PointPillars inference with TensorRT

Overview

PointPillars inference with TensorRT

This repository contains sources and model for pointpillars inference using TensorRT. The model is created by OpenPCDet and modified by onnx_graphsurgeon.

Inference has four parts: generateVoxels: convert points cloud into voxels which has 4 channles generateFeatures: convert voxels into feature maps which has 10 channles Inference: convert feature maps to raw data of bounding box, class source and direction Postprocessing: parse bounding box, class source and direction

Data

The demo use the data from KITTI Dataset and more data can be downloaded following the linker GETTING_STARTED

Model

The onnx file can be converted from a model trainned by OpenPCDet with the tool in the demo.

Build

Prerequisites

To build the pointpillars inference, TensorRT with PillarScatter layer and CUDA are needed. PillarScatter layer plugin is already implemented as a plugin for TRT in the demo.

  • Jetpack 4.5
  • TensorRT v7.1.3
  • CUDA-10.2 + cuDNN-8.0.0
  • PCL is optinal to store pcd pointcloud file

Compile


$ cd test
$ mkdir build
$ cd build
$ make -j$(nproc)

Run

$ ./demo

Enviroments

  • Jetpack 4.5
  • Cuda10.2 + cuDNN8.0.0 + TensorRT 7.1.3
  • Nvidia Jetson AGX Xavier

Performance

  • FP16
|                   | GPU/ms | 
| ----------------- | ------ |
| generateVoxels    | 0.22   |
| generateFeatures  | 0.21   |
| Inference         | 30.75  |
| Postprocessing    | 3.19   |

Note

  1. GPU processes all points at the same time and points selected form points cloud for a voxel randomly, so the output of generateVoxels has random value. Because CPU will select the first 32 points, the output of generateVoxels by CPU has fixed value.

  2. The demo will cache the onnx file to improve performance. If a new onnx will be used, please remove the cache file in "./model"

  3. MAX_VOXELS in params.h is used to allocate cache during inference. Decrease the value to save memory.

References

Owner
NVIDIA AI IOT
NVIDIA AI IOT
Data-depth-inference - Data depth inference with python

Welcome! This readme will guide you through the use of the code in this reposito

Marco 3 Feb 08, 2022
A geometric deep learning pipeline for predicting protein interface contacts.

A geometric deep learning pipeline for predicting protein interface contacts.

44 Dec 30, 2022
This repository contains code released by Google Research.

This repository contains code released by Google Research.

Google Research 26.6k Dec 31, 2022
From the basics to slightly more interesting applications of Tensorflow

TensorFlow Tutorials You can find python source code under the python directory, and associated notebooks under notebooks. Source code Description 1 b

Parag K Mital 5.6k Jan 09, 2023
Experiments and examples converting Transformers to ONNX

Experiments and examples converting Transformers to ONNX This repository containes experiments and examples on converting different Transformers to ON

Philipp Schmid 4 Dec 24, 2022
An Open Source Machine Learning Framework for Everyone

Documentation TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries, a

170.1k Jan 05, 2023
CenterNet:Objects as Points目标检测模型在Pytorch当中的实现

CenterNet:Objects as Points目标检测模型在Pytorch当中的实现

Bubbliiiing 267 Dec 29, 2022
Edge Restoration Quality Assessment

ERQA - Edge Restoration Quality Assessment ERQA - a full-reference quality metric designed to analyze how good image and video restoration methods (SR

MSU Video Group 27 Dec 17, 2022
Computational modelling of ray propagation through optical elements using the principles of geometric optics (Ray Tracer)

Computational modelling of ray propagation through optical elements using the principles of geometric optics (Ray Tracer) Introduction By applying the

Son Gyo Jung 1 Jul 09, 2022
The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".

Codebase for learning control flow in transformers The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformer

Csordás Róbert 24 Oct 15, 2022
Conformer: Local Features Coupling Global Representations for Visual Recognition

Conformer: Local Features Coupling Global Representations for Visual Recognition (arxiv) This repository is built upon DeiT and timm Usage First, inst

Zhiliang Peng 378 Jan 08, 2023
Lighting the Darkness in the Deep Learning Era: A Survey, An Online Platform, A New Dataset

Lighting the Darkness in the Deep Learning Era: A Survey, An Online Platform, A New Dataset This repository provides a unified online platform, LoLi-P

Chongyi Li 457 Jan 03, 2023
Performance Analysis of Multi-user NOMA Wireless-Powered mMTC Networks: A Stochastic Geometry Approach

Performance Analysis of Multi-user NOMA Wireless-Powered mMTC Networks: A Stochastic Geometry Approach Thanh Luan Nguyen, Tri Nhu Do, Georges Kaddoum

Thanh Luan Nguyen 2 Oct 10, 2022
Official repository for ABC-GAN

ABC-GAN The work represented in this repository is the result of a 14 week semesterthesis on photo-realistic image generation using generative adversa

IgorSusmelj 10 Jun 23, 2022
PyTorch implementation of SmoothGrad: removing noise by adding noise.

SmoothGrad implementation in PyTorch PyTorch implementation of SmoothGrad: removing noise by adding noise. Vanilla Gradients SmoothGrad Guided backpro

SSKH 143 Jan 05, 2023
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

Yonglong Tian 2.2k Jan 08, 2023
Meta Language-Specific Layers in Multilingual Language Models

Meta Language-Specific Layers in Multilingual Language Models This repo contains the source codes for our paper On Negative Interference in Multilingu

Zirui Wang 20 Feb 13, 2022
Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021.

Code of the paper "Deep Human Dynamics Prior" in ACM MM 2021. Figure 1: In the process of motion capture (mocap), some joints or even the whole human

Shinny cui 3 Oct 31, 2022
source code for 'Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge' by A. Shah, K. Shanmugam, K. Ahuja

Source code for "Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge" Reference: Abhin Shah, Karthikeyan Shanmugam, Kartik Ahu

Abhin Shah 1 Jun 03, 2022
Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.

Unsupervised Contrastive Learning of Sound Event Representations This repository contains the code for the following paper. If you use this code or pa

Eduardo Fonseca 81 Dec 22, 2022