python人工智能AI复现 ArcFace 毕业论文学术

2401807 3909
    


来源:
Licence:
联系:
分类:
平台:
环境:
大小:
更新:
标签:
联系方式 :
免费下载 ×

下载APP,支持永久资源免费下载

限免产品服务请联系qq:1585269081

下载APP
免费下载 ×
下载 ×

下载APP,资源永久免费


论文定制和修改服务请联系qq:1585269081 如果出现不能下载的情况,请联系站长,联系方式在下方。

免费下载 ×

载论文助手APP,资源永久免费

论文定制和修改服务请联系qq:1585269081 免费获取

如果你已经登录仍然出现不能下载的情况,请【点击刷新】本页面或者联系站长


InsightFace

Implementation of Additive Angular Margin Loss for Deep Face Detection. paper.

@article{deng2018arcface,
title={ArcFace: Additive Angular Margin Loss for Deep Face Recognition},
author={Deng, Jiankang and Guo, Jia and Niannan, Xue and Zafeiriou, Stefanos},
journal={arXiv:1801.07698},
year={2018}
}

DataSet

CASIA WebFace DataSet, 494,414 faces over 10,575 identities.

Dependencies

  • PyTorch 1.0.0

Usage

Data wrangling

Extract images, scan them, to get bounding boxes and landmarks:

$ python pre_process.py

Image alignment:

  1. Face detection(MTCNN).
  2. Face alignment(similar transformation).
  3. Central face selection.
  4. Resize -> 112x112.
Original Aligned Original Aligned
image image image image
image image image image
image image image image
image image image image
image image image image

Train

$ python train.py

To visualize the training process:

$ tensorboard --logdir=runs

Performance evaluation

DataSet

Use Labeled Faces in the Wild (LFW) dataset for performance evaluation:

  • 13233 faces
  • 5749 identities
  • 1680 identities with >=2 photo

Download LFW database put it under data folder:

$ wget http://vis-www.cs.umass.edu/lfw/lfw-funneled.tgz
$ wget http://vis-www.cs.umass.edu/lfw/pairs.txt
$ wget http://vis-www.cs.umass.edu/lfw/people.txt

Get it started

$ python lfw_eval.py

Results

# image size network use-se loss func gamma batch size weight decay s m LFW accuracy
1 112x112 ResNet-152 True ce na 128 5e-4 50 0.5 99.42%
2 112x112 ResNet-152 True focal 2.0 128 5e-4 50 0.5 99.38%
3 112x112 ResNet-101 True focal 2.0 256 5e-4 50 0.5 99.27%
4 112x112 ResNet-101 False focal 2.0 256 5e-4 50 0.5 99.23%

θj Distribution

image

Error analysis

False Positive

8 false positives:

1 2 1 2
image image image image
image image image image
image image image image
image image image image
False Negative

27 false negative, these 10 are randomly chosen:

1 2 1 2
image image image image
image image image image
image image image image
image image image image
image image image image

看大家都在讨论什么

0 条评论
免费下载 ×

下载APP,支持永久资源免费下载

下载APP 免费下载
温馨提示
请用电脑打开本网页,即可以免费获取你想要的了。