#8383rd of 88 in Learning and cookbooks
unet
Keras U-Net for binary image segmentation on the ISBI membrane dataset
- Stars
- 4.9k
- License
- MIT
- Last commit
- Mar 2026
- Language
- Jupyter Notebook
4,892 on 20 Apr 20264,940 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Keras functional-API implementation of the U-Net architecture for biomedical image segmentation. It includes the ISBI challenge membrane data (30 images, 512x512), augmentation via Keras ImageDataGenerator, and a main.py script and notebook that train for 5 epochs and write predicted masks. The README reports about 0.97 accuracy with binary crossentropy loss.
Who it is for: Students learning image segmentation with Keras
Strengths
- Small, readable reference U-Net in the Keras functional API
- Ships the preprocessed ISBI membrane dataset in data/membrane
- Includes augmentation code and a training notebook (trainUnet)
- Runs end to end from a single main.py
Weaknesses
- README targets Python 2.7-3.5 and Keras >= 1.0, which are outdated
- Trained on only 30 images for a single binary segmentation task
- Reports accuracy only, with no IoU or Dice metrics
- No pretrained weights or tagged releases
What it needs
- GPU optional
- Needs TensorFlow, Keras
- Models: U-Net, Keras
Quick answers
Is unet open source?
Yes. Its code is on GitHub under the MIT license.
Does unet need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Learning and cookbooks
See all 88| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 91 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 81 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 81 out of 100 |
| #5 | ai-for-beginners24-lesson AI curriculum with notebooks in PyTorch and TensorFlow | 80 out of 100 |