首页
所有分类
TAGS
文字工具 EMOJI BIBLE
编程 Python

把vgg-face.mat权重迁移到pytorch模型示例

Posted in Python onDecember 27, 2019

最近使用pytorch时，需要用到一个预训练好的人脸识别模型提取人脸ID特征，想到很多人都在用用vgg-face，但是vgg-face没有pytorch的模型，于是写个vgg-face.mat转到pytorch模型的代码

#!/usr/bin/env python2
# -*- coding: utf-8 -*-
"""
Created on Thu May 10 10:41:40 2018
@author: hy
"""
import torch
import math
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
from scipy.io import loadmat
import scipy.misc as sm
import matplotlib.pyplot as plt
 
class vgg16_face(nn.Module):
  def __init__(self,num_classes=2622):
    super(vgg16_face,self).__init__()
    inplace = True
    self.conv1_1 = nn.Conv2d(3,64,kernel_size=(3,3),stride=(1,1),padding=(1,1))
    self.relu1_1 = nn.ReLU(inplace)
    self.conv1_2 = nn.Conv2d(64,64,kernel_size=(3,3),stride=(1,1),padding=(1,1))
    self.relu1_2 = nn.ReLU(inplace)
    self.pool1 = nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1), ceil_mode=False)
      
    self.conv2_1 = nn.Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu2_1 = nn.ReLU(inplace)
    self.conv2_2 = nn.Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu2_2 = nn.ReLU(inplace)
    self.pool2 = nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1), ceil_mode=False)
      
    self.conv3_1 = nn.Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu3_1 = nn.ReLU(inplace)
    self.conv3_2 = nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu3_2 = nn.ReLU(inplace)
    self.conv3_3 = nn.Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu3_3 = nn.ReLU(inplace)
    self.pool3 = nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1), ceil_mode=False)
      
    self.conv4_1 = nn.Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu4_1 = nn.ReLU(inplace)
    self.conv4_2 = nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu4_2 = nn.ReLU(inplace)
    self.conv4_3 = nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu4_3 = nn.ReLU(inplace)
    self.pool4 = nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1), ceil_mode=False)
      
    self.conv5_1 = nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu5_1 = nn.ReLU(inplace)
    self.conv5_2 = nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu5_2 = nn.ReLU(inplace)
    self.conv5_3 = nn.Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    self.relu5_3 = nn.ReLU(inplace)
    self.pool5 = nn.MaxPool2d(kernel_size=(2, 2), stride=(2, 2), dilation=(1, 1), ceil_mode=False) 
      
    self.fc6 = nn.Linear(in_features=25088, out_features=4096, bias=True)
    self.relu6 = nn.ReLU(inplace)
    self.drop6 = nn.Dropout(p=0.5)
    
    self.fc7 = nn.Linear(in_features=4096, out_features=4096, bias=True)
    self.relu7 = nn.ReLU(inplace)
    self.drop7 = nn.Dropout(p=0.5)
    self.fc8 = nn.Linear(in_features=4096, out_features=num_classes, bias=True)
      
    self._initialize_weights()
  def forward(self,x):
    out = self.conv1_1(x)
    x_conv1 = out
    out = self.relu1_1(out)
    out = self.conv1_2(out)
    out = self.relu1_2(out)
    out = self.pool1(out)
    x_pool1 = out
    
    out = self.conv2_1(out)
    out = self.relu2_1(out)
    out = self.conv2_2(out)
    out = self.relu2_2(out)
    out = self.pool2(out)
    x_pool2 = out
    
    out = self.conv3_1(out)
    out = self.relu3_1(out)
    out = self.conv3_2(out)
    out = self.relu3_2(out)
    out = self.conv3_3(out)
    out = self.relu3_3(out)
    out = self.pool3(out)
    x_pool3 = out
    
    out = self.conv4_1(out)
    out = self.relu4_1(out)
    out = self.conv4_2(out)
    out = self.relu4_2(out)
    out = self.conv4_3(out)
    out = self.relu4_3(out)
    out = self.pool4(out)
    x_pool4 = out
    
    out = self.conv5_1(out)
    out = self.relu5_1(out)
    out = self.conv5_2(out)
    out = self.relu5_2(out)
    out = self.conv5_3(out)
    out = self.relu5_3(out)
    out = self.pool5(out)
    x_pool5 = out
    
    out = out.view(out.size(0),-1)
    
    out = self.fc6(out)
    out = self.relu6(out)
    out = self.fc7(out)
    out = self.relu7(out)
    out = self.fc8(out)
    
