Learn how to train an AutoML Vision model with properly prepared input data (photos).
- [Voiceover] The next step in the process,…after you've uploaded your labeled data,…is to train your model.…In addition to Google automatically selecting…the most appropriate model,…Google will set the hyperparameters…and these are parameters values,…such as batch size and training size, so on, so forth.…In order to do this, Google pre-splits your input data,…so you have your input data set and by default,…and this can be adjusted, as shown here,…80% of the images are used for model training,…10% of the images are used for hyperparameter tuning…and/or to decide when to stop training…and 10% of images are used for evaluating the model.…
These images are not used in training.…This is sometimes called a holdout set.…This becomes important when you're looking…at the quality of the output of the model…and determining whether you need to, for example,…provide more sample input photos, different kinds of labels,…different kinds of photos.…We'll be addressing that later in the section of movies,…but for right now, we need to train our model.…
- 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.