A repo to show how to use custom dataset to train s2anet, and change backbone to resnext101

Overview

<<<<<<< HEAD

S2ANet-custom-dataset

A repo to show how to use custom dataset to train s2anet, and change backbone to resnext101

Align Deep Features for Oriented Object Detection

Align Deep Features for Oriented Object Detection,
Jiaming Han*, Jian Ding*, Jie Li, Gui-Song Xia,
arXiv preprint (arXiv:2008.09397) / TGRS (IEEE Xplore).

The repo is based on mmdetection, S2ANet branch pytorch1.9, and UCAS-AOD-benchmark thanks to their work.

Two versions are provided here: Original version and v20210104. We recommend to use v20210104 (i.e. the master branch).

Introduction

As there is a need for me to run S2ANet on UCAS_AOD. However, there is no present work to do this. This repo is both a tutorial and an extension to original project S2ANet. Besides, I used UCAS-AOD-benchmark to prepare for dataset.

The main problems this repo solved are:

  • custom dataset training(UCAS_AOD as an example)
  • change the backbone to ResNeXt101x64_4d to gain more performance.(this pretrain model is provided in the link below, after downloading, move it to torch pretrain cache dir)
  • a tutorial for begineers in remote-sensing
  • provide some pretrained models with baidu Netdisk
  • align the accuracy provided in UCAS-AOD-benchmark (The Reason might be training params for I only have RTX3060 12G)

Results for UCAS_AOD

class ap
car 80.75557185
airplane 90.64514424
pretrained model file can be downloaded here. code: 0lsj

Tutorial for custom training

files to be added :

  • DOTA_devkit/ucas_aod_evaluation.py
  • mmdet/datasets/UCAS_AOD.py
  • tools/test.py
  • configs/ucasaod/*

The first one is used when evaluating.
The second one is for loading custom dataset(like this directory in UCAS_AOD_Benchmark).
The third is adding params for evaluating.
The fourth is config file for training.

Something Important to be noticed

  • 1.the processed dataset anno filed(.txt) have 14 cols, and they are $class,x_1,y_1,x_2,y_2,x_3,y_3,x_4,y_4,theta,x,y, width,height$. And theta is angle not arc(see here).

Citation

@article{han2021align,  
  author={J. {Han} and J. {Ding} and J. {Li} and G. -S. {Xia}},  
  journal={IEEE Transactions on Geoscience and Remote Sensing},   
  title={Align Deep Features for Oriented Object Detection},   
  year={2021}, 
  pages={1-11},  
  doi={10.1109/TGRS.2021.3062048}}

@inproceedings{xia2018dota,
  title={DOTA: A large-scale dataset for object detection in aerial images},
  author={Xia, Gui-Song and Bai, Xiang and Ding, Jian and Zhu, Zhen and Belongie, Serge and Luo, Jiebo and Datcu, Mihai and Pelillo, Marcello and Zhang, Liangpei},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={3974--3983},
  year={2018}
}

@InProceedings{Ding_2019_CVPR,
  author = {Ding, Jian and Xue, Nan and Long, Yang and Xia, Gui-Song and Lu, Qikai},
  title = {Learning RoI Transformer for Oriented Object Detection in Aerial Images},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2019}
}

@article{chen2019mmdetection,
  title={MMDetection: Open mmlab detection toolbox and benchmark},
  author={Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and Liu, Ziwei and Xu, Jiarui and others},
  journal={arXiv preprint arXiv:1906.07155},
  year={2019}
}

pytorch1.9

Owner
jedibobo
jedibobo
Code and Data for the paper: Molecular Contrastive Learning with Chemical Element Knowledge Graph [AAAI 2022]

Knowledge-enhanced Contrastive Learning (KCL) Molecular Contrastive Learning with Chemical Element Knowledge Graph [ AAAI 2022 ]. We construct a Chemi

Fangyin 58 Dec 26, 2022
Source code and data in paper "MDFEND: Multi-domain Fake News Detection (CIKM'21)"

MDFEND: Multi-domain Fake News Detection This is an official implementation for MDFEND: Multi-domain Fake News Detection which has been accepted by CI

Rich 40 Dec 18, 2022
LSTM-VAE Implementation and Relevant Evaluations

LSTM-VAE Implementation and Relevant Evaluations Before using any file in this repository, please create two directories under the root directory name

