基于Paddle框架的arcface复现

Overview

arcface-Paddle

基于Paddle框架的arcface复现

ArcFace-Paddle

本项目基于paddlepaddle框架复现ArcFace,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:

InsightFace

Paddle版本:

paddlepaddle-gpu==2.0.2

数据集

MS1M-ArcFace 解压数据集,你应该得到以下目录结构

faces_more
|───property
└───cplfw.bin
└───agedb_30.bin
└───vgg2_fp.bin
└───lfw.bin
└───cfp_ff.bin
└───cfp_fp.bin
└───calfw.bin
└───train.rec
└───train.idx

其中train.rec包含训练的图像,train.idx包含训练的标签,其均为mxnet数据格式,其余.bin文件均为二进制bytes文件

训练

整个工程文件具有以下目录结构

|───faces_more
└───eval
└───mxnet_reader
└───mxnet_reader_win10
└───backbones
└───paddle_pretrainedmodel
└───utils
└───dataset.py
└───losses.py
└───partial_fc.py
└───config.py
└───train.py

注意:mxnet_reader用于Linux系统部署训练,mxnet_reader_win10用于win10系统部署训练,两者均为重构mxnet数据读取后的代码

配置说明

config.py里面包含训练的超参数,学习率衰减函数,训练文件路径以及验证文件列表

backbones里面包含提供的训练模型,iresnet18iresnet34iresnet50iresnet100iresnet200

partial_fc来源于论文《Partial FC: Training 10 Million Identities on a Single Machine》,其目的是加速训练超大规模数据集

paddle_pretrainedmodel包含网络的预训练文件,其均为由torch模型转换而来,里面包含测试代码model_test.py以及精度文件results.txt

启动训练

python train.py [--network XXX]

这将会在log文件夹下产生训练的日志文件,其包括损失值以及所需训练的的时间,工程中的training.log包含了部分训练过程中的打印信息

训练过程中的权重文件将保存在emore_arcface_r50文件夹下,保存路径源于你的config文件设置,你应具有以下类似目录

|───emore_arcface_r50
└───backbone.pdparams
└───rank:0_softmax_weight.pkl
└───rank:0_softmax_weight_mom.pkl

本次利用aistudio训练的iresnet50得到的backbone.pdparams精度如下,其中lfw=0.99750cplfw=0.92117calfw=0.96017,你可以通过修改/home/aistudio/paddle_pretrainedmodel/ model_test.py权重路径model_params=/home/aistudio/emore_arcface_r50/backbone.pdparams来测试自己的模型

由于aistudio对保存版本文件的限制,我将保存的文件已上传至我的服务器,你可以通过wget ftp://207.246.98.85/emore_arcface_r50.zip下载获取

启动测试

模型和数据集读取代码下载

提取码:dzc0

AIStudio链接

cd /home/aistudio/paddle_pretrainedmodel
python model_test.py [--network XXX]

注意到model_test.py测试的官方提供的预训练模型,测试自己的训练模型,你需要修改读取文件的路径以及网络结构

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
BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training By Likun Cai, Zhi Zhang, Yi Zhu, Li Zhang, Mu Li, Xiangyang Xue. This

290 Dec 29, 2022
Source code for "MusCaps: Generating Captions for Music Audio" (IJCNN 2021)

MusCaps: Generating Captions for Music Audio Ilaria Manco1 2, Emmanouil Benetos1, Elio Quinton2, Gyorgy Fazekas1 1 Queen Mary University of London, 2

Ilaria Manco 57 Dec 07, 2022
codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification

DLCF-DCA codes for paper Combining Dynamic Local Context Focus and Dependency Cluster Attention for Aspect-level sentiment classification. submitted t

15 Aug 30, 2022
Official PyTorch implementation of "Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets" (ICLR 2021)

Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets This is the official PyTorch implementation for the paper Rapid Neural A

