• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号

goodluckcwl/Face-alignment-mobilenet-v2: Face Alignment by Mobilenetv2

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

goodluckcwl/Face-alignment-mobilenet-v2

开源软件地址(OpenSource Url):

https://github.com/goodluckcwl/Face-alignment-mobilenet-v2

开源编程语言(OpenSource Language):

Python 100.0%

开源软件介绍(OpenSource Introduction):

Face-alignment-mobilenet-v2

Face Alignment by MobileNetv2. Note that MTCNN is used to provided the input boundingbox. You need to modify the path of images in order to run the demo.

Network Structure

The most important part of the mobilenet-v2 network is the design of bottleneck. In our experiments, we crop the face image by the boundingbox and resize it to , which is the input size of the network. Based on this, we can design the structure of our customized mobilenet-v2 for facial landmark lacalization. Note that the receptive field is a key factor to the design of the network.

Input Operator t channels n stride
conv2d - 16 1 2
bottleneck 6 24 1 2
conv2d 6 24 1 1
conv2d 6 32 1 2
conv2d 6 32 1 1
conv2d 6 64 1 2
conv2d 6 64 1 1
inner product - 200 1 -
200 inner product - 200 1 -
200 inner product - 50 1 -
50 inner product - 136 1 -

Note that this structure mainly has two features:

  • Use LeakyReLU rather than ReLU.
  • Use bottleneck embedding, which is 50 in our experiments.

Training

The training data including:

  • Training data of 300W dataset
  • Training data of Menpo dataset

Data Augmentation

Data augmentation is important to the performance of face alignment. I have tried several kinds of data augmentation method, including:

  • Random Flip.
  • Random Shift.
  • Random Scale.
  • Random Rotation. The image is rotated by the degree sampled from -30 to 30.
  • Random Noise. Gaussian noise is added to the input images.

Performance

The performance on 300W is not good enough. May be I need to try more times. If you have any ideas, please contact me or open an issue.

Method Input Size Common Challenge Full set Training Data
VGG-Shadow(With Dropout) 70 * 60 5.66 10.82 6.67 300W
Mobilenet-v2-stage1 64 * 64 6.07 10.60 6.96 300W and Menpo
Mobilenet-v2-stage2 64 * 64 5.76 8.93 6.39 300W and Menpo

Dataset

Dataset Number of images for training
300-W 3148
Menpo 12006

Result on 300W

The ground truth landmarks is donated by white color while the predicted ones blue.

Pre-train Models

The pre-train models can be downloaded from baiduyun or GoogleDisk.

Demo

I write a demo to view the alignment results. Besides, the yaw, row and pitch parameters are estimated by the predicted landmarks. To run the domo, please do:

  1. Download and compile caffe. Compile pycaffe.
  2. Use MTCNN to detect face of the images and save the boundingbox of faces.
  3. Modified the path in demo.py.
  4. Run.

Dependence

To use my code to reproduce the results, you need to use my caffe. I have added some useful layers.

Reference:




鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
上一篇:
juleswhite/mobile-cloud-asgn1发布时间:2022-08-30
下一篇:
chehongshu/ncnnforandroid_objectiondetection_Mobilenetssd: 利用Mobilenetssd目标 ...发布时间:2022-08-30
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap