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
A complete speech segmentation system using Kaldi and x-vectors for voice activity detection (VAD) and speaker diarisation.

bbc-speech-segmenter: Voice Activity Detection & Speaker Diarization A complete speech segmentation system using Kaldi and x-vectors for voice activit

BBC 16 Oct 27, 2022
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks This repository contains a TensorFlow implementation of "

Jingwei Zheng 5 Jan 08, 2023
Implements pytorch code for the Accelerated SGD algorithm.

AccSGD This is the code associated with Accelerated SGD algorithm used in the paper On the insufficiency of existing momentum schemes for Stochastic O

205 Jan 02, 2023
PyTorch 1.5 implementation for paper DECOR-GAN: 3D Shape Detailization by Conditional Refinement.

DECOR-GAN PyTorch 1.5 implementation for paper DECOR-GAN: 3D Shape Detailization by Conditional Refinement, Zhiqin Chen, Vladimir G. Kim, Matthew Fish

Zhiqin Chen 72 Dec 31, 2022
OOD Generalization and Detection (ACL 2020)

Pretrained Transformers Improve Out-of-Distribution Robustness How does pretraining affect out-of-distribution robustness? We create an OOD benchmark

littleRound 57 Jan 09, 2023
SeqTR: A Simple yet Universal Network for Visual Grounding

SeqTR This is the official implementation of SeqTR: A Simple yet Universal Network for Visual Grounding, which simplifies and unifies the modelling fo

seanZhuh 76 Dec 24, 2022
Official code for the CVPR 2021 paper "How Well Do Self-Supervised Models Transfer?"

How Well Do Self-Supervised Models Transfer? This repository hosts the code for the experiments in the CVPR 2021 paper How Well Do Self-Supervised Mod

Linus Ericsson 157 Dec 16, 2022
FEMDA: Robust classification with Flexible Discriminant Analysis in heterogeneous data

FEMDA: Robust classification with Flexible Discriminant Analysis in heterogeneous data. Flexible EM-Inspired Discriminant Analysis is a robust supervised classification algorithm that performs well i

0 Sep 06, 2022
Omniscient Video Super-Resolution

Omniscient Video Super-Resolution This is the official code of OVSR (Omniscient Video Super-Resolution, ICCV 2021). This work is based on PFNL. Datase

36 Oct 27, 2022
Second-order Attention Network for Single Image Super-resolution (CVPR-2019)

Second-order Attention Network for Single Image Super-resolution (CVPR-2019) "Second-order Attention Network for Single Image Super-resolution" is pub

516 Dec 28, 2022
PyTorch Implementation of Realtime Multi-Person Pose Estimation project.

PyTorch Realtime Multi-Person Pose Estimation This is a pytorch version of Realtime_Multi-Person_Pose_Estimation, origin code is here Realtime_Multi-P

Dave Fang 157 Nov 12, 2022
This folder contains the python code of UR5E's advanced forward kinematics model.

This folder contains the python code of UR5E's advanced forward kinematics model. By entering the angle of the joint of UR5e, the detailed coordinates of up to 48 points around the robot arm can be c

Qiang Wang 4 Sep 17, 2022
A benchmark framework for Tensorflow

TensorFlow benchmarks This repository contains various TensorFlow benchmarks. Currently, it consists of two projects: PerfZero: A benchmark framework

1.1k Dec 30, 2022
NOMAD - A blackbox optimization software

################################################################################### #

Blackbox Optimization 78 Dec 29, 2022
This is an open source library implementing hyperbox-based machine learning algorithms

hyperbox-brain is a Python open source toolbox implementing hyperbox-based machine learning algorithms built on top of scikit-learn and is distributed

Complex Adaptive Systems (CAS) Lab - University of Technology Sydney 21 Dec 14, 2022
On-device wake word detection powered by deep learning.

Porcupine Made in Vancouver, Canada by Picovoice Porcupine is a highly-accurate and lightweight wake word engine. It enables building always-listening

Picovoice 2.8k Dec 29, 2022
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution Kai Zhang, Jingyun Liang, Luc Van Gool, Radu Timofte Computer Vision Lab

Kai Zhang 804 Jan 08, 2023
Official Repository for Machine Learning class - Physics Without Frontiers 2021

PWF 2021 Física Sin Fronteras es un proyecto del Centro Internacional de Física Teórica (ICTP) en Trieste Italia. El ICTP es un centro dedicado a fome

36 Aug 06, 2022
An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.

An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models. Hyperactive: is very easy to lear

Simon Blanke 422 Jan 04, 2023
Neural HMMs are all you need (for high-quality attention-free TTS)

Neural HMMs are all you need (for high-quality attention-free TTS) Shivam Mehta, Éva Székely, Jonas Beskow, and Gustav Eje Henter This is the official

Shivam Mehta 0 Oct 28, 2022