yingkaisha/keras-unet-collection
Keras and TensorFlow implementations of U-net and related encoder-decoder architectures for image segmentation.
Not currently ranked — collecting fresh signals.
star history
This repository provides TensorFlow/Keras implementations of classic and modern segmentation architectures including U-net, V-net, U-net++, UNET 3+, Attention U-net, R2U-Net, ResUnet-a, U^2-Net, TransUNET, and Swin-UNET. These are encoder-decoder convolutional neural networks primarily used for semantic segmentation tasks in images. The library supports optional ImageNet-pretrained backbones and deep supervision mechanisms for several models.
Frequently asked
- What is yingkaisha/keras-unet-collection?
- Keras and TensorFlow implementations of U-net and related encoder-decoder architectures for image segmentation.
- Is keras-unet-collection open source?
- Yes — yingkaisha/keras-unet-collection is open source, released under the MIT license.
- What language is keras-unet-collection written in?
- yingkaisha/keras-unet-collection is primarily written in Python.
- How popular is keras-unet-collection?
- yingkaisha/keras-unet-collection has 762 stars on GitHub.
- Where can I find keras-unet-collection?
- yingkaisha/keras-unet-collection is on GitHub at https://github.com/yingkaisha/keras-unet-collection.