PyTorch implementation of UNet++ (Nested U-Net).

Last update: Jan 04, 2023

Overview

PyTorch implementation of UNet++ (Nested U-Net)

This repository contains code for a image segmentation model based on UNet++: A Nested U-Net Architecture for Medical Image Segmentation implemented in PyTorch.

[NEW] Add support for multi-class segmentation dataset.

[NEW] Add support for PyTorch 1.x.

Requirements

PyTorch 1.x or 0.41

Installation

Create an anaconda environment.

conda create -n=<env_name> python=3.6 anaconda
conda activate <env_name>

Install PyTorch.

conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

Install pip packages.

pip install -r requirements.txt

Training on 2018 Data Science Bowl dataset

Download dataset from here to inputs/ and unzip. The file structure is the following:

inputs
└── data-science-bowl-2018
    ├── stage1_train
    |   ├── 00ae65...
    │   │   ├── images
    │   │   │   └── 00ae65...
    │   │   └── masks
    │   │       └── 00ae65...            
    │   ├── ...
    |
    ...

Preprocess.

python preprocess_dsb2018.py

Train the model.

python train.py --dataset dsb2018_96 --arch NestedUNet

Evaluate.

python val.py --name dsb2018_96_NestedUNet_woDS

(Optional) Using LovaszHingeLoss

Clone LovaszSoftmax from bermanmaxim/LovaszSoftmax.

git clone https://github.com/bermanmaxim/LovaszSoftmax.git

Train the model with LovaszHingeLoss.

python train.py --dataset dsb2018_96 --arch NestedUNet --loss LovaszHingeLoss

Training on original dataset

Make sure to put the files as the following structure (e.g. the number of classes is 2):

inputs
└── <dataset name>
    ├── images
    |   ├── 0a7e06.jpg
    │   ├── 0aab0a.jpg
    │   ├── 0b1761.jpg
    │   ├── ...
    |
    └── masks
        ├── 0
        |   ├── 0a7e06.png
        |   ├── 0aab0a.png
        |   ├── 0b1761.png
        |   ├── ...
        |
        └── 1
            ├── 0a7e06.png
            ├── 0aab0a.png
            ├── 0b1761.png
            ├── ...

Train the model.

python train.py --dataset <dataset name> --arch NestedUNet --img_ext .jpg --mask_ext .png

Evaluate.

python val.py --name <dataset name>_NestedUNet_woDS

Results

DSB2018 (96x96)

Here is the results on DSB2018 dataset (96x96) with LovaszHingeLoss.

Model	IoU	Loss
U-Net	0.839	0.365
Nested U-Net	0.842	0.354
Nested U-Net w/ Deepsupervision	0.843	0.362

PyTorch implementation of UNet++ (Nested U-Net).

Related tags

Overview

PyTorch implementation of UNet++ (Nested U-Net)

Requirements

Installation

Training on 2018 Data Science Bowl dataset

(Optional) Using LovaszHingeLoss

Training on original dataset

Results

DSB2018 (96x96)

Owner

4ui_iurz1

CrossNorm and SelfNorm for Generalization under Distribution Shifts (ICCV 2021)

Solution of Kaggle competition: Sartorius - Cell Instance Segmentation

A Graph Neural Network Tool for Recovering Dense Sub-graphs in Random Dense Graphs.

Implement of homography net by pytorch

A package for music online and offline rhythmic information analysis including music Beat, downbeat, tempo and meter tracking.

JAX-based neural network library

Official implementation of CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification

Locally Enhanced Self-Attention: Rethinking Self-Attention as Local and Context Terms

BigbrotherBENL - Face recognition on the Big Brother episodes in Belgium and the Netherlands.

A collection of semantic image segmentation models implemented in TensorFlow

Kaggle Ultrasound Nerve Segmentation competition [Keras]

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

Transfer-Learn is an open-source and well-documented library for Transfer Learning.

Learning from Synthetic Humans, CVPR 2017

Python wrapper class for OpenVINO Model Server. User can submit inference request to OVMS with just a few lines of code

A small library for doing fluid simulation with neural networks.

ByteTrack(Multi-Object Tracking by Associating Every Detection Box)のPythonでのONNX推論サンプル

A parallel framework for population-based multi-agent reinforcement learning.

A model to classify a piece of news as REAL or FAKE

Implementation of average- and worst-case robust flatness measures for adversarial training.