This is a simple implementation of the U-Net arhitecture and a project to utilize segmentation using Tensorboard.

A Korean translation of U-Net Paper: http://bit.ly/UNet_Paper_Translation

This tutorial depends on the following libraries:

• Tensorflow == 1.14
• Keras == 2.3.1

My computing resources are as follows:

• CPU: Intel i7-8700k
• GPU: GTX 1080ti
• RAM: 64GB

python main.py

Tensorboard

tensorboard --logdir=./logs --host localhost

The original dataset is from ISBI challenge, and I've downloaded it and done the pre-processing.

You can find it in folder data/membrane.

1. Data Augmentation

10 times more images were used from the original number.

Augmentation images examples

2. Hyperparameters

• epochs : 50
• batch size : 5
• Learning rate : 0.0001

3. Optimizer, Loss function and Metric

• Adam
• Binary Cross Entropy
• Accuracy

Model performance was approximately 91% accuracy for validation data when 50 epochs were trained.

• Paper: U-Net: Convolutional Networks for Biomedical Image Segmentation
• Code: https://github.com/zhixuhao/unet