这是一个facenet-pytorch的库，可以用于训练自己的人脸识别模型。

Last update: Jan 06, 2023

Related tags

Overview

Facenet：人脸识别模型在Pytorch当中的实现

性能情况

训练数据集	权值文件名称	测试数据集	输入图片大小	accuracy
CASIA-WebFace	facenet_mobilenet.pth	LFW	160x160	98.23%
CASIA-WebFace	facenet_inception_resnetv1.pth	LFW	160x160	98.78%

所需环境

pytorch==1.2.0

文件下载

已经训练好的facenet_mobilenet.pth和facenet_inception_resnetv1.pth可以在百度网盘下载。
链接: https://pan.baidu.com/s/1slUYdpskFpUX62WpJeLByA 提取码: fe1w

训练用的CASIA-WebFaces数据集以及评估用的LFW数据集可以在百度网盘下载。
链接: https://pan.baidu.com/s/1fhiHlylAFVoR43yfDbi4Ag 提取码: gkch

预测步骤

a、使用预训练权重

下载完库后解压，在model_data文件夹里已经有了facenet_mobilenet.pth，可直接运行predict.py输入：

img\1_001.jpg
img\1_002.jpg

也可以在百度网盘下载facenet_inception_resnetv1.pth，放入model_data，修改facenet.py文件的model_path后，输入：

img\1_001.jpg
img\1_002.jpg

b、使用自己训练的权重

按照训练步骤训练。
在facenet.py文件里面，在如下部分修改model_path和backbone使其对应训练好的文件；model_path对应logs文件夹下面的权值文件，backbone对应主干特征提取网络。

_defaults = {
    "model_path"    : "model_data/facenet_mobilenet.pth",
    "input_shape"   : (160, 160, 3),
    "backbone"      : "mobilenet",
    "cuda"          : True,
}

运行predict.py，输入

img\1_001.jpg
img\1_002.jpg

训练步骤

本文使用如下格式进行训练。

|-datasets
    |-people0
        |-123.jpg
        |-234.jpg
    |-people1
        |-345.jpg
        |-456.jpg
    |-...

下载好数据集，将训练用的CASIA-WebFaces数据集以及评估用的LFW数据集，解压后放在根目录。
在训练前利用txt_annotation.py文件生成对应的cls_train.txt。
利用train.py训练facenet模型，训练前，根据自己的需要选择backbone，model_path和backbone一定要对应。
运行train.py即可开始训练。

评估步骤

下载好评估数据集，将评估用的LFW数据集，解压后放在根目录
在eval_LFW.py设置使用的主干特征提取网络和网络权值。
运行eval_LFW.py来进行模型准确率评估。

Reference

https://github.com/davidsandberg/facenet
https://github.com/timesler/facenet-pytorch

Comments

训练过程经常遇到BrokenPipeError: [Errno 32] Broken pipe

Epoch 1/100: 100%|██████████| 583/583 [07:36<00:00, 1.07it/s, accuracy=0.89, lr=0.01, total_CE_loss=9.02, total_triple_loss=0.101]Traceback (most recent call last): File "/opt/vitis_ai/conda/envs/vitis-ai-optimizer_pytorch/lib/python3.7/multiprocessing/queues.py", line 242, in _feed send_bytes(obj) File "/opt/vitis_ai/conda/envs/vitis-ai-optimizer_pytorch/lib/python3.7/multiprocessing/connection.py", line 200, in send_bytes self._send_bytes(m[offset:offset + size]) File "/opt/vitis_ai/conda/envs/vitis-ai-optimizer_pytorch/lib/python3.7/multiprocessing/connection.py", line 404, in _send_bytes self._send(header + buf) File "/opt/vitis_ai/conda/envs/vitis-ai-optimizer_pytorch/lib/python3.7/multiprocessing/connection.py", line 368, in _send n = write(self._handle, buf) BrokenPipeError: [Errno 32] Broken pipe

opened by jia0511 1
lfw数据集处理有什么区别？精度目前97%

使用facenet_mobilenet.pth 在 LFW 数据集上，调整图片大小为 160x160 ，得到了0.97的精度，没有到| 98.23%，而在百度网盘提供的slfw数据上，精度可以到98%，但是我看网页上提供的数据图片大小是96*112，请问下，LFW处理上应用什么其他方法吗？