    return out, x_pool1, x_pool2, x_pool3, x_pool4, x_pool5
 
  def _initialize_weights(self):
    for m in self.modules():
      if isinstance(m, nn.Conv2d):
        n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
        m.weight.data.normal_(0, math.sqrt(2. / n))
        if m.bias is not None:
          m.bias.data.zero_()
      elif isinstance(m, nn.BatchNorm2d):
        m.weight.data.fill_(1)
        m.bias.data.zero_()
      elif isinstance(m, nn.Linear):
        m.weight.data.normal_(0, 0.01)
        m.bias.data.zero_()
     
def copy(vgglayers, dstlayer,idx):
  layer = vgglayers[0][idx]
  kernel, bias = layer[0]['weights'][0][0]
  if idx in [33,35]: # fc7, fc8
    kernel = kernel.squeeze()
    dstlayer.weight.data.copy_(torch.from_numpy(kernel.transpose([1,0]))) # matrix format: axb -> bxa
  elif idx == 31: # fc6
    kernel = kernel.reshape(-1,4096)
    dstlayer.weight.data.copy_(torch.from_numpy(kernel.transpose([1,0]))) # matrix format: axb -> bxa
  else:
    dstlayer.weight.data.copy_(torch.from_numpy(kernel.transpose([3,2,1,0]))) # matrix format: axbxcxd -> dxcxbxa
  dstlayer.bias.data.copy_(torch.from_numpy(bias.reshape(-1)))
 
def get_vggface(vgg_path):
  """1. define pytorch model"""   
  model = vgg16_face()   
  
  """2. get pre-trained weights and other params"""     
  #vgg_path = "/home/hy/vgg-face.mat" # download from http://www.vlfeat.org/matconvnet/pretrained/
  vgg_weights = loadmat(vgg_path)
  data = vgg_weights
  meta = data['meta']
  classes = meta['classes']
  class_names = classes[0][0]['description'][0][0]
  normalization = meta['normalization']
  average_image = np.squeeze(normalization[0][0]['averageImage'][0][0][0][0])
  image_size = np.squeeze(normalization[0][0]['imageSize'][0][0])
  layers = data['layers']
  # =============================================================================
  # for idx,layer in enumerate(layers[0]):
  #   name = layer[0]['name'][0][0]
  #   print idx,name
  # """
  # 0 conv1_1
  # 1 relu1_1
  # 2 conv1_2
  # 3 relu1_2
  # 4 pool1
  # 5 conv2_1
  # 6 relu2_1
  # 7 conv2_2
  # 8 relu2_2
  # 9 pool2
  # 10 conv3_1
  # 11 relu3_1
  # 12 conv3_2
  # 13 relu3_2
  # 14 conv3_3
  # 15 relu3_3
  # 16 pool3
  # 17 conv4_1
  # 18 relu4_1
  # 19 conv4_2
  # 20 relu4_2
  # 21 conv4_3
  # 22 relu4_3
  # 23 pool4
  # 24 conv5_1
  # 25 relu5_1
  # 26 conv5_2
  # 27 relu5_2
  # 28 conv5_3
  # 29 relu5_3
  # 30 pool5
  # 31 fc6
  # 32 relu6
  # 33 fc7
  # 34 relu7
  # 35 fc8
  # 36 prob
  # """
  # =============================================================================
  
  """3. load weights to pytorch model"""  
  copy(layers,model.conv1_1,0)
  copy(layers,model.conv1_2,2)
  copy(layers,model.conv2_1,5)
  copy(layers,model.conv2_2,7)
  copy(layers,model.conv3_1,10)
  copy(layers,model.conv3_2,12)
  copy(layers,model.conv3_3,14)
  copy(layers,model.conv4_1,17)
  copy(layers,model.conv4_2,19)
  copy(layers,model.conv4_3,21)
  copy(layers,model.conv5_1,24)
  copy(layers,model.conv5_2,26)
  copy(layers,model.conv5_3,28)
  copy(layers,model.fc6,31)
  copy(layers,model.fc7,33)
  copy(layers,model.fc8,35)
  return model,class_names,average_image,image_size
 
if __name__ == '__main__':
  """test""" 
  vgg_path = "/home/hy/vgg-face.mat" # download from http://www.vlfeat.org/matconvnet/pretrained/ 
  model,class_names,average_image,image_size = get_vggface(vgg_path) 
  imgpath = "/home/hy/e/avg_face.jpg"
  img = sm.imread(imgpath)
  img = sm.imresize(img,[image_size[0],image_size[1]])
  input_arr = np.float32(img)#-average_image # h,w,c
  x = torch.from_numpy(input_arr.transpose((2,0,1))) # c,h,w
  avg = torch.from_numpy(average_image) # 
  avg = avg.view(3,1,1).expand(3,224,224)
  x = x - avg
  x = x.contiguous()
  x = x.view(1, x.size(0), x.size(1), x.size(2))
  x = Variable(x)
  out, x_pool1, x_pool2, x_pool3, x_pool4, x_pool5 = model(x)
#  plt.imshow(x_pool1.data.numpy()[0,45]) # plot

