope these projects can spark new applied ML project ideas and provide opportunities for ML community leaders to discuss ML use cases.
4 Winners of “ML in Action” are:
Detecting Food Quality with Raspberry Pi and TensorFlow
By George Soloupis, ML Google Developer Expert (Greece)
This project helps people with smell impairment by identifying food degradation. The idea came suddenly when a friend revealed that he has no sense of smell due to a bike crash. Even with experiences attending a lot of IT meetings, this issue was unaddressed and the power of machine learning is something we could rely on. Hence the goal. It is to create a prototype that is affordable, accurate and usable by people with minimum knowledge of computers.
The basic setting of the food quality detection is this. Raspberry Pi collects data from air sensors over time during the food degradation process. This single board computer was very useful! With the GUI, it’s easy to execute Python scripts and see the results on screen. Eight sensors collected data of the chemical elements such as NH3, H2s, O3, CO, and CH4. After operating the prototype for one day, categories were set following the results. The first hours of the food out of the refrigerator as “good” and the rest as “bad”. Then the dataset was evaluated with the help of TensorFlow and the inference was done with TensorFlow Lite.
Since there were no open source prototypes out there with similar goals, it was a complete adventure. Sensors on PCBs and standalone sensors were used to get the best mixture of accuracy, stability and sensitivity. A logic level converter has been used to minimize the use of resistors, and capacitors have been placed for stability. And the result, a compact prototype! The Raspberry Pi could attach directly on with slots for eight sensors. It is developed in such a way that sensors can be replaced at any time. Users can experiment with different sensors. And the inference time values are sent through the bluetooth to a mobile device. As an end result a user with no advanced technical knowledge will be able to see food quality on an app built on Android (Kotlin).
Election Watch: Applying ML in Analyzing Elections Discourse and Citizen Participation in Nigeria
By Victor Dibia, ML Google Developer Expert (USA)
This project explores the use of GCP tools in ingesting, storing and analyzing data on citizen participation and election discourse in Nigeria. It began on the premise that the proliferation of social media interactions provides an interesting lens to study human behavior, and ask important questions about election discourse in Nigeria as well as interrogate social/demographic questions.
It is based on data collected from twitter between September 2018 to March 2019 (tweets geotagged to Nigeria and tweets containing election related keywords). Overall, the data set contains 25.2 million tweets and retweets, 12.6 million original tweets, 8.6 million geotagged tweets and 3.6 million tweets labeled (using an ML model) as political.
By analyzing election discourse, we can learn a few important things including – issues that drive election discourse, how social media was utilized by candidates, and how participation was distributed across geographic regions in the country. Finally, in a country like Nigeria where updated demographics data is lacking (e.g., on community structures, wealth distribution etc), this project shows how social media can be used as a surrogate to infer relative statistics (e.g., existence of diaspora communities based on election discussion and wealth distribution based on device type usage across the country).
Data for the project was collected using python scripts that wrote tweets from the Twitter streaming api (matching certain criteria) to BigQuery. BigQuery queries were then used to generate aggregate datasets used for visualizations/analysis and training machine learning models (political text classification models to label political text and multi class classification models to label general discourse). The models were built using Tensorflow 2.0 and trained on Colab notebooks powered by GCP GPU compute VMs.
Bioacoustic Sound Detector (To identify bird calls in soundscapes)
By Usha Rengaraju, TFUG Organizer (India)
(Bird image is taken by Krisztian Toth @unsplash)
“Visionary Perspective Plan (2020-2030) for the conservation of avian diversity, their ecosystems, habitats and landscapes in the country” proposed by the Indian government to help in the conservation of birds and their habitats inspired me to take up this project.
Extinction of bird species is an increasing global concern as it has a huge impact on food chains. Bioacoustic monitoring can provide a passive, low labor, and cost-effective strategy for studying endangered bird populations. Recent advances in machine learning have made it possible to automatically identify bird songs for common species with ample training data. This innovation makes it easier for researchers and conservation practitioners to accurately survey population trends and they’ll be able to regularly and more effectively evaluate threats and adjust their conservation actions.
This project is an implementation of a Bioacoustic monitor using Masked Autoencoders in TensorFlow and Cloud TPUs. The project will be presented as a browser based application using Flask. The deep learning prototype can process continuous audio data and then acoustically recognize the species.
The goal of the project when I started was to build a basic prototype for monitoring of rare bird species in India. In future I would like to expand the project to monitor other endangered species as well.
