The Developer Show — TL;DR 106
The Developer Show is where you can stay up to date on all the latest Google Developer news, straight from the experts.
Have a question? Use #AskDevShow to let us know!
TensorRT and TensorFlow 1.7
NVIDIA® TensorRT is a library that optimizes deep learning models for inference and creates a runtime for deployment on GPUs in production environments. TensorRT and TensorFlow are integrated with TensorFlow 1.7. In our tests, we found that ResNet-50 performed 8 time faster under 7 milliseconds latency with the TensorFlow-TensorRT integration using NVIDIA Volta Tensor Cores as compared with running TensorFlow only. For graphs and code, check out the post.
Android Studio 3.1
Android Studio 3.1 is now available to download in the stable release channel. The focus areas for this release are around product quality and app development productivity. In addition to many underlying quality changes, we added several new features into Android Studio 3.1 that you should take a look at integrating into your development flow including a C++ performance profiler, better code editor support to aid in your SQL table and query creation statements, and better lint support for your Kotlin code. Details and screenshots are on the post.
Wear OS by Google
The Wear OS developer preview is now available, bringing Android P platform features to wearables. Included are the dark UI system theme and restriction related to non-SDK methods and fields. Install instructions are on the post.
Stackdriver APM and Stackdriver Profiler
Stackdriver Profiler is now available. It lets you profile and explore how your code actually executes in production, to optimize performance and reduce cost of computation. Head on over to the post to learn more about the the Stackdriver Application Performance Management toolkit including integrations between Stackdriver Debugger and GitHub Enterprise and GitLab.
Cloud Text-to-Speech
You can use Cloud Text-to-Speech for high-quality text-to-speech synthesis that produces natural sounding speech. It lets you choose from 32 different voices from 12 languages and variants, correctly pronounces complex text such as names, dates, times and addresses, *and* allows you to customize pitch, speaking rate, and volume gain. Links to get started are on the post.
Kubernetes Engine Private Clusters
Kubernetes Engine Private Clusters is now available in beta. With it, you can deploy clusters privately as part of the Google Virtual Private Cloud. Your cluster’s nodes can then only be accessed from within the trusted VPC. Getting started instructions are on the post.