https://github.com/billbillbilly/cityscapegh

https://github.com/billbillbilly/cityscapegh

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: billbillbilly
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 318 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License

README.md

cityscapeGH

Introduction

cityscapeGH aims to integtate generative models in Grasshopper (GH) workflow to create the reimagination of urban landscape based on 3D reconstructions in Rhino3D space.

Prerequisites

  • Linux or macOS
  • Python 3
  • CPU or NVIDIA GPU (11G memory or larger) + CUDA cuDNN

Getting Started

Installation

  • Create a virtual envi with conda (recommended)
  • Install PyTorch from http://pytorch.org
  • Install Rhino6 or later
  • Clone this repo: bash git clone https://github.com/billbillbilly/cityscapeGH cd cityscapeGH
  • Download the checkpoint in ./cityscapeGH/src/pix2pix_model/checkpoints/pix2pix from here

Setup in Grasshopper

  • set work directory (it shuold be this repo)
  • set python path (it may be the conda envi). To find the path of python: bash # which python{version} which python3.10

Note

Current project only applies basic pix2pix model trained on cityscapes dataset. More models such stable diffusion will be available in the near future.

Reference

``` @inproceedings{isola2017image, title={Image-to-Image Translation with Conditional Adversarial Networks}, author={Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A}, booktitle={Computer Vision and Pattern Recognition (CVPR), 2017 IEEE Conference on}, year={2017} }

@inproceedings{Cordts2016Cityscapes, title={The Cityscapes Dataset for Semantic Urban Scene Understanding}, author={Cordts, Marius and Omran, Mohamed and Ramos, Sebastian and Rehfeld, Timo and Enzweiler, Markus and Benenson, Rodrigo and Franke, Uwe and Roth, Stefan and Schiele, Bernt}, booktitle={Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2016} } ```

Acknowledgments

This project is heavily based on pytorch-CycleGAN-and-pix2pix.

Owner

  • Name: Xiaohao Yang
  • Login: billbillbilly
  • Kind: user
  • Location: Ann Arbor, MI

Graduate researcher assistant @land-info-lab at the School for Environment and Sustainability, University of Michigan

GitHub Events

Total
Last Year