Skip to content
This repository has been archived by the owner on Jun 1, 2024. It is now read-only.
/ voxelcnn Public archive

VoxelCNN: Order-Aware Generative Modeling Using the 3D-Craft Dataset

License

Notifications You must be signed in to change notification settings

facebookresearch/voxelcnn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

VoxelCNN

VoxelCNN is an order-aware generative model for building houses in Minecraft. This codebase is a PyTorch implementation of the training and evaluation pipeline for VoxelCNN. VoxelCNN

VoxelCNN is trained and evaluated with the 3D-Craft dataset. 3D-Craft Dataset

For more details, please refer to the ICCV 19' paper Order-Aware Generative Modeling Using the 3D-Craft Dataset.

Installation

Python version >= 3.7 is required.

0. Clone the repo

git clone https://github.com/facebookresearch/VoxelCNN
cd VoxelCNN

1. (Optional) Create a virtual environment

pip install virtualenv
virtualenv voxelcnn_venv
source voxelcnn_venv/bin/activate

2. Install PyTorch

Please follow the official installation guide to install PyTorch version >= 1.3.

3. Install other dependencies

pip install numpy requests tqdm

4. (Optional) Verify installation by running unit tests

python -m unittest discover -s test -v

Training and Evaluation

The 3D-Craft dataset will be downloaded automatically when launching the training for the first time.

Run the fast training (fewer epochs, slightly worse results):

python main.py --num_epochs 3 --step_size 1 --save_dir /path/to/save/log/and/checkpoints

Example final test results for the fast training:

acc@1: 0.622  acc@5: 0.760  acc@10: 0.788
cca_10%: 13.374  cca_25%: 11.115  cca_50%: 12.546  cca_75%: 12.564  cca_90%: 7.632  cca_avg: 11.446
mtc: 131.411  mtc_normed: 0.241

Run the full training:

python main.py --save_dir /path/to/save/log/and/checkpoints

Example final test results for the full training:

acc@1: 0.640  acc@5: 0.778  acc@10: 0.806
cca_10%: 13.630  cca_25%: 12.223  cca_50%: 13.168  cca_75%: 13.047  cca_90%: 7.571  cca_avg: 11.928
mtc: 121.753  mtc_normed: 0.223

License

VoxelCNN is released under the CC-BY-NC 4.0 license.

Citing

@inproceedings{zchen2019,
  title = {Order-Aware Generative Modeling Using the 3D-Craft Dataset},
  author = {Chen, Zhuoyuan and Guo, Demi and Xiao, Tong and Xie, Saining and Chen, Xinlei and Yu, Haonan and Gray, Jonathan and Srinet, Kavya and Fan, Haoqi and Ma, Jerry and Qi, Charles R and Tulsiani, Shubham and Szlam, Arthur and Zitnick, C. Lawrence},
  booktitle = {ICCV},
  year = {2019},
}

About

VoxelCNN: Order-Aware Generative Modeling Using the 3D-Craft Dataset

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages