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
Source code for CVPR 2020 paper "Learning to Forget for Meta-Learning"

L2F - Learning to Forget for Meta-Learning Sungyong Baik, Seokil Hong, Kyoung Mu Lee Source code for CVPR 2020 paper "Learning to Forget for Meta-Lear

Sungyong Baik 29 May 22, 2022
Simple and Distributed Machine Learning

Synapse Machine Learning SynapseML (previously MMLSpark) is an open source library to simplify the creation of scalable machine learning pipelines. Sy

Microsoft 3.9k Dec 30, 2022
A collection of SOTA Image Classification Models in PyTorch

A collection of SOTA Image Classification Models in PyTorch

sithu3 85 Dec 30, 2022
CoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery

CoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery This paper (CoANet) has been published in IEEE TIP 2021. This code i

Jie Mei 53 Dec 03, 2022
Node-level Graph Regression with Deep Gaussian Process Models

Node-level Graph Regression with Deep Gaussian Process Models Prerequests our implementation is mainly based on tensorflow 1.x and gpflow 1.x: python

1 Jan 16, 2022
A python package for generating, analyzing and visualizing building shadows

pybdshadow Introduction pybdshadow is a python package for generating, analyzing and visualizing building shadows from large scale building geographic

Qing Yu 13 Nov 30, 2022
Open Source Light Field Toolbox for Super-Resolution

BasicLFSR BasicLFSR is an open-source and easy-to-use Light Field (LF) image Super-Ressolution (SR) toolbox based on PyTorch, including a collection o

Squidward 50 Nov 18, 2022
Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation".

PixelTransformer Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation". Project Page Installation Please insta

Shubham Tulsiani 24 Dec 17, 2022
Research into Forex price prediction from price history using Deep Sequence Modeling with Stacked LSTMs.

Forex Data Prediction via Recurrent Neural Network Deep Sequence Modeling Research Paper Our research paper can be viewed here Installation Clone the

Alex Taradachuk 2 Aug 07, 2022
(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"

Res2Net The official pytorch implemention of the paper "Res2Net: A New Multi-scale Backbone Architecture" Our paper is accepted by IEEE Transactions o

Res2Net Applications 928 Dec 29, 2022
Representing Long-Range Context for Graph Neural Networks with Global Attention

Graph Augmentation Graph augmentation/self-supervision/etc. Algorithms gcn gcn+virtual node gin gin+virtual node PNA GraphTrans Augmentation methods N

UC Berkeley RISE 67 Dec 30, 2022
Official pytorch implementation of paper "Image-to-image Translation via Hierarchical Style Disentanglement".

HiSD: Image-to-image Translation via Hierarchical Style Disentanglement Official pytorch implementation of paper "Image-to-image Translation

364 Dec 14, 2022
Official implementation of particle-based models (GNS and DPI-Net) on the Physion dataset.

Physion: Evaluating Physical Prediction from Vision in Humans and Machines [paper] Daniel M. Bear, Elias Wang, Damian Mrowca, Felix J. Binder, Hsiao-Y

Hsiao-Yu Fish Tung 18 Dec 19, 2022
Face Mesh is a face geometry solution that estimates 468 3D face landmarks in real-time even on mobile devices

Face-Mesh Face Mesh is a face geometry solution that estimates 468 3D face landmarks in real-time even on mobile devices. It employs machine learning

Farnam Javadi 9 Dec 21, 2022
SeqTR: A Simple yet Universal Network for Visual Grounding

SeqTR This is the official implementation of SeqTR: A Simple yet Universal Network for Visual Grounding, which simplifies and unifies the modelling fo

seanZhuh 76 Dec 24, 2022
Save-restricted-v-3 - Save restricted content Bot For telegram

Save restricted content Bot Contact: Telegram A stable telegram bot to get restr

DEVANSH 11 Dec 21, 2022
Improving Calibration for Long-Tailed Recognition (CVPR2021)

MiSLAS Improving Calibration for Long-Tailed Recognition Authors: Zhisheng Zhong, Jiequan Cui, Shu Liu, Jiaya Jia [arXiv] [slide] [BibTeX] Introductio

Jia Research Lab 116 Dec 20, 2022
Optical machine for senses sensing using speckle and deep learning

# Senses-speckle [Remote Photonic Detection of Human Senses Using Secondary Speckle Patterns](https://doi.org/10.21203/rs.3.rs-724587/v1) paper Python

Zeev Kalyuzhner 0 Sep 26, 2021
This repository contains a set of codes to run (i.e., train, perform inference with, evaluate) a diarization method called EEND-vector-clustering.

EEND-vector clustering The EEND-vector clustering (End-to-End-Neural-Diarization-vector clustering) is a speaker diarization framework that integrates

45 Dec 26, 2022
An educational AI robot based on NVIDIA Jetson Nano.

JetBot Looking for a quick way to get started with JetBot? Many third party kits are now available! JetBot is an open-source robot based on NVIDIA Jet

NVIDIA AI IOT 2.6k Dec 29, 2022