Implementation of U-Net and SegNet for building segmentation

Last update: Dec 07, 2022

Overview

Specialized project

Created by Katrine Nguyen and Martin Wangen-Eriksen as a part of our specialized project at Norwegian University of Science and Technology (NTNU).

Models

Most of our code and the U-net model is significantly inspired by this project Unet-for-Person-Segmentation. The SegNet model we created on our own based on other implementations of SegNet in Tensorflow.

Data

The model is trained and tested on Massachusetts Buildings Dataset from Kaggle. The original images where 1500X1500 pixels each over an area of 1500x1500 meters (1mx1m resolution). The original 137 images were cropped into 64x64 pixels and images without building were filtered out.

To make the masks compatible with our model the masks was changed from white (255,255,255) labels to greyscale with value 1. This is done in image_fix.py found in the repo.

Folder structure

Images and masks are saved in local directories and used in data.py and test.py. This is of course possible to change, however if you want to use the exact same code you can follow this folder structure.


.
├── ...
├── building-segmentation                # Directory for all images
│   ├── Images                           # Directory for raw images
│   │   ├── cropped_images_train_64      # Directory for cropped images where number specifies resolution, containg .jpg
│   │   ├── cropped_images_train_128     # Directory for cropped images where number specifies resolution, containg .jpg 
│   │   └── ...                          # More directories with other resolutions
│   ├── Masks                            # Directory for all maskes
│   │   ├── cropped_masks_train_64       # Directory for cropped masks where number specifies resolution, containg .jpg
│   │   ├── cropped_masks_train_128      # Directory for cropped masks where number specifies resolution, containg .jpg 
│   │   └── ...                          # More directories with other resolutions
│   └── Test                             # Miscellaneous information
│       ├── test_64                      # Directory for images where number specifies resolution, containing .jpg
│       └── ...                          # More directories with other resolutions
└── ...

# data.py
    images = glob(os.path.join(dataset_path, "images/cropped_images_train_64/*"))
    masks = glob(os.path.join(dataset_path, "masks/cropped_masks_train_64/*"))
    
    # In main:
        dataset_path = "building-segmentation"
    
# test.py
    test_images = glob("building-segmentation/test/test_64/*")

Implementation of U-Net and SegNet for building segmentation

Related tags

Overview

Specialized project

Models

Data

Folder structure

Running the project

Requirements

Training

Testing

Owner

Martin.w-e

Alternatives to Deep Neural Networks for Function Approximations in Finance

Official git for "CTAB-GAN: Effective Table Data Synthesizing"

A wrapper around SageMaker ML Lineage Tracking extending ML Lineage to end-to-end ML lifecycles, including additional capabilities around Feature Store groups, queries, and other relevant artifacts.

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".

Benchmark tools for Compressive LiDAR-to-map registration

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

This project hosts the code for implementing the ISAL algorithm for object detection and image classification

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

Cross View SLAM

Python version of the amazing Reaction Mechanism Generator (RMG).

Rotary Transformer

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

Reinforcement Learning Theory Book (rus)

Some code of the implements of Geological Modeling Using 3D Pixel-Adaptive and Deformable Convolutional Neural Network

This code uses generative adversarial networks to generate diverse task allocation plans for Multi-agent teams.

Vit-ImageClassification - Pytorch ViT for Image classification on the CIFAR10 dataset

PyTorch implementation of the paper:A Convolutional Approach to Melody Line Identification in Symbolic Scores.

Efficient Householder transformation in PyTorch

An official implementation of the paper Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers

[内测中]前向式Python环境快捷封装工具，快速将Python打包为EXE并添加CUDA、NoAVX等支持。