基于TensorRT7实现DCNv2插件

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

ONNX-TensorRT: TensorRT backend for ONNX

Open standard for machine learning interoperability

Implementation of popular deep learning networks with TensorRT network definition API

TensorRT 7 C++ (almost) minimal examples

convert mmdetection model to tensorrt, support fp16, int8, batch input, dynamic shape etc.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

TensorRT deployment for CenterPoint Lidar Detection Model.

OpenMMLab Model Deployment Framework

A simple and quick example shows how to convert the model of Pytoch to ONNX, and then deploy it with tensorrt in C++

A 3D detection Pointpillars ROS deployment on Nvidia Jetson TX1/Xavier

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

mlpack: a fast, header-only C++ machine learning library

A logic synthesis tool

CenterPoint model trained with MMDetection3d on custom dataset, and deployed with TensorRT

Useful CMake Examples

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…