Learn how to use TensorBoard to evaluate and understand a custom ML photo classification model built on TensorFlow.
- [Instructor] As we continue exploring working with…custom algorithms for deep neural networks using TensorFlow,…let's return to an earlier example,…and this was where we were using the flower classifier,…and you might remember that I had referred to the library…that was abstracted above the top of TensorFlow…and you access with the magic sign in line one here,…percent sign, percent sign, and then ML.…This is a library that calls TensorFlow activities.…In addition to being able to use TensorFlow more easily…here without understanding the underlying details,…there's also another tool that can help you…to get into the details of how TensorFlow is being used…for training and model prediction.…
And that's a tool called TensorBoard.…So I've paused this model after the prediction,…and you can see here we have TensorBoard…which started successfully, click here to access it.…So I have it loaded.…So TensorBoard is a predictor in a very great detail…of your model accuracy.…So you might remember when we were working with…
- 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.