2021 National Underwater Robotics Vision Optics

Last update: Nov 04, 2022

Overview

2021-National-Underwater-Robotics-Vision-Optics

2021年全国水下机器人算法大赛-光学赛道-B榜精度第18名 (Kilian_Di的团队：A榜[email protected]:95 56.36 B榜[email protected]:95 56.7） 2021年全国水下机器人算法大赛-声学赛道-B榜精度第5名 (Kilian_Di的团队：A榜[email protected]:95 52.3 B榜[email protected]:95 53.1）

请按照mmdetection官方文档配置环境，并运行Config文件对应的模型

代码内容和trick：

基本网络模型
- cascade rcnn
- resnext101 pretrained on COCO
- soft-nms
- 基于mmdetection
- mmcv-full==1.2.5
- pytorch==1.6.0
- torchvision==0.7.0
- cudatoolkit=10.1
添加的trick
- dcn
- global_context(gcb)
- RandomRotate90
- cutout
- Mixup
- 边框抖动
- 高斯噪声椒盐噪声
- Libra RCNN
- GIoU/CIoU/DIoU Loss
- Attention Block
- Multi-scale Training and Testing

Note：mmdet-new/下的models文件请直接复制mmdetection项目即可

Contact me

Email：[email protected]

Owner

Di Chang

Computer Vision/[email protected] /

GitHub Repository

Proximal Backpropagation - a neural network training algorithm that takes implicit instead of explicit gradient steps

Proximal Backpropagation Proximal Backpropagation (ProxProp) is a neural network training algorithm that takes implicit instead of explicit gradient s

40 Dec 17, 2022

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

Transformer Based Multi-Source Domain Adaptation Dustin Wright and Isabelle Augenstein To appear in EMNLP 2020. Read the preprint: https://arxiv.org/a

36 Dec 05, 2022

reimpliment of DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

DFANet This repo is an unofficial pytorch implementation of DFANet:Deep Feature Aggregation for Real-Time Semantic Segmentation log 2019.4.16 After 48

248 Oct 21, 2022

A parallel framework for population-based multi-agent reinforcement learning.

MALib: A parallel framework for population-based multi-agent reinforcement learning MALib is a parallel framework of population-based learning nested

348 Jan 08, 2023

Contrastive Multi-View Representation Learning on Graphs

Contrastive Multi-View Representation Learning on Graphs This work introduces a self-supervised approach based on contrastive multi-view learning to l

208 Dec 23, 2022

An official source code for "Augmentation-Free Self-Supervised Learning on Graphs"

Augmentation-Free Self-Supervised Learning on Graphs An official source code for Augmentation-Free Self-Supervised Learning on Graphs paper, accepted

59 Dec 01, 2022

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection This repository contains an implementation of FCAF3D, a 3D object detection method introdu

153 Dec 29, 2022

Pure python PEMDAS expression solver without using built-in eval function

pypemdas Pure python PEMDAS expression solver without using built-in eval function. Supports nested parenthesis. Supported operators: + - * / ^ Exampl

1 Dec 22, 2021

CyTran: Cycle-Consistent Transformers for Non-Contrast to Contrast CT Translation

CyTran: Cycle-Consistent Transformers for Non-Contrast to Contrast CT Translation We propose a novel approach to translate unpaired contrast computed

13 Jan 02, 2023

VISNOTATE: An Opensource tool for Gaze-based Annotation of WSI Data

VISNOTATE: An Opensource tool for Gaze-based Annotation of WSI Data Introduction Requirements Installation and Setup Supported Hardware and Software R

1 Jun 14, 2022

Official PyTorch Code of GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection (CVPR 2021)

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Mo

76 Jan 02, 2023

2021 National Underwater Robotics Vision Optics

Related tags

Overview

2021-National-Underwater-Robotics-Vision-Optics

请按照mmdetection官方文档配置环境，并运行Config文件对应的模型

代码内容和trick：

Note：mmdet-new/下的models文件请直接复制mmdetection项目即可

Contact me

Owner

Di Chang

Proximal Backpropagation - a neural network training algorithm that takes implicit instead of explicit gradient steps

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

reimpliment of DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

A parallel framework for population-based multi-agent reinforcement learning.

Contrastive Multi-View Representation Learning on Graphs

An official source code for "Augmentation-Free Self-Supervised Learning on Graphs"

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

Pure python PEMDAS expression solver without using built-in eval function

CyTran: Cycle-Consistent Transformers for Non-Contrast to Contrast CT Translation

VISNOTATE: An Opensource tool for Gaze-based Annotation of WSI Data

Official PyTorch Code of GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection (CVPR 2021)

K-Means Clustering and Hierarchical Clustering Unsupervised Learning Solution in Python3.

Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences

Automated detection of anomalous exoplanet transits in light curve data.

Official repository of the paper Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Paper list of log-based anomaly detection

Python suite to construct benchmark machine learning datasets from the MIMIC-III clinical database.

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking.

GraphGT: Machine Learning Datasets for Graph Generation and Transformation

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".