Top 1817 Cuda open source projects

Code accompanying my blog post on k-means in Python, C++ and CUDA

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds

Structured Receptive Fields in Convolutional Neural Networks

No description, website, or topics provided.

DukeMTMC-reID_baseline (Matlab)

GPU Implementation of some Connected Component Labeling Algorithms

No description, website, or topics provided.

Replication of Heterogeneous Agent New Keynesian (HANK) model in MATLAB

language models toolkits with hierarchical softmax setting

a forked copy of caffe from Berkeley

No description, website, or topics provided.

No description, website, or topics provided.

Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Implementation of PCN(Point Completion Network) in PyTorch.

The implementation of "Neural Machine Translation without Embeddings"

No description, website, or topics provided.

No description, website, or topics provided.

This repository consists for gpu bootcamp material for HPC and AI

对https://github.com/ruinmessi/RFBNet 代码做中文注释,便于理解

Achieve peak performance on x86 CPUs and NVIDIA GPUs

No description, website, or topics provided.

Code release for "Differential Angular Imaging for Material Recognition", CVPR 2017.

Fast, lightweight, GPU-based, CT Image Reconstruction

Caffe fork with unpool layers, deconvolution layers, locally connected layers, and a custom layer called TweakFeaturesLayer.

simple and lightweight humanpose estimation

caffecn_master

You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery

Official implementation of "SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements", CVPR 2021 https://arxiv.org/abs/2104.07660

No description, website, or topics provided.

APRCP HRNet: Adaptive Pruning Rate Channel Pruning for HRNet Applied to 2D Human Pose Estimation

RWKV v2 is a RNN with transformer performance. It can be directly trained like a GPT transformer (parallelizable). You only need x_t, a_t, b_t of position t to compute the vectors for position t+1. Hence it can be 100x faster than GPT, and 100x more VRAM friendly, and you get a free sentence embedding.

No description, website, or topics provided.

Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

No description, website, or topics provided.

HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate (CTR) estimating training

An ultra-fast, GPU-based large graph embedding algorithm utilizing a novel coarsening algorithm requiring not more than a single GPU.

2018搜狐内容识别算法大赛-解决方案（4th）

Repository of paper "Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks"

这是一个基于NVIDIA cuda的开源程序，其中包括了二维和三维VTI介质正演模拟和逆时偏移成像，二维TTI介质逆时偏移成像，以及以上介质的ADCIGs提取[translation: This is an open source program based on NVIDIA cuda, which includes two-dimensional and three-dimensional VTI media forward simulation and reverse time migration imaging, two-dimensional TTI media reverse time migration imaging, and ADCIGs extraction of …

NTU-X, which is an extended version of popular NTU dataset

Extended-precision modular arithmetic library that targets CUDA.

Fast parallel RNN-Transducer.

ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics

Source code for "Interactive All-Hex Meshing via Cuboid Decomposition [SIGGRAPH Asia 2021]".

SimDeblur is a simple framework for image and video deblurring, implemented by PyTorch

Min-Entropy Latent Model for Weakly Supervised Object Detection

No description, website, or topics provided.

computer vision Toolkit of pytorch

GPU ray tracing framework.

PlenOctree Volume Rendering (supports CUDA & fragment shader backends)