Take AutoML Vision for a test drive

What kind of cloud is this?

I don’t know either. Can you think of other types of images that would be useful to classify? For example, if you have an online tire shop, wouldn’t it be cool if your customers could upload a photo of their current tire to find a matching replacement?

AutoML can help your tire shop decrease the number of returns and increase customer delight. And it’s easier than you think – learn how to take advantage of this powerful new tool with a new lab, AutoML Vision API.

Here’s some of what you’ll do:

  • You’ll be prompted to log into the AutoML UI. Open the link in a new tab to make it easy to hop between AutoML and your lab manual. Then, you’ll log into AutoML with your Qwiklabs-provided credentials.
  • In the AutoML UI, you will see a button for “Billing”. You do not need to worry about billing for this lab, as Qwiklabs covers the cost of this lab for you.
  • When you load data into your storage bucket, you’ll set your project name with one of the first commands you run. Find your project name on the left of your lab manual, just below your GCP credentials:

AutoML is currently in beta, so we expect to see constant changes to the user interface. Send any questions to Support@Qwiklabs.com and we’ll be happy to help. Plus you’ll help us keep the lab up to date as the product continues to improve!

Curious about what type of clouds were spotted during our trip to Muir Woods? Here are our model’s predictions:

The model is 99% certain these are cumulus clouds! Prediction certainty and accuracy would be better if we trained our model with more than 20 images per category. When you’re helping customers order tires, you will probably want to use 100+ photos per category.

Happy lab-taking!

 

Dig deep into BigQuery Machine Learning with Google Cloud

You don’t need a B.S. in Computer Science to take advantage of powerful GCP data analysis tools. Google announced fully managed service at Next’18, BigQuery ML (BQML). BQML allows you to:

  • Create, train, evaluate, predict and deploy machine learning models with minimal coding
  • Use SQL directly in the database

Get started with BQML by taking the Predict Visitor Purchases with a Classification Model in BQML lab today and get a 30 day pass (free of charge, no CC required) to help you take advantage of this shiny new toy — I mean, seriously, an impactful data analysis tool!

Here’s some of what you’ll do in the lab:

  • Explore Ecommerce data & run the Query to find out what percentage made a purchase from website visitors:
  • Run the Query to find out your top 5 selling products: 
  • Preview the demo dataset to find useful features a machine learning model uses to understand if a first time visitor will return to make a purchase & dig deeper to know the risks of only using these fields for your classification model:
  • Evaluate classification model to maximize the True Positive Rate (predict that returning users will make a purchase) & visualize a ROC (Receiver Operating Characteristic) curve to maximize the area under the curve:Take the lab  and get your 30 day pass to be one step closer to earning the Data Engineering Quest badge.

Google Cloud training: 33 new labs

Big things are happening in Google Cloud. BigQuery ML, for example, just announced at Next ‘18. Even if you weren’t there, you can still take advantage of 33+ new labs released at the conference. And if you haven’t yet seen the new BigQuery interface, you can check it out with a lab.

Here’s what’s new on Qwiklabs:

  1. Predict Visitor Purchases with a Classification Model in BQML: Use the latest and greatest technology to answer the top question in online retail. Click here to take the lab free of charge, first 25 readers only.
    Google Cloud BQML lab
  2. Classify Images of Clouds in the Cloud with AutoML Vision: AutoML Vision helps developers with limited ML expertise train high quality image recognition models. Take AutoML on a test drive with this lab.
  3. Managing Cloud Infrastructure with Terraform: #MakeGoogleDoIt – launch your cloud resources, that is. Learn how Terraform can boost your team’s efficiency, by creating configuration files that can be shared, treated as code, edited, reviewed, and versioned.
    Terraform Google Cloud Training
  4. Kubernetes Solutions: Work hard, play harder. Use Kubernetes to run dedicated gaming servers, plus 7 more advanced Kubernetes use cases in this Quest.
    Kubernetes Google Cloud Training
  5. Network Performance and Optimization: If you’re the one they call when the network is down, these labs are for you. Learn how GCP can help you sleep at night with better network speed, performance, and reliability.
    Networking Google Cloud Training
  6. Challenge Quest: Your company is ready to launch a brand new website, but the person who built the new site left the company before they could deploy it. Your challenge is to deploy the site in the public cloud. This and six other scenarios make up the Challenge Quest, to test your skills in a simulated crisis. Good luck!
    Challenge lab: Google Cloud Training

If you have an Advantage subscription, all of this new content is included in your subscription, no extra charge. Not a subscriber yet? Use promo code NEW33 for 33% off your first month. Promo code is valid through August 1o (Friday).

