|
--- |
|
library_name: keras |
|
language: |
|
- pt |
|
- en |
|
tags: |
|
- art |
|
- image |
|
- remove-background |
|
- u^2-net |
|
- residual |
|
--- |
|
|
|
## U²-Net |
|
<p>This is an implementation of U²-Net for image background removing purposes based on <a href="https://arxiv.org/pdf/2005.09007" target="_blank">this article</a>. The U²-Net architecture is designed to capture both fine details and global context, making it highly effective for image segmentation tasks such as background removal. |
|
|
|
## Dataset |
|
Dichotomous Image Segmentation (DIS) is a dataset wich contains around 5k images (images + masks) and it's used in image segmenation model training.<br> |
|
You can find more about this dataset <a href="https://github.com/xuebinqin/DIS" target="_blank">here.</a> |
|
|
|
## Me: |
|
Find me at GitHub: <a href="https://github.com/reidn3r">https://github.com/reidn3r</a> <br> |
|
Find me at Linkedin: <a href="https://www.linkedin.com/in/reidner-adnan/">https://www.linkedin.com/in/reidner-adnan/</a> |
