基于Paddle框架的fcanet复现

Overview

fcanet-Paddle

基于Paddle框架的fcanet复现

fcanet

本项目基于paddlepaddle框架复现fcanet,并参加百度第三届论文复现赛,将在2021年5月15日比赛完后提供AIStudio链接~敬请期待

参考项目:

frazerlin-fcanet

数据准备

本项目已挂载论文所使用的数据集,对于tgztar文件需要利用以下命令解压

tar -xvf benchmark.tgz
tar xvf VOCtrainval_11-May-2012.tar

整个工程具有以下目录结构

/home/aistudio
|───Data(数据集)
└───────benchmark_RELEASE
└───────VOCdevkit
└───────GrabCut
└───────Berkeley
└───fcanet(代码文件)
└───InitialPaddleModel(初始化权重)

训练

The official PyTorch implementation of CVPR 2020 paper "Interactive Image Segmentation with First Click Attention". 并未提供训练代码。通过邮件联系作者,作者由于企业合作项目原因,合作结束后会将会提供训练代码

测试

模型下载

提取码:2ira

AIStudio链接

验证集测试

python fcanet/evaluate.py --backbone [resnet/res2net] --dataset [GrabCut,Berkeley,DAVIS(not exists in this repo),VOCdevkit] (--sis)

如下图所示,默认的backbone均为101

resnet101测试示例

res2net101测试示例

backbone dataset mNoC mIoU-NoC
resnet101 Berkeley 4.23 [0. 0.728 0.854 0.885 0.912 0.915 0.926 0.935 0.939 0.935 0.94 0.943 0.942 0.944 0.945 0.945 0.947 0.947 0.948 0.947 0.949]
resnet101 GrabCut 2.24 [0. 0.78 0.87 0.923 0.944 0.95 0.956 0.966 0.964 0.971 0.971 0.971 0.975 0.977 0.978 0.979 0.978 0.978 0.979 0.979 0.979]
resnet101 VOC2012 2.9810329734461627 [0. 0.715 0.838 0.885 0.909 0.926 0.937 0.945 0.951 0.957 0.962 0.964 0.967 0.969 0.971 0.973 0.974 0.976 0.977 0.978 0.979]
res2net101 Berkeley 3.98 [0. 0.788 0.872 0.901 0.921 0.93 0.933 0.938 0.938 0.943 0.943 0.943 0.943 0.945 0.947 0.948 0.949 0.949 0.95 0.951 0.95 ]
res2net101 GrabCut 2.16 [0. 0.819 0.877 0.927 0.916 0.931 0.948 0.96 0.966 0.967 0.969 0.971 0.973 0.976 0.977 0.976 0.978 0.977 0.98 0.977 0.979]
res2net101 VOC2012 2.793988911584476 [0. 0.757 0.841 0.882 0.908 0.925 0.937 0.945 0.952 0.958 0.963 0.966 0.968 0.971 0.973 0.974 0.976 0.977 0.978 0.98 0.98 ]

可视化测试

利用annotator.py可以实现可视化操作,感兴趣的读者可是利用Qt实现UI程序,实现效果如下所示

需要注意的是,AIStudio环境暂不支持这种可视化方式,你需要将此仓库部署到本地运行,你可能需要修改代码文件中的路径

python fcanet/annotator.py --backbone res2net --input fcanet/test.jpg --output test_mask.jpg

关于作者

姓名 郭权浩
学校 电子科技大学研2020级
研究方向 计算机视觉
主页 Deep Hao的主页
如有错误,请及时留言纠正,非常蟹蟹!
后续会有更多论文复现系列推出,欢迎大家有问题留言交流学习,共同进步成长!
Owner
QuanHao Guo
master at UESTC
QuanHao Guo
Deep Residual Learning for Image Recognition

Deep Residual Learning for Image Recognition This is a Torch implementation of "Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhan

Kimmy 561 Dec 01, 2022
PyTorch implementation of spectral graph ConvNets, NIPS’16

Graph ConvNets in PyTorch October 15, 2017 Xavier Bresson http://www.ntu.edu.sg/home/xbresson https://github.com/xbresson https://twitter.com/xbresson

