- In this project i did Classification with localization (aka object localization)
- I used portion of Caltech-101 dataset this protion was ['airplanes', 'Faces', 'Motorbikes']
- Version 2:
- functions that I used to parse data and show image all in my_helper_funcs.py file
- I trained two transfer learning models:
- first one was with NasNet as base model
- training class accuracy: 100%
- training bounding box loss: 1551.15
- Validation accuracy: 100%
- training bounding box loss: 1293.05
- second model was with VGG-16 as base model
- training class accuracy: 0.9984%
- training bounding box loss: 688.58
- Validation accuracy: 100%
- training bounding box loss: 802.32
- first one was with NasNet as base model
- Version 3:
-
Notifications
You must be signed in to change notification settings - Fork 0
abdo-ashraf/Image-Classification-with-localization
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published