Skip to content

An unofficial PyTorch implementation of Neural Causation Coefficient (NCC)

License

Notifications You must be signed in to change notification settings

euphoria0-0/Neural-Causation-Coefficient

Repository files navigation

Neural Causation Coefficient

An unofficial PyTorch implementation of Neural Causation Coefficient (NCC) in the paper, "Discovering Causal Signals in Images".

Requirements

torch=1.9.0
torchvision=1.10.0
scikit-learn
scipy
tqdm
numpy
pandas
matplotlib
seaborn
skimage
pycocotools

Usage

  1. Download datasets: 1) Tubingen dataset, 2) PASCAL VOC2012 dataset, and 3) MSCOCO dataset.

  2. NCC_Training.ipynb: Train NCC Classifier on synthetic dataset and Test it on Tubingen dataset

    • Our reproduced model results/NCC_classifier_best.pt showed 78.74% accuracy on Tubingen dataset, which was 79% in the original paper.
  3. ObjectClassifier_Training.ipynb: Train object classifier on PASCAL VOC2012 dataset

  4. NCC_Testing.ipynb: Test NCC Classifier on MSCOCO dataset

References

David Lopez-Pas et al., Discovering Causal Signals in Images, ICML 2017

About

An unofficial PyTorch implementation of Neural Causation Coefficient (NCC)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published