Learn how to use a Cloud Datalab notebook to create a custom TensorFlow model for photo classification.
- [Instructor] Now to see an example…of a custom ML model using Cloud ML Engine,…we're going to take a look at one of the Google samples.…Now I've run the notebook in advance,…just to save us some time, but we'll just review it.…This is hosted on DataLab,…so you may remember from a previous movie,…that we created GCE instance with DataLab…and here what I've done is I've just reconnected to it.…Because it actually stops…if you don't access it for a while.…And then you may remember that you connect on port 8081…and then you can see the Jupyter-style notebook.…
Now what I've done is I've drilled in to some of the samples…and we're gonna take a look…at the flower classifier small dataset example.…And this is using publicly available data from the UCI…or University of California at Irvine data repository,…so you can replicate this as well.…This notebook is a great example…showing the lifecycle to prepare the data, analyze the data,…and then use some higher level libraries…so that you can access the tensor TensorFlow algorithm…
- 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.