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
Repository
Basic Info
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
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/pix2pixfrom 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
- Website: https://www.xiaohaoy.com/
- Repositories: 3
- Profile: https://github.com/billbillbilly
Graduate researcher assistant @land-info-lab at the School for Environment and Sustainability, University of Michigan