A parallel implementation of the forward phase of convolutional neural nets, written in CUDA C.
-
Updated
Dec 25, 2016 - CMake
CUDA® is a parallel computing platform and programming model developed by NVIDIA for general computing on graphical processing units (GPUs). With CUDA, developers are able to dramatically speed up computing applications by harnessing the power of GPUs.
A parallel implementation of the forward phase of convolutional neural nets, written in CUDA C.
Real-time 3D Reconstruction with Semantic Segmentation
Nonequispaced FFTs on GPUs (based on NFFT: http://www.nfft.org)
CUDA projet template (tested on Arch Linux)
TensorFlow examples in C, C++, Go and Python without bazel but with cmake and FindTensorFlow.cmake
CUDA accelerated Path Tracer to render realistic scenes
Collective Knowledge workflow for Caffe to automate installation across diverse platforms and to collaboratively evaluate and optimize Caffe-based workloads across diverse hardware, software and data sets (compilers, libraries, tools, models, inputs):
CUDA based Iterative Closest Point Algorithm Implementation
Created by Nvidia
Released June 23, 2007