This project uses annotated images of soles from the shoe to train the model with UNET architecture in order to obtain a mask with predicted sole outline and location.This approach can be used in the shoe recycling industry to locate the sole and separate it from the upper part of the shoe, which would be an alternative method of sepparating the rubber part of the show within shoe-recycling industry.
Implemented in PyTorch.
Used dataset : UT Zappos50K - https://vision.cs.utexas.edu/projects/finegrained/utzap50k/
-
Notifications
You must be signed in to change notification settings - Fork 0
This project uses annotated images of soles from the shoe to train the model with UNET architecture in order to obtain a mask with predicted sole outline and location
License
marseller/Shoe-sole-segmentation
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
This project uses annotated images of soles from the shoe to train the model with UNET architecture in order to obtain a mask with predicted sole outline and location
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published