Learn how to use the LIME open-source image classification utility to understand the quality of a custom classification model.
- [Instructor] Now, continuing on,…in addition to the numerical output,…this example includes an additional library…that I think is particularly helpful…in understanding image classification,…so if we scroll down, we can see…that we have an explanation about the model.…It's called LIME.…So if we use ml explain,…it includes the LIME open source library,…and this is a library that performs…feature sensitivity analysis.…I highly recommend that you read the reference paper here…and I think it's a fantastic library…that really helps with understanding the quality…of image classification, and you'll see what I mean here.…
So if I take a look at ml explain…and I look at the analysis using LIME,…you can see that there is a section of the image…that's highlighted, and what this refers to…is the yellow line is showing you what section…of the image is being used for classification.…And the LIME work was quite groundbreaking…in that it demonstrated…that classifiers were predicting in a way…that was unintuitive to people.…
The sort of famous example that's included in the LIME paper…
- 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.