Xavier Bresson 287 Jan 04, 2023
4st place solution for the PBVS 2022 Multi-modal Aerial View Object Classification Challenge - Track 1 (SAR) at PBVS2022

A Two-Stage Shake-Shake Network for Long-tailed Recognition of SAR Aerial View Objects 4st place solution for the PBVS 2022 Multi-modal Aerial View Ob

LinpengPan 5 Nov 09, 2022
A large-scale video dataset for the training and evaluation of 3D human pose estimation models

ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation models. It contains 17 different amateur subjects performing 30

Aiden Nibali 25 Jun 20, 2021
BC3407-Group-5-Project - BC3407 Group Project With Python

BC3407-Group-5-Project As the world struggles to contain the ever-changing varia

1 Jan 26, 2022
Build Graph Nets in Tensorflow

Graph Nets library Graph Nets is DeepMind's library for building graph networks in Tensorflow and Sonnet. Contact DeepMind 5.2k Jan 05, 2023

PyTorch Implementation of DSB for Score Based Generative Modeling. Experiments managed using Hydra.

Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling This repository contains the implementation for the paper Diffusion

James Thornton 50 Jan 03, 2023
Experiment about Deep Person Re-identification with EfficientNet-v2

We evaluated the baseline with Resnet50 and Efficienet-v2 without using pretrained models. Also Resnet50-IBN-A and Efficientnet-v2 using pretrained on ImageNet. We used two datasets: Market-1501 and

lan.nguyen2k 77 Jan 03, 2023
Code for Overinterpretation paper Overinterpretation reveals image classification model pathologies

Overinterpretation This repository contains the code for the paper: Overinterpretation reveals image classification model pathologies Authors: Brandon

Gifford Lab, MIT CSAIL 17 Dec 10, 2022
This is a Python wrapper for TA-LIB based on Cython instead of SWIG.

TA-Lib This is a Python wrapper for TA-LIB based on Cython instead of SWIG. From the homepage: TA-Lib is widely used by trading software developers re

John Benediktsson 7.3k Jan 03, 2023
UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model

UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model Official repository for the ICCV 2021 paper: UltraPose: Syn

MomoAILab 92 Dec 21, 2022
Point Cloud Registration using Representative Overlapping Points.

Point Cloud Registration using Representative Overlapping Points (ROPNet) Abstract 3D point cloud registration is a fundamental task in robotics and c

ZhuLifa 36 Dec 16, 2022
RodoSol-ALPR Dataset

RodoSol-ALPR Dataset This dataset, called RodoSol-ALPR dataset, contains 20,000 images captured by static cameras located at pay tolls owned by the Ro

Rayson Laroca 45 Dec 15, 2022
Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation.

Pretrain-Recsys This is our Tensorflow implementation for our WSDM 2021 paper: Bowen Hao, Jing Zhang, Hongzhi Yin, Cuiping Li, Hong Chen. Pre-Training

30 Nov 14, 2022
PyTorch implementation of "Dataset Knowledge Transfer for Class-Incremental Learning Without Memory" (WACV2022)

Dataset Knowledge Transfer for Class-Incremental Learning Without Memory [Paper] [Slides] Summary Introduction Installation Reproducing results Citati

Habib Slim 5 Dec 05, 2022
Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust.

Subspace Adversarial Training Single-step adversarial training (AT) has received wide attention as it proved to be both efficient and robust. However,

15 Sep 02, 2022
🇰🇷 Text to Image in Korean

KoDALLE Utilizing pretrained language model’s token embedding layer and position embedding layer as DALLE’s text encoder. Background Training DALLE mo

HappyFace 74 Sep 22, 2022
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

EFENet EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation Code is a bit messy now. I woud clean up soon. For training the EF

Yaping Zhao 19 Nov 05, 2022
Dataset for the Research2Clinics @ NeurIPS 2021 Paper: What Do You See in this Patient? Behavioral Testing of Clinical NLP Models

Behavioral Testing of Clinical NLP Models This repository contains code for testing the behavior of clinical prediction models based on patient letter

Betty van Aken 2 Sep 20, 2022