Good luck on your next Quest!

Get ready for Google Cloud Next ‘18

Are you ready for Next week? Join Google Cloud for the event of the year. Grow your network, grow your skills, and learn about the growth of Google Cloud – what’s happening now, and what’s next. And even if you’re not in San Francisco, join a Next event near you. Find one here.

Get a head start today by familiarizing yourself with key cloud concepts. Cloud training is available online, on-demand and on the real cloud console (not a video, lecture, or slideshow). Check out these hands-on labs, and follow any of the links below in the next 24 hours and you’ll get 25 Qwiklabs credits free of charge to help you start your Google Cloud training journey:

Complete a Quest and you’ll earn a badge. A badge shows your “flight time” with Google Cloud, and differentiates you as someone with hands-on GCP experience. Click this link → log into Qwiklabs → you will get 25 Qwiklabs credits to help you tackle your next Quest. Hurry, link expires in 24 hours.

See you next week!

The independence of upskilling

The U.S. will be celebrating its 242nd year of independence on July 4th. Set your own “independence” day – learn new skills and take your career where *you* want to go. Enroll in any of these Quests by Monday, July 8th and get a 30 day pass to earn these badges (free of charge, no credit card required). What skills can you add to your resume? 

  1. Baseline: Infrastructure Quest: Learn to use Cloud Storage, deploy a containerized application with Google Kubernetes Engine, build a Docker image, create and deploy a Cloud Function, publish and consume messages, create a Cloud IoT Core device registry and use Cloud Spanner. Here’s the badge you’ll earn:

  1. GCP Essential Quest: This Quest has the best of both worlds! While it helps you get more comfortable with the Google Cloud, like spinning up a virtual machine, it also challenges you to configure key infrastructure tools through working with more advanced Stackdriver and Kubernetes concepts. Tackle the Quest to earn this badge:

  1. Application Development Quest: Think you’re a Java Jedi or a Python powerhouse? Well we’ve got challenging Quests for you! In these two Quests, you’ll either put your Java or Python skills to test by developing cloud-based applications using GCP services such as App Engine, Cloud Datastore and Cloud Spanner. Then integrate these services and deploy to an App Engine and a Kubernetes Engine. Are you excited to earn these badges?

 

                                                           

 

 

4. Scaling Your Infrastructure Quest: Not for beginners! If you’re ready for an expert level Quest, this one’s for you. Learn how to: set up multiple NAT gateways, deploy an autoscaling Compute Engine, customize Stackdriver logging, set up Jenkins on Google Kubernetes Engine to help orchestrate your software delivery pipeline and use Spinnaker to continuously deploy the application when changes are made. You’ll earn this badge:

Celebrate your own independence day with us. Enroll by Monday, July 8th, get a 30 day pass (free of charge, no credit card required), and take charge of your career!

Dig deep into Machine Learning with Google Cloud: Part 2

If you haven’t enrolled in the machine learning Quests mentioned in this blog, you’re missing out! One last chance for free labs, follow any of the Quest links in this post and get a 30 day pass to finish these Quests. Hurry, offer expires Thursday, June 28 (free of charge, no CC required).

Tackle any of the Quests from the roadmap below to become a ML master. If you’re a beginner… begin at the beginning 🙂

Earn a machine learning Quest badge or two, get practice with real-world scenarios, and make the most out of your time at Next ‘18 with some ML rockstars. Who might you meet at Next ’18?

Fei Fei Li is a Chief Scientist of Cloud AI and ML at Google Cloud. She works in the areas of computer vision and cognitive neuroscience. Her publications include Scaling Human-Object Interaction Recognition through Zero-Shot Learning  and Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks. Get hands-on practice with Cloud AI at scale with the Machine Learning APIs Quest.

