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
python del()函数用法
Mar 24 Python
简单的Python的curses库使用教程
Apr 11 Python
Python遍历目录的4种方法实例介绍
Apr 13 Python
利用python批量修改word文件名的方法示例
Oct 17 Python
使用pygame模块编写贪吃蛇的实例讲解
Feb 05 Python
Python检测网络延迟的代码
May 15 Python
python实现简单名片管理系统
Nov 30 Python
Python编写带选项的命令行程序方法
Aug 13 Python
python小程序基于Jupyter实现天气查询的方法
Mar 27 Python
Django如何批量创建Model
Sep 01 Python
Python 串口通信的实现
Sep 29 Python
Jupyter Notebook安装及使用方法解析
Nov 12 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
性能优化(3) 缓存(3) 锁(1) 策略(1) 逻辑架构(1) Mysql报错(1) 事务(5) offset(1) mysql.user(1) limit(1)
You might like
php 用checkbox一次性删除多条记录的方法
2010/02/23 PHP
PHP 面向对象详解
2012/09/13 PHP
php利用ob_start()清除输出和选择性输出的方法
2018/01/18 PHP
自适应高度框架 ----属个人收藏内容
2007/01/22 Javascript
JavaScript 直接操作本地文件的实现代码
2009/12/01 Javascript
document.all的一个比较完整的总结及案例
2013/01/31 Javascript
多种方式实现JS调用后台方法进行数据交互
2013/08/20 Javascript
JQuery1.8 判断元素是否绑定事件的方法
2014/07/10 Javascript
一个实用的图片切换支持点击切换和自动轮播
2014/09/09 Javascript
JavaScript bold方法入门实例（把指定文字显示为粗体）
2014/10/17 Javascript
jquery实现Slide Out Navigation滑出式菜单效果代码
2015/09/07 Javascript
javascript实现C语言经典程序题
2015/11/29 Javascript
深入理解bootstrap框架之第二章整体架构
2016/10/09 Javascript
JS中Array数组学习总结
2017/01/18 Javascript
vue.js开发环境搭建教程
2017/05/04 Javascript
js简易版购物车功能
2017/06/17 Javascript
jQuery实现表格冻结顶栏效果
2017/08/20 jQuery
vue-cli3.0+element-ui上传组件el-upload的使用
2018/12/03 Javascript
浅谈js中的bind
2019/03/18 Javascript
element-ui 实现响应式导航栏的示例代码
2020/05/08 Javascript
[51:32]Optic vs Serenity 2018国际邀请赛淘汰赛BO3 第一场 8.22
2018/08/23 DOTA
python实现代码行数统计示例分享
2014/02/10 Python
简单谈谈Python中的反转字符串问题
2016/10/24 Python
彻彻底底地理解Python中的编码问题
2018/10/15 Python
Python Django的安装配置教程图文详解
2019/07/17 Python
Python中实现输入一个整数的案例
2020/05/03 Python
解决keras,val_categorical_accuracy:,0.0000e+00问题
2020/07/02 Python
Python偏函数实现原理及应用
2020/11/20 Python
英国豪华真皮和布艺沙发销售网站：Darlings of Chelsea
2018/01/05 全球购物
介绍一下grep命令的使用
2015/06/12 面试题
仓库管理员岗位职责
2014/03/19 职场文书
新闻传媒系求职信范文
2014/04/19 职场文书
2015年校务公开工作总结
2015/05/26 职场文书
详解MySQL中的pid与socket
2021/06/15 MySQL
详解非极大值抑制算法之Python实现
2021/06/28 Python
MySQL子查询中order by不生效问题的解决方法
2021/08/02 MySQL