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

Related tags

Deep Learningfacenet-pytorch
Overview

Facenet：人脸识别模型在Pytorch当中的实现

目录

  1. 性能情况 Performance
  2. 所需环境 Environment
  3. 注意事项 Attention
  4. 文件下载 Download
  5. 预测步骤 How2predict
  6. 训练步骤 How2train
  7. 参考资料 Reference

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

  1. 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
  1. 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

  1. 按照训练步骤训练。
  2. 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,
}
  1. 运行predict.py，输入
img\1_001.jpg
img\1_002.jpg

训练步骤

  1. 本文使用如下格式进行训练。
|-datasets
    |-people0
        |-123.jpg
        |-234.jpg
    |-people1
        |-345.jpg
        |-456.jpg
    |-...
  1. 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。
  2. 在训练前利用txt_annotation.py文件生成对应的cls_train.txt。
  3. 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。
  4. 运行train.py即可开始训练。

评估步骤

  1. 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
  2. 在eval_LFW.py设置使用的主干特征提取网络和网络权值。
  3. 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

You might also like...
Comments
  • 训练过程经常遇到BrokenPipeError: [Errno 32] Broken pipe

    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%

    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)
Owner
Bubbliiiing
Bubbliiiing
GitHub Repository
torchbearer: A model fitting library for PyTorch

Note: We're moving to PyTorch Lightning! Read about the move here. From the end of February, torchbearer will no longer be actively maintained. We'll

631 Jan 04, 2023
On Evaluation Metrics for Graph Generative Models

On Evaluation Metrics for Graph Generative Models Authors: Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham Taylor This is the offic

13 Jan 07, 2023
The official github repository for Towards Continual Knowledge Learning of Language Models

Towards Continual Knowledge Learning of Language Models This is the official github repository for Towards Continual Knowledge Learning of Language Mo

Joel Jang | 장요엘 65 Jan 07, 2023
Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

Step by Step on how to create an vision recognition model using LOBE.ai, export the model and run the model in an Azure Function

El Bruno 3 Mar 30, 2022
Anonymize BLM Protest Images

Anonymize BLM Protest Images This repository automates @BLMPrivacyBot, a Twitter bot that shows the anonymized images to help keep protesters safe. Us

Stanford Machine Learning Group 40 Oct 13, 2022
This repository contains pre-trained models and some evaluation code for our paper Towards Unsupervised Dense Information Retrieval with Contrastive Learning

Contriever: Towards Unsupervised Dense Information Retrieval with Contrastive Learning This repository contains pre-trained models and some evaluation

Meta Research 207 Jan 08, 2023
Dataloader tools for language modelling

Installation: pip install lm_dataloader Design Philosophy A library to unify lm dataloading at large scale Simple interface, any tokenizer can be inte

5 Mar 25, 2022
Implementation for "Exploiting Aliasing for Manga Restoration" (CVPR 2021)

[CVPR Paper](To appear) | [Project Website](To appear) | BibTex Introduction As a popular entertainment art form, manga enriches the line drawings det

133 Dec 15, 2022
[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

BCMI 49 Jul 27, 2022
WarpDrive: Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU

WarpDrive is a flexible, lightweight, and easy-to-use open-source reinforcement learning (RL) framework that implements end-to-end multi-agent RL on a single GPU (Graphics Processing Unit).

Salesforce 334 Jan 06, 2023
Implementation of our paper "DMT: Dynamic Mutual Training for Semi-Supervised Learning"

DMT: Dynamic Mutual Training for Semi-Supervised Learning This repository contains the code for our paper DMT: Dynamic Mutual Training for Semi-Superv

Zhengyang Feng 120 Dec 30, 2022
Source code for "Understanding Knowledge Integration in Language Models with Graph Convolutions"

Graph Convolution Simulator (GCS) Source code for "Understanding Knowledge Integration in Language Models with Graph Convolutions" Requirements: PyTor

yifan 10 Oct 18, 2022
Compositional and Parameter-Efficient Representations for Large Knowledge Graphs

NodePiece - Compositional and Parameter-Efficient Representations for Large Knowledge Graphs NodePiece is a "tokenizer" for reducing entity vocabulary

Michael Galkin 107 Jan 04, 2023
The code of "Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer".

Code data_preprocess.py: preprocess data for Dependent-T5. parameters.py: define parameters of Dependent-T5. train_tools.py: traning and evaluation co

1 Apr 21, 2022
Ontologysim: a Owlready2 library for applied production simulation

Ontologysim: a Owlready2 library for applied production simulation Ontologysim is an open-source deep production simulation framework, with an emphasi

10 Nov 30, 2022
N-gram models- Unsmoothed, Laplace, Deleted Interpolation

N-gram models- Unsmoothed, Laplace, Deleted Interpolation

Ravika Nagpal 1 Jan 04, 2022
An implementation for Neural Architecture Search with Random Labels (CVPR 2021 poster) on Pytorch.

Neural Architecture Search with Random Labels(RLNAS) Introduction This project provides an implementation for Neural Architecture Search with Random L

18 Nov 08, 2022
Generate pixel-style avatars with python.

face2pixel Generate pixel-style avatars with python. Run: Clone the project: git clone https://github.com/theodorecooper/face2pixel install requiremen

Theodore Cooper 2 May 11, 2022
Detecting Blurred Ground-based Sky/Cloud Images

Detecting Blurred Ground-based Sky/Cloud Images With the spirit of reproducible research, this repository contains all the codes required to produce t

1 Oct 20, 2021
Source code for ZePHyR: Zero-shot Pose Hypothesis Rating @ ICRA 2021

ZePHyR: Zero-shot Pose Hypothesis Rating ZePHyR is a zero-shot 6D object pose estimation pipeline. The core is a learned scoring function that compare

R-Pad - Robots Perceiving and Doing 18 Aug 22, 2022