Or you might run into Valliappa Lakshmanan. Lak is on a mission to democratize machine learning so anyone can do it using Google’s infrastructure. Check out his latest book, Data Science on the Google Cloud Platform, explaining how to apply statistical and machine learning methods to real-world problems. And try it for yourself with a lab from the Scientific Data Processing Quest!

Take some labs ahead of time, gain a little experience, and ask better questions at the ML sessions offered at the Next ’18! Check out these sessions:

Can’t get enough of machine learning? When you register for Next ‘18, you will have the option to add some of these ML boot camps:

    • End-to-End Machine Learning with TensorFlow on GCP: You’ll go through the process of building a complete machine learning pipeline, covering ingest, exploration, training, evaluation, deployment and prediction.
    • Building and updating a Machine Learning Model on Edge Network using Cloud ML: You’ll learn how to process and store IoT or other data using Cloud Pub/Sub, Cloud Dataflow, Cloud Storage, and Google BigQuery.
    • Building Chatbots with Machine Learning: You’ll use Dialogflow and Cloud Natural Language API to rapidly convert an HR manual document into a fully functional and conversational chatbot. You’ll also add text and voice interactions to the chatbot and secure and scale it for production.

If you can’t make it to Next in San Francisco, take classes worldwide. Find one here.

To make the most of your time at Next ’18, enroll in these ML Quests by Thursday, June 28 (free of charge, no CC required).

Dig deep into Machine Learning with Google Cloud

Fun fact: there are 1,829 open positions for machine learning engineers on LinkedIn. Do you want to become a machine learning engineer? It’s easier than you might think, and we can help with a Quest or two.

Tackle any of the Quests from the roadmap below and become a ML expert:

1. Enroll in Baseline: Data, ML & AI Quest – If you’re new to ML, it’s a perfect Quest! You’ll work with big data, machine learning and artificial intelligence services in Google Cloud, like Dataproc and Bigtable.  Enroll now and get a free 30 day pass to earn this badge, plus as many others as you can (free of charge, no CC required). Hurry, link expires Thursday, June 21. 

 

2. The Machine Learning APIs Quest: This is the next step in your ML journey. You’ll capture text strings from images, recognize characters translate text into other languages using Cloud Vision API, Natural Language API and Translation API. You’ll even build a responsive chat bot using Google Cloud Dialogflow and train & deploy a TensorFlow model to Cloud ML Engine for serving (prediction).

 3. Enroll in Scientific Data Processing: Ready for a challenge? Tackle this Quest next. You’ll explore public domain scientific data sets, and learn to manipulate and transform data using the power of Google’s cloud infrastructure.

Can’t get enough of machine learning? Want to know what’s Next?  Stay tuned for Part 2!

This is the Quest you have been looking for…

You have been waiting patiently for a security training Quest…. today’s your lucky day! A new Quest from Qwiklabs, just released: Security & Identity Fundamentals. Dig deep into the building blocks of Google Cloud Platform Security by working with: Cloud Identity and Access Management (IAM), Network Security, setting up VPCs, VPNs and a private Kubernetes Cluster.

Are you ready to earn your Google Cloud Security and Identity badge? Click here to accept the challenge! (And use this link for 10 credits free of charge to help you along… click now, offer expires Friday.)

Here’s some of what you’ll do in this Quest:

Cloud IAM Custom Roles: Work with the right tools to manage resource permissions. Instead of directly granting users permissions, you grant them roles, which bundles permissions to map job functions within your company to groups and roles. Permissions management at scale? Yup.

Cloud Key Management Storage (KMS): Practice with advanced features of Google Cloud Security and Privacy APIs, set up a secure Cloud Storage bucket and manage keys and encrypted data using KMS. You’ll even use the Enron Corpus!

Virtual Private Cloud (VPC) Network Peering: Work with private connectivity across two VPC networks even if they don’t belong to same project or same organization. Plus, learn to save money with lower GCP egress bandwidth costs.

Cloud Security Scanner: Learn how to identify security vulnerabilities in your Google App Engine web applications. You will scan a sample app – can you find the vulnerabilities?

