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

Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment"

aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

quantize aware training package for NCNN on pytorch

Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

Official implementation of deep-multi-trajectory-based single object tracking (IEEE T-CSVT 2021).

Compositional and Parameter-Efficient Representations for Large Knowledge Graphs

NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go

A dead simple python wrapper for darknet that works with OpenCV 4.1, CUDA 10.1

A PyTorch implementation of the continual learning experiments with deep neural networks

CVPR 2022 "Online Convolutional Re-parameterization"

The repository for freeCodeCamp's YouTube course, Algorithmic Trading in Python

Streamlit app demonstrating an image browser for the Udacity self-driving-car dataset with realtime object detection using YOLO.

Garbage Detection system which will detect objects based on whether it is plastic waste or plastics or just garbage.

Implementation for the EMNLP 2021 paper "Interactive Machine Comprehension with Dynamic Knowledge Graphs".

Probabilistic Tensor Decomposition of Neural Population Spiking Activity

Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models.

Automates Machine Learning Pipeline with Feature Engineering and Hyper-Parameters Tuning :rocket:

Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).

Baseline and template code for node21 detection track

Codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing