A general and strong 3D object detection codebase that supports more methods, datasets and tools (debugging, recording and analysis).

Last update: Nov 03, 2022

Overview

ALLINONE-Det

ALLINONE-Det is a general and strong 3D object detection codebase built on OpenPCDet, which supports more methods, datasets and tools (debugging, recording and analysis).

Changelog

[2022-01-08] NEW: Update ALLINONE-Det to v0.1.0:

Initial commit

Supported Features

Support the latest version of OpenPCDet v0.5.2
Support KITTI, ONCE, NuScnees, Lyft and Waymo datasets
Support more models and modules than OpenPCDet, e.g., CT3D, LiDAR R-CNN, VarifocalLoss, ATSS
Support plug-and-play remote visual debugging
Support unified model configuration, training, recording and analysis
Support Adaptive Object Augmentation Module
Support Balanced Sample Assignment and Objective Module
Support Test Time Augmentation

Model Zoo

Installation

Please refer to OpenPCDet for the installation of ALLINONE-Det.

Getting Started

Acknowledgement

Thanks to the strong and flexible OpenPCDet codebase maintained by Shaoshuai Shi (@sshaoshuai) and the reproduced benchmark (ONCE_Benchmark) on the ONCE (One Million Scenes) dataset by PointsCoder (@PointsCoder).

A general and strong 3D object detection codebase that supports more methods, datasets and tools (debugging, recording and analysis).

Related tags

Overview

ALLINONE-Det

Overview

Changelog

Supported Features

Model Zoo

Installation

Getting Started

Acknowledgement

Owner

Michael.CV

《A-CNN: Annularly Convolutional Neural Networks on Point Clouds》(2019)

Dataset and Code for ICCV 2021 paper "Real-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme"

Evaluation and Benchmarking of Speech Super-resolution Methods

Object DGCNN and DETR3D, Our implementations are built on top of MMdetection3D.

Machine Learning Model deployment for Container (TensorFlow Serving)

Code of the paper "Shaping Visual Representations with Attributes for Few-Shot Learning (ASL)".

DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold

A Streamlit component to render ECharts.

A very lightweight monitoring system for Raspberry Pi clusters running Kubernetes.

LLVM-based compiler for LightGBM gradient-boosted trees. Speeds up prediction by ≥10x.

Official PyTorch implementation of "IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos", CVPRW 2021

Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network

Fast sparse deep learning on CPUs

PyTorch code to run synthetic experiments.

PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021.

Posterior predictive distributions quantify uncertainties ignored by point estimates.

Equivariant CNNs for the sphere and SO(3) implemented in PyTorch

Code for "SRHEN: Stepwise-Refining Homography Estimation Network via Parsing Geometric Correspondences in Deep Latent Space"

Code base for "On-the-Fly Test-time Adaptation for Medical Image Segmentation"

Official pytorch implementation of the IrwGAN for unaligned image-to-image translation