Data Loss Prevention: Practice with an intelligent data service, Google Cloud Dataprep, to visually explore, clean and prepare data for analysis. This one’s in beta so you’ll be one of the first to use it!

Private Kubernetes Cluster: Learn how to create a private cluster in the cloud environment. Since nodes in the private cluster do not have public IP addresses, your workload runs in an isolated environment from the Internet. This one’s a two-fer, which means if you complete this one lab, you’re making progress on both your Security & Identity Quest, and your Kubernetes in the Google Cloud Quest.

Ready to tackle this challenge? Enroll by Friday, June 22 and get 10 Qwiklabs credits free of charge (no credit card required).

 

 

Next ’18: Got your ticket?

Are you ready for the Next ‘18 conference? You’ll get access to Google keynotes, working sessions, exclusive certification opportunities, expert Q&A, opportunities to participate in bootcamps, and more. And if you can’t make it to San Francisco, check out these Next Extended events around the world. 

Next ’18 is the perfect opportunity to take a certification exam. Not sure where to begin, or how to prepare? Start your certification journey with hands-on labs. You can even take labs before the event so you get the most out of your experience at the conference.

Enroll in any of the following Quests, and get 30 credits free of charge (no credit card required). 

 1. The GCP Essential Quest is the most popular Quest of all time. Practice with GCP basics like starting a Virtual Machine and working with key infrastructure tools like Stackdriver and Kubernetes. Complete the Quest and you’ll earn this badge:

2. Need more specialized practice with the Google Cloud? Tackle the Baseline: Infrastructure Quest and you will learn to use Cloud Storage, deploy a containerized application with Google Kubernetes Engine, build a Docker image, create and deploy a Cloud Function, publish and consume messages, create a Cloud IoT Core device registry and use Cloud Spanner. Here’s the badge you’ll earn:

3. Hoping to become a certified Google Cloud Architect? Next attendees who get certified will have exclusive access to the certification lounge (and snacks!). Complete the Cloud Architecture Quest to help you practice exam topics. Get in-depth experience with Identity and Access Management (IAM), infrastructure scenarios, Cloud Security and Privacy APIs, breaking an application into microservices, debugging, API call tracing and using Deployment Manager to establish alerts to trigger incident response. You’ll earn another badge, too!

4. Google’s Data Engineering certification is unique. Set yourself apart by earning this certification. Practice key exam concepts with the Data Engineering Quest (designed by Google’s training team). You’ll get experience with TensorFlow, an IoT pipeline, BigQuery and Datalab, and even learn how to correspond to your sales data with the weather! Here’s the badge you’ll earn:

See you at Next ’18!

 

 

TensorFlow with Machine Learning Engine and Datalab: There’s a lab for that

A Machine Learning algorithm walks into a bar. The bartender asks, “What will you have?”

The ML algorithm: “What’s everyone else having?”

If you laughed, you’re probably into machine learning. And because you laughed at our terrible joke, have one lab on us. Follow this link to take the lab “Using Distributed TensorFlow with Cloud ML Engine and Cloud Datalab” free of charge.

Here are the steps you’ll take to do the lab and be one step closer to earning your Google Cloud Solutions ll badge!

  1. Sign into Google Cloud Platform using the lab credentials:

You might have noticed – the lab instructions tell you to go to “Products and Services” but the menu in the console has changed. The cloud is always changing! When you see things like this, let us know (just click the yellow button  at the bottom-right of the screen) so we can improve the lab. Thanks!

2. Train the model on Cloud Machine Learning Engine

3. Visualizing the training process with TensorBoard

4. Draw a number with your cursor – can you think of anything else to sketch?

Did you see that red error message I got at first? Can you spot what happened?

Still can’t get enough of Machine Learning? Well, watch a short Machine Learning demo with Josh & Heather, practice with the Cloud ML Engine lab they demo (click the link in the YouTube description), then get more practice with the Using Distributed TensorFlow with Cloud ML Engine and Cloud Datalab.

Don’t forget to follow this link to get 25 Qwiklabs credits to take the lab and other Data and Machine Learning labs in the Google Cloud Solutions II Quest free of charge. Hurry, the link expires Friday, June 8th.