以上这篇把vgg-face.mat权重迁移到pytorch模型示例就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持三水点靠木。

把vgg-face.mat权重迁移到pytorch模型示例

- Author -

美利坚节度使

声明：登载此文出于传递更多信息之目的，并不意味着赞同其观点或证实其描述。

Python 相关文章推荐
浅析python 中__name__ = '__main__' 的作用
Jul 05 Python
Python 中的with关键字使用详解
Sep 11 Python
python获取文件路径、文件名、后缀名的实例
Apr 23 Python
Django中STATIC_ROOT和STATIC_URL及STATICFILES_DIRS浅析
May 08 Python
python skimage 连通性区域检测方法
Jun 21 Python
pip安装py_zipkin时提示的SSL问题对应
Dec 29 Python
python 去除二维数组/二维列表中的重复行方法
Jan 23 Python
使用Python做垃圾分类的原理及实例代码附源码
Jul 02 Python
pandas DataFrame行或列的删除方法的实现示例
Aug 02 Python
python使用配置文件过程详解
Dec 28 Python
Python unittest单元测试框架及断言方法
Apr 15 Python
matplotlib 生成的图像中无法显示中文字符的解决方法
Jun 10 Python
Pytorch 多维数组运算过程的索引处理方式
Dec 27 #Python
Pytorch 之修改Tensor部分值方式
Dec 27 #Python
pytorch 实现tensor与numpy数组转换
Dec 27 #Python
Numpy与Pytorch 矩阵操作方式
Dec 27 #Python
基于python及pytorch中乘法的使用详解
Dec 27 #Python
pytorch:torch.mm()和torch.matmul()的使用
Dec 27 #Python
pytorch点乘与叉乘示例讲解
Dec 27 #Python
哈萨克斯坦购物网站(2) 约旦购物网站(1) C++面试题(199) 冰岛购物网站(1) 保加利亚购物网站(3) 白俄罗斯购物网站(3) 罗马尼亚购物网站(10) JAVA面试题(401) 马耳他购物网站(1) PHP面试题(54)
You might like
提升你网站水平的jQuery插件集合推荐
2011/04/19 Javascript
JavaScript版DateAdd和DateDiff函数代码
2012/03/01 Javascript
触屏中的JavaScript事件分析
2015/02/06 Javascript
Nodejs学习笔记之入门篇
2015/04/16 NodeJs
JavaScript获取页面中超链接数量的方法
2015/11/09 Javascript
jQuery EasyUI Tab 选项卡问题小结
2016/08/16 Javascript
javascript实现的上下无缝滚动效果
2016/09/19 Javascript
基于VUE.JS的移动端框架Mint UI的使用
2017/10/11 Javascript
在React项目中使用Eslint代码检查工具及常见问题
2018/10/10 Javascript
如何手动实现es5中的bind方法详解
2018/12/07 Javascript
详解Vue中组件的缓存
2019/04/20 Javascript
VueCli4项目配置反向代理proxy的方法步骤
2020/05/17 Javascript
JavaScript冒泡算法原理与实现方法深入理解
2020/06/04 Javascript
javascript实现前端分页功能
2020/11/26 Javascript
java直接调用python脚本的例子
2014/02/16 Python
Python 私有函数的实例详解
2017/09/11 Python
在python中pandas读文件,有中文字符的方法
2018/12/12 Python
Python线程池模块ThreadPoolExecutor用法分析
2018/12/28 Python
对PyQt5的输入对话框使用(QInputDialog)详解
2019/06/25 Python
django之使用celery-把耗时程序放到celery里面执行的方法
2019/07/12 Python
对django中foreignkey的简单使用详解
2019/07/28 Python
pygame实现俄罗斯方块游戏（对战篇1）
2019/10/29 Python
Python和Sublime整合过程图示
2019/12/25 Python
input file上传文件样式支持html5的浏览器解决方案
2012/11/14 HTML / CSS
全球工业：Global Industrial
2020/02/01 全球购物
送餐员岗位职责范本
2014/02/21 职场文书
外国人聘用意向书
2014/04/01 职场文书
3的组成教学反思
2014/04/30 职场文书
节约用水的口号
2014/06/20 职场文书
2015年家长学校工作总结
2015/04/22 职场文书
解决Jupyter-notebook不弹出默认浏览器的问题
2021/03/30 Python
MySQL中InnoDB存储引擎的锁的基本使用教程
2021/05/26 MySQL
CSS中Single Div 绘图技巧的实现
2021/06/18 HTML / CSS
基于JavaScript实现省市联动效果
2021/06/22 Javascript
JavaScript正则表达式实现注册信息校验功能
2022/05/30 Java/Android
postgresql中如何执行sql文件
2023/05/08 PostgreSQL