All Projects → LitLeo → Tensorrt_tutorial

LitLeo / Tensorrt_tutorial

Labels

Projects that are alternatives of or similar to Tensorrt tutorial

Libsgm
Stereo Semi Global Matching by cuda
Stars: ✭ 368 (-9.58%)
Mutual labels:  cuda
Cudf
cuDF - GPU DataFrame Library
Stars: ✭ 4,370 (+973.71%)
Mutual labels:  cuda
Cubert
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
Stars: ✭ 395 (-2.95%)
Mutual labels:  cuda
Vuda
VUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.
Stars: ✭ 373 (-8.35%)
Mutual labels:  cuda
Hipsycl
Implementation of SYCL for CPUs, AMD GPUs, NVIDIA GPUs
Stars: ✭ 377 (-7.37%)
Mutual labels:  cuda
Neuralnetwork.net
A TensorFlow-inspired neural network library built from scratch in C# 7.3 for .NET Standard 2.0, with GPU support through cuDNN
Stars: ✭ 392 (-3.69%)
Mutual labels:  cuda
Loopy
A code generator for array-based code on CPUs and GPUs
Stars: ✭ 367 (-9.83%)
Mutual labels:  cuda
Warp Ctc
Fast parallel CTC.
Stars: ✭ 3,954 (+871.5%)
Mutual labels:  cuda
Music Translation
A UNIVERSAL MUSIC TRANSLATION NETWORK - a method for translating music across musical instruments and styles.
Stars: ✭ 385 (-5.41%)
Mutual labels:  cuda
Integral Human Pose
Integral Human Pose Regression
Stars: ✭ 395 (-2.95%)
Mutual labels:  cuda
Nvpipe
NVIDIA-accelerated zero latency video compression library for interactive remoting applications
Stars: ✭ 376 (-7.62%)
Mutual labels:  cuda
Ilgpu
ILGPU JIT Compiler for high-performance .Net GPU programs
Stars: ✭ 374 (-8.11%)
Mutual labels:  cuda
Ganet
GA-Net: Guided Aggregation Net for End-to-end Stereo Matching
Stars: ✭ 393 (-3.44%)
Mutual labels:  cuda
Mini Caffe
Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.
Stars: ✭ 373 (-8.35%)
Mutual labels:  cuda
Pytorch Pwc
a reimplementation of PWC-Net in PyTorch that matches the official Caffe version
Stars: ✭ 402 (-1.23%)
Mutual labels:  cuda
Darkpose
Distribution-Aware Coordinate Representation for Human Pose Estimation
Stars: ✭ 369 (-9.34%)
Mutual labels:  cuda
Amgcl
C++ library for solving large sparse linear systems with algebraic multigrid method
Stars: ✭ 390 (-4.18%)
Mutual labels:  cuda
Ai Lab
All-in-one AI container for rapid prototyping
Stars: ✭ 406 (-0.25%)
Mutual labels:  cuda
Gocv
Go package for computer vision using OpenCV 4 and beyond.
Stars: ✭ 4,511 (+1008.35%)
Mutual labels:  cuda
Cudanative.jl
Julia support for native CUDA programming
Stars: ✭ 393 (-3.44%)
Mutual labels:  cuda

建议看最新视频版本!列表如下

进度记录

  • 2017-04-27 项目发起,创建GitHub仓库。
  • 2017-09-30 TensorRT 3最近发布,整理一下目前的资源。
  • 2017-10-18 增加博客-使用TensorRT实现leaky relu层
  • 2017-11-11 资源:新增google的INT8开源库
  • 2017-11-25 增加博客-TensorRT Plugin使用方式简介-以leaky relu层为例
  • 2020-8-31 增加博客《TensorRT Github 开源部分介绍》
  • 2020-9-7 增加博客《TensorRT 可借鉴代码汇总》

资源整理


博客

TensorRT_Tutorial

TensorRT作为NVIDIA推出的c++库,能够实现高性能推理(inference)过程。最近,NVIDIA发布了TensorRT 2.0 Early Access版本,重大更改就是支持INT8类型。在当今DL大行其道的时代,INT8在缩小模型大小、加速运行速度方面具有非常大的优势。Google新发布的TPU就采用了8-bit的数据类型。

本人目前在使用TensorRT进行INT8的探究。已经被TensorRT不完善的文档坑了一次了。所以想自力更生做一个TensorRT Tutorial,主要包括三部分:

  • TensorRT User Guide 翻译;
  • TensorRT samples 介绍分析讲解;
  • TensorRT 使用经验。

感谢每一位为该翻译项目做出贡献的同学.

内容来源: TensorRT 下载页面: https://developer.nvidia.com/nvidia-tensorrt-20-download

TensorRT 文档、Samples 安装后对应目录中

参与者(按参与时间排序)

TensorRT User Guide 翻译

翻译校对

  • 赵开勇

TensorRT samples 介绍分析讲解

TensorRT 使用经验。

欲参与者请加QQ群:483063470

支持捐赠项目

招实习生

【实习】【腾讯北京AILAB】招募AI异构加速实习生
简历直接给负责人,给简历保证迅速反馈。
基本条件: 熟悉c++,至少实习6个月
工作内容:

  1. 使用c++复现框架训练的模型并进行CPU、GPU、ARM加速,达到上线的性能要求。
  2. 调研各种inference框架并投入生产 加分项:
  3. 写过或者维护过深度学习框架代码;
  4. 会CUDA 开发,能自己写kernel,会用cublas,cudnn等库;
  5. linux cpu c++编程能力,会写avx、会用mkl;
  6. 熟悉深度学习计算过程
  7. 学习能力强,实习时间长 联系方式: [email protected]
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].