48 Dec 26, 2022
Clustergram - Visualization and diagnostics for cluster analysis in Python

Clustergram Visualization and diagnostics for cluster analysis Clustergram is a diagram proposed by Matthias Schonlau in his paper The clustergram: A

Martin Fleischmann 96 Dec 26, 2022
NumQMBasic - A mini-course offered to Undergrad physics students

The best way to use this material is by forking it by click the Fork button at the top, right corner. Then you will get your own copy to play with! Th

Raghu 35 Dec 05, 2022
🔊 Audio and fastai v2

Fastaudio An audio module for fastai v2. We want to help you build audio machine learning applications while minimizing the need for audio domain expe

152 Dec 28, 2022
Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.

Monk - A computer vision toolkit for everyone Why use Monk Issue: Want to begin learning computer vision Solution: Start with Monk's hands-on study ro

Tessellate Imaging 507 Dec 04, 2022
Tree LSTM implementation in PyTorch

Tree-Structured Long Short-Term Memory Networks This is a PyTorch implementation of Tree-LSTM as described in the paper Improved Semantic Representati

Riddhiman Dasgupta 529 Dec 10, 2022
Shōgun

The SHOGUN machine learning toolbox Unified and efficient Machine Learning since 1999. Latest release: Cite Shogun: Develop branch build status: Donat

Shōgun ML 2.9k Jan 04, 2023
HMLET (Hybrid-Method-of-Linear-and-non-linEar-collaborative-filTering-method)

Methods HMLET (Hybrid-Method-of-Linear-and-non-linEar-collaborative-filTering-method) Dynamically selecting the best propagation method for each node

Yong 7 Dec 18, 2022
This package contains a PyTorch Implementation of IB-GAN of the submitted paper in AAAI 2021

The PyTorch implementation of IB-GAN model of AAAI 2021 This package contains a PyTorch implementation of IB-GAN presented in the submitted paper (IB-

Insu Jeon 9 Mar 30, 2022
Re-implememtation of MAE (Masked Autoencoders Are Scalable Vision Learners) using PyTorch.

mae-repo PyTorch re-implememtation of "masked autoencoders are scalable vision learners". In this repo, it heavily borrows codes from codebase https:/

Peng Qiao 1 Dec 14, 2021
Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts

DataSelection-NMT Selecting Parallel In-domain Sentences for Neural Machine Translation Using Monolingual Texts Quick update: The paper got accepted o

Javad Pourmostafa 6 Jan 07, 2023
A Flexible Generative Framework for Graph-based Semi-supervised Learning (NeurIPS 2019)

G3NN This repo provides a pytorch implementation for the 4 instantiations of the flexible generative framework as described in the following paper: A

Jiaqi Ma 14 Oct 11, 2022
Python parser for DTED data.

DTED Parser This is a package written in pure python (with help from numpy) to parse and investigate Digital Terrain Elevation Data (DTED) files. This

Ben Bonenfant 12 Dec 18, 2022
SCAAML is a deep learning framwork dedicated to side-channel attacks run on top of TensorFlow 2.x.

SCAAML (Side Channel Attacks Assisted with Machine Learning) is a deep learning framwork dedicated to side-channel attacks. It is written in python and run on top of TensorFlow 2.x.

Google 69 Dec 21, 2022
Ensemble Visual-Inertial Odometry (EnVIO)

Ensemble Visual-Inertial Odometry (EnVIO) Authors : Jae Hyung Jung, Yeongkwon Choe, and Chan Gook Park 1. Overview This is a ROS package of Ensemble V

Jae Hyung Jung 95 Jan 03, 2023
A simple and useful implementation of LPIPS.

lpips-pytorch Description Developing perceptual distance metrics is a major topic in recent image processing problems. LPIPS[1] is a state-of-the-art

So Uchida 121 Dec 24, 2022
A Deep Reinforcement Learning Framework for Stock Market Trading

DQN-Trading This is a framework based on deep reinforcement learning for stock market trading. This project is the implementation code for the two pap

61 Jan 01, 2023