https://github.com/fel-thomas/simple_unet

Simple Unet implementation to copy paste
https://github.com/fel-thomas/simple_unet

deep-learning image-segmentation machine-learning python satellite-imagery tensorflow u-net unet

Last synced: about 1 year ago
JSON representation

Simple Unet implementation to copy paste

• Host: GitHub
• URL: https://github.com/fel-thomas/simple_unet
• Owner: fel-thomas
• Created: 2020-01-27T19:59:07.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2020-02-02T20:32:25.000Z (over 6 years ago)
• Last Synced: 2024-01-29T17:06:41.098Z (over 2 years ago)
• Topics: deep-learning, image-segmentation, machine-learning, python, satellite-imagery, tensorflow, u-net, unet
• Language: Python
• Homepage:
• Size: 120 KB
• Stars: 7
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          


  


    Unet to copy paste

  



Simple implementation of Unet top copy paste, using Keras and Tensorflow (2.X).

The implementation is offered in two forms : plain file and as a function.

Original paper [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597).

![Example of Unet architecture](assets/unet_example.png)

---

## Quick Start

```python

model = build_Unet(input_shape=(128, 128, 3), output_channels=1, depth=4)

model.summary()

```

### Dependencies

* Tensorflow (2.X)

You need Python 3.5 or later.

## Acknowledgements

-   [@tensorflow](https://github.com/tensorflow/tensorflow)

-   [@keras](https://github.com/keras-team/keras)

```

"U-Net: Convolutional Networks for Biomedical Image Segmentation."

Olaf Ronneberger, Philipp Fischer, and Thomas Brox

arXiv preprint arXiv:1505. 04597, 2015.

```

🖐 Thomas FEL, 2020