By Martin Andrews and Sam Witteveen, ML Google Developer Experts (Singapore)
Over the last 3 years, Red Dragon AI (a company co-founded by Martin and Sam) has been developing real-time digital “Personas”. The key idea is to enable users to interact with life-like Personas in a format similar to a Zoom call : Speaking to them and seeing them respond in real time, just as a human would. Naturally, each Persona can be tailored to tasks required (by adjusting the appearance, voice, and ‘motivation’ of the dialog system behind the scenes and their corresponding backend APIs).
The components required to make the Personas work effectively include dynamic face models, expression generation models, Text-to-Speech (TTS), dialog backend(s) and Speech Recognition (ASR). Much of this was built on GCP, with GPU VMs running the (many) Deep Learning models and combining the outputs into dynamic WebRTC video that streams to users via a browser front-end.
Much of the previous years’ work focussed on making the Personas’ faces behave in a life-like way, while making sure that the overall latency (i.e. the time between the Persona hearing the user asking a question, to their lips starting the response) is kept low, and the rendering of individual images matches the 25 frames-per-second video rate required. As you might imagine, there were many Deep Learning modeling challenges, coupled with hard engineering issues to overcome.
In terms of backend technologies, Google Cloud GPUs were used to train the Deep Learning models (built using TensorFlow/TFLite, PyTorch/ONNX & more recently JAX/Flax), and the real-time serving is done by Nvidia T4 GPU-enabled VMs, launched as required. Google ASR is currently used as a streaming backend for speech recognition, and Google’s WaveNet TTS is used when multilingual TTS is needed. The system also makes use of Google’s serverless stack with CloudRun and Cloud Functions being used in some of the dialog backends.
Visit the Persona’s website (linked below) and you can see videos that demonstrate several aspects : What the Personas look like; their Multilingual capability; potential applications; etc. However, the videos can’t really demonstrate what the interactivity ‘feels like’. For that, it’s best to get a live demo from Sam and Martin – and see what real-time Deep Learning model generation looks like!
Amazon S3 on Outposts now supports presigned URLs for granting time-limited access to objects stored locally on an Outpost. S3 on Outposts bucket owners can now more easily share objects with individuals in their Virtual Private Cloud (VPC).
You can now use AWS Application Migration Service (AWS MGN) for use cases that are subject to System and Organization Controls (SOC) reporting. You can also now install the AWS Application Migration Service agent on your source servers using AWS Identity and Access Management (IAM) temporary security credentials with limited permissions. AWS Application Migration Service allows you to quickly migrate and modernize applications on AWS.
Amazon QuickSight launches a suite of functions called Level Aware Calculations (LAC). The new calculation enables customers to specify the level of granularity that they want the window functions (in what window to partition by) or aggregate functions (at what level to group by) to be conducted. This brings flexibility and simplification for users to build some advanced calculations and powerful analyses. Without LAC, user will have to prepare pre-aggregated tables in their original data source, or run queries in the data prep phase to enable those calculations. For further details, visit here.
AWS DataSync now supports copying files to and from Amazon FSx for NetApp ONTAP, a storage service that allows customers to launch and run fully managed ONTAP file systems in the cloud. Using AWS DataSync, you can quickly and securely migrate your data from your on-premises storage, the edge, or other clouds to your FSx for NetApp ONTAP file systems running in AWS. You can also use DataSync to move data between your FSx for NetApp ONTAP file system and Amazon S3 buckets, Amazon EFS file systems, or other Amazon FSx file systems.
Amazon RDS now allows you to have up to 20 concurrent snapshot copy requests per destination region per account, an increase from the former limit of five concurrent copies per destination region per account.
AWS Fargate para Amazon Elastic Kubernetes Service (EKS) ya está disponible en la región de China (Pekín) de Amazon Web Services administrada por Sinnet, y la región de China (Ningxia) de Amazon Web Services administrada por NWCD. AWS Fargate es un motor informático sin servidor de pago por uso que permite centrarse en la creación de aplicaciones sin tener que administrar los servidores. Amazon EKS es un servicio de contenedor administrado para ejecutar y escalar aplicaciones Kubernetes. Con el uso del cómputo sin servidor de AWS Fargate en los clústeres de Amazon EKS se elimina la necesidad de aprovisionar y administrar servidores, permite especificar y pagar recursos por aplicación y mejora la seguridad mediante el aislamiento de aplicaciones por diseño.