Lan Zhang 5 Oct 08, 2022
領域を指定し、キーを入力することで画像を保存するツールです。クラス分類用のデータセット作成を想定しています。

image-capture-class-annotation 領域を指定し、キーを入力することで画像を保存するツールです。 クラス分類用のデータセット作成を想定しています。 Requirement OpenCV 3.4.2 or later Usage 実行方法は以下です。 起動後はマウスクリック4

KazuhitoTakahashi 5 May 28, 2021
EqGAN - Improving GAN Equilibrium by Raising Spatial Awareness

EqGAN - Improving GAN Equilibrium by Raising Spatial Awareness Improving GAN Equilibrium by Raising Spatial Awareness Jianyuan Wang, Ceyuan Yang, Ying

GenForce: May Generative Force Be with You 149 Dec 19, 2022
A code generator from ONNX to PyTorch code

onnx-pytorch Generating pytorch code from ONNX. Currently support onnx==1.9.0 and torch==1.8.1. Installation From PyPI pip install onnx-pytorch From

Wenhao Hu 94 Jan 06, 2023
Performant, differentiable reinforcement learning

deluca Performant, differentiable reinforcement learning Notes This is pre-alpha software and is undergoing a number of core changes. Updates to follo

Google 114 Dec 27, 2022
StyleGAN2-ADA - Official PyTorch implementation

Abstract: Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmenta

NVIDIA Research Projects 3.2k Dec 30, 2022
Code for "Learning Graph Cellular Automata"

Learning Graph Cellular Automata This code implements the experiments from the NeurIPS 2021 paper: "Learning Graph Cellular Automata" Daniele Grattaro

Daniele Grattarola 37 Oct 26, 2022
Optimizaciones incrementales al problema N-Body con el fin de evaluar y comparar las prestaciones de los traductores de Python en el ámbito de HPC.

Python HPC Optimizaciones incrementales de N-Body (all-pairs) con el fin de evaluar y comparar las prestaciones de los traductores de Python en el ámb

Andrés Milla 12 Aug 04, 2022
Companion code for "Bayesian logistic regression for online recalibration and revision of risk prediction models with performance guarantees"

Companion code for "Bayesian logistic regression for online recalibration and revision of risk prediction models with performance guarantees" Installa

0 Oct 13, 2021
《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

The Most Important Thing. Our code is developed based on: LXMERT: Learning Cross-Modality Encoder Representations from Transformers

53 Dec 16, 2022
SSD-based Object Detection in PyTorch

SSD-based Object Detection in PyTorch 서강대학교 현대모비스 SW 프로그램에서 진행한 인공지능 프로젝트입니다. Jetson nano를 이용해 pre-trained network를 fine tuning시켜 차량 및 신호등 인식을 구현하였습니다

Haneul Kim 1 Nov 16, 2021
Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

Federated learning on graph, especially on graph neural networks (GNNs), knowledge graph, and private GNN.

keven 198 Dec 20, 2022
Unofficial implementation of Proxy Anchor Loss for Deep Metric Learning

Proxy Anchor Loss for Deep Metric Learning Unofficial pytorch, tensorflow and mxnet implementations of Proxy Anchor Loss for Deep Metric Learning. Not

Geonmo Gu 3 Jun 09, 2021
Unofficial keras(tensorflow) implementation of MAE model from Masked Autoencoders Are Scalable Vision Learners

MAE-keras Unofficial keras(tensorflow) implementation of MAE model described in 'Masked Autoencoders Are Scalable Vision Learners'. This work has been

Yewon 11 Jun 12, 2022
SANet: A Slice-Aware Network for Pulmonary Nodule Detection

SANet: A Slice-Aware Network for Pulmonary Nodule Detection This paper (SANet) has been accepted and early accessed in IEEE TPAMI 2021. This code and

Jie Mei 39 Dec 17, 2022
Generic template to bootstrap your PyTorch project with PyTorch Lightning, Hydra, W&B, and DVC.

NN Template Generic template to bootstrap your PyTorch project. Click on Use this Template and avoid writing boilerplate code for: PyTorch Lightning,

Luca Moschella 520 Dec 30, 2022
FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset (CVPR2022)

FaceVerse FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset Lizhen Wang, Zhiyuan Chen, Tao Yu, Chenguang

Lizhen Wang 219 Dec 28, 2022
Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement

Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement In this project, we proposed a Domain Disentanglement Faster-RCNN (DDF)

19 Nov 24, 2022