Adversarial-point-perturbations-on-3D-objects icon indicating copy to clipboard operation
Adversarial-point-perturbations-on-3D-objects copied to clipboard

New distributional and shape attacks on neural networks that process 3D point cloud data.

Results 5 Adversarial-point-perturbations-on-3D-objects issues
Sort by recently updated
recently updated
newest added

Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.4.1 to 2.12.0. Release notes Sourced from tensorflow-gpu's releases. TensorFlow 2.12.0 Release 2.12.0 TensorFlow Breaking Changes Build, Compilation and Packaging Removed redundant packages tensorflow-gpu and tf-nightly-gpu. These...

dependencies

Bumps [numpy](https://github.com/numpy/numpy) from 1.16.6 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependencies

Hi, thank you for your good work! I’m wondering if these attacters work on semantic segmentation task as well as on the classification. Have you explored the possibilities for applying...

I have adjusted some of the scripts to make them modular, so they can be imported and used inside other scripts or executed within _Jupyter notebook_ for further development. Take...

Hi, Every time I try to construct PerturbProjTree, it turns out ![image](https://user-images.githubusercontent.com/22851860/65039205-464ef180-d984-11e9-96d7-8d21f853f15a.png) I am using TensorFlow 1.14 and Python 2.7 as you suggested. How does this error happen?