Implementation of the Chamfer Distance as a module for pyTorch

Last update: Jan 05, 2023

Overview

Chamfer Distance for pyTorch

This is an implementation of the Chamfer Distance as a module for pyTorch. It is written as a custom C++/CUDA extension.

As it is using pyTorch's JIT compilation, there are no additional prerequisite steps that have to be taken. Simply import the module as shown below; CUDA and C++ code will be compiled on the first run.

Usage

from chamfer_distance import ChamferDistance
chamfer_dist = ChamferDistance()

#...
# points and points_reconstructed are n_points x 3 matrices

dist1, dist2 = chamfer_dist(points, points_reconstructed)
loss = (torch.mean(dist1)) + (torch.mean(dist2))


#...

Integration

This code has been integrated into the Kaolin library for 3D Deep Learning by NVIDIAGameWorks. You should probably take a look at it if you are working on anything 3D :)

Owner

Christian Diller

PhD Student at the 3D AI Lab @ TU Munich

GitHub Repository

Model Agnostic Interpretability for Multiple Instance Learning

MIL Model Agnostic Interpretability This repo contains the code for "Model Agnostic Interpretability for Multiple Instance Learning". Overview Executa

10 Dec 17, 2022

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

Deep GNN, Shallow Sampling Hanqing Zeng, Muhan Zhang, Yinglong Xia, Ajitesh Srivastava, Andrey Malevich, Rajgopal Kannan, Viktor Prasanna, Long Jin, R

117 Dec 20, 2022

Implementation of the Chamfer Distance as a module for pyTorch

Related tags

Overview

Chamfer Distance for pyTorch

Usage

Integration

Owner

Christian Diller

Model Agnostic Interpretability for Multiple Instance Learning

We have implemented shaDow-GNN as a general and powerful pipeline for graph representation learning. For more details, please find our paper titled Deep Graph Neural Networks with Shallow Subgraph Samplers, available on arXiv (https//arxiv.org/abs/2012.01380).

PyTorch code for 'Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning'

Official Implementation of "Transformers Can Do Bayesian Inference"

Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration

A Joint Video and Image Encoder for End-to-End Retrieval

A Kernel fuzzer focusing on race bugs

A Self-Supervised Contrastive Learning Framework for Aspect Detection

The code uses SegFormer for Semantic Segmentation on Drone Dataset.

object recognition with machine learning on Respberry pi

PPO Lagrangian in JAX

Deep Anomaly Detection with Outlier Exposure (ICLR 2019)

Near-Optimal Sparse Allreduce for Distributed Deep Learning (published in PPoPP'22)

From the basics to slightly more interesting applications of Tensorflow

Reinforcement learning models in ViZDoom environment

Framework that uses artificial intelligence applied to mathematical models to make predictions

Source-to-Source Debuggable Derivatives in Pure Python

a general-purpose Transformer based vision backbone

Implementation of Bottleneck Transformer in Pytorch