ethanhe42/u-net
A Keras implementation of the U-Net convolutional neural network for biomedical image segmentation tasks like ultrasound nerve detection.
Not currently ranked — collecting fresh signals.
star history
This repository provides a tutorial implementation of the U-Net architecture for the Kaggle Ultrasound Nerve Segmentation competition. The model is a convolutional auto-encoder with skip connections between encoder and decoder layers at corresponding levels, implemented using Keras with TensorFlow backend. It processes ultrasound images resized to 64x80 pixels and outputs segmentation masks scaled between 0 and 1.
Frequently asked
- What is ethanhe42/u-net?
- A Keras implementation of the U-Net convolutional neural network for biomedical image segmentation tasks like ultrasound nerve detection.
- Is u-net open source?
- Yes — ethanhe42/u-net is open source, released under the MIT license.
- What language is u-net written in?
- ethanhe42/u-net is primarily written in Python.
- How popular is u-net?
- ethanhe42/u-net has 451 stars on GitHub.
- Where can I find u-net?
- ethanhe42/u-net is on GitHub at https://github.com/ethanhe42/u-net.