Review an image search application architecture that uses multiple types of GCP machine learning services.
- [Woman Speaking] This next reference architecture…is interesting because it uses…three different types of GCP machine learning services.…The use case is image processing, so let's start on…the left side.…We're gonna start with the mobile client,…and they're gonna upload an image.…Which is gonna be saved to cloud storage.…That is subsequently going to trigger a…Cloud Pub/Sub message.…Next the Cloud Pub/Sub push notification will call a…Google Cloud App Engine end point.…
Then the first layer of machine learning will be invoked.…The request label detection and add detected labels to…the search index will be handled by the Cloud Vision API.…What's really interesting about this use case is that…after that step there are two optional steps with…additional types of machine learning.…You'll notice on the step after Cloud Vision API,…the next step is to request a custom label detection from…AutoML Vision models and add those to the search index.…
Do you remember when we were looking at the…difference between Cloud Vision API and AutoML Vision and…
- Hosting options: Serverless, containers, and virtual machines
- Enabling the GCP ML AIs
- Preparing data with Cloud Dataflow and Dataprep
- Modeling predictions for images, video, text to speech, and cloud translation
- Machine learning with AutoML
- Advanced machine learning and deep learning
- Machine learning architectures
Skill Level Intermediate
1. Machine Learning on Google Cloud Platform
2. Machine Learning API Services
3. Machine Learning with AutoML
Understand AutoML Vision4m 57s
4. Advanced Machine Learning
5. Machine Learning Architectures
Next steps1m 30s
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.