Intro to ML: Image Processing

Name: Intro to ML: Image Processing
Start: 2021-10-24T19:00:00+08:00
End: 2021-10-24T23:00:00+08:00

National Taiwan Normal University

Google Cloud Study Jams are community-run study groups for developers. Hands-on technical labs。This is an co-host event with TKU. 

Oct 24, 2021, 11:00 AM – 3:00 PM

7

RSVP'd

RSVP Now

Key Themes

Career DevelopmentGoogle CloudMachine Learning

About this event

Using large scale computing power to recognize patterns and "read" images is one of the foundational technologies in AI, from self-driving cars to facial recognition. The Google Cloud Platform provides world class speed and accuracy via systems that can utilized by simply calling APIs. With these and a host of other APIs, GCP has a tool for just about any machine learning job. In this introductory quest, you will get hands-on practice with machine learning as it applies to image processing by taking labs that will enable you to label images, detect faces and landmarks, as well as extract, analyze, and translate text from within images.

When

Sunday, October 24, 2021
11:00 AM – 3:00 PM UTC

Agenda

Welcome!	Self introductions, lightning talks, chat. Get Every one ready with their qwikilabs account.
AI Platform: Qwik Start	The sample builds a classification model for predicting income category based on United States Census Income Dataset. The two income categories (also known as labels) are: >50K — Greater than 50,000 dollars <=50K — Less than or equal to 50,000 dollars The sample defines the model using the Keras Sequential API. The sample defines the data transformations particular to the census dataset, then assigns these (potentially) transformed features to either the DNN or the linear portion of the model.
APIs Explorer: Qwik Start	The Google APIs Explorer is a tool that helps you explore various Google APIs interactively. With the APIs Explorer, you can: Browse quickly through available APIs and versions. See methods available for each API and what parameters they support along with inline documentation. Execute requests for any method and see responses in real time. Make authenticated and authorized API calls. Search across all services, methods, and your recent requests to quickly find what you are looking for. The APIs Explorer uses its own API key whenever it makes a request. When you use the APIs Explorer to make a request, it displays the request syntax, which includes a placeholder labeled {YOUR_API_KEY}. If you want to make the same request in your application, you need to replace this placeholder with your own API key. What you'll do Create a Cloud Storage bucket. Upload an image to Cloud Storage and make it public. Make a request to the Vision API with that image.
Break, Chat, QA	Your chance to network and chat up with each other with AMA(ask me anything)
Classify Images of Clouds in the Cloud with AutoML Vision	AutoML Vision helps developers with limited ML expertise train high quality image recognition models. Once you upload images to the AutoML UI, you can train a model that will be immediately available on Google Cloud for generating predictions via an easy to use REST API. In this lab you will upload images to Cloud Storage and use them to train a custom model to recognize different types of clouds (cumulus, cumulonimbus, etc.). What you'll learn Uploading a labeled dataset to Cloud Storage and connecting it to AutoML Vision with a CSV label file. Training a model with AutoML Vision and evaluating its accuracy. Generating predictions on your trained model.
Break, Chat, QA and Next steps	Your chance to network and chat up with each other with AMA(ask me anything) What would you like our next cloud study jam to be on?