Test Epoch: [5888/6000 (96%)]: : 24it [00:32, 1.34s/it] Accuracy: 0.97383+-0.00675 Best_thresholds: 1.16000 Validation rate: 0.82100+-0.03127 @ FAR=0.00100

opened by xiaomujiang 1

Releases(v2.0)

v2.0(Mar 24, 2022)
仓库特点

支持多backbone训练。

支持训练时评估，通过train.py的lfw_eval_flag调整、

大量的注释，多个可调整参数。

summary.py文件用于观看网络结构。

使用softmax辅助训练

Source code(tar.gz)
Source code(zip)
v1.0(May 16, 2021)

Source code(tar.gz)
Source code(zip)
backbone_weights_of_inception_resnetv1.pth(86.31 MB)
backbone_weights_of_mobilenetv1.pth(16.25 MB)
facenet_inception_resnetv1.pth(92.42 MB)
facenet_mobilenet.pth(18.05 MB)

Owner

Bubbliiiing

GitHub Repository

Video Instance Segmentation using Inter-Frame Communication Transformers (NeurIPS 2021)

Video Instance Segmentation using Inter-Frame Communication Transformers (NeurIPS 2021) Paper Video Instance Segmentation using Inter-Frame Communicat

81 Dec 29, 2022

GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape Completion

GarmentNets This repository contains the source code for the paper GarmentNets: Category-Level Pose Estimation for Garments via Canonical Space Shape

43 Nov 21, 2022

PyTorch implementation for "HyperSPNs: Compact and Expressive Probabilistic Circuits", NeurIPS 2021

HyperSPN This repository contains code for the paper: HyperSPNs: Compact and Expressive Probabilistic Circuits "HyperSPNs: Compact and Expressive Prob

8 Nov 08, 2022

Minimalist Error collection Service compatible with Rollbar clients. Sentry or Rollbar alternative.

Minimalist Error collection Service Features Compatible with any Rollbar client(see https://docs.rollbar.com/docs). Just change the endpoint URL to yo

381 Nov 11, 2022

Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.

Optimum Transformers Accelerated NLP pipelines for fast inference 🚀 on CPU and GPU. Built with 🤗 Transformers, Optimum and ONNX runtime. Installatio

115 Dec 16, 2022

Bayesian inference for Permuton-induced Chinese Restaurant Process (NeurIPS2021).

Permuton-induced Chinese Restaurant Process Note: Currently only the Matlab version is available, but a Python version will be available soon! This is

3 Dec 17, 2022

Code for "Learning to Segment Rigid Motions from Two Frames".

rigidmask Code for "Learning to Segment Rigid Motions from Two Frames". ** This is a partial release with inference and evaluation code.

157 Nov 21, 2022

Website which uses Deep Learning to generate horror stories.

Creepypasta - Text Generator Website which uses Deep Learning to generate horror stories. View Demo · View Website Repo · Report Bug · Request Feature

5 Oct 14, 2022

The code repository for "RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection" (ACM MM'21)

RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection (ACM MM'21) By Zhuofan Zong, Qianggang Cao, Biao Leng Introduction F

9 Jul 30, 2022

Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

PSML paper: Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors PSML_IONE,PSML_ABNE,PSML_DEEPLINK,PSML_SNNA: numpy

13 Nov 27, 2022

How will electric vehicles affect traffic congestion and energy consumption: an integrated modelling approach

EV-charging-impact This repository contains the code that has been used for the Queue modelling for the paper "How will electric vehicles affect traff

7 Nov 30, 2022

Differentiable Quantum Chemistry (only Differentiable Density Functional Theory and Hartree Fock at the moment)

DQC: Differentiable Quantum Chemistry Differentiable quantum chemistry package. Currently only support differentiable density functional theory (DFT)

75 Dec 02, 2022

I-BERT: Integer-only BERT Quantization

I-BERT: Integer-only BERT Quantization HuggingFace Implementation I-BERT is also available in the master branch of HuggingFace! Visit the following li

139 Dec 27, 2022

Implementation of 'lightweight' GAN, proposed in ICLR 2021, in Pytorch. High resolution image generations that can be trained within a day or two

512x512 flowers after 12 hours of training, 1 gpu 256x256 flowers after 12 hours of training, 1 gpu Pizza 'Lightweight' GAN Implementation of 'lightwe

1.5k Jan 02, 2023