The main objectives of this project include: 1). Classifying car based on three classes of brands by applying transfer learning techniques such as ResNet-50, VGG-16 and VGG-19 classifiers on image dataset collected from Google and comparing the performance of these classifiera. 2). Applying various explainable techniques such as LIME and GRAD-CAM to explian the black-box deep learning transfer techniques used.
-
Notifications
You must be signed in to change notification settings - Fork 0
Lusanji/Explainable-car-brand-classification-
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Using LIME and Grad-CAM techniques to explain the results achieved by various image transfer learning techniques
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published