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
举例讲解Python设计模式编程中对抽象工厂模式的运用
Mar 02 Python
python字典DICT类型合并详解
Aug 17 Python
Python pyinotify日志监控系统处理日志的方法
Mar 08 Python
使用Python爬了4400条淘宝商品数据,竟发现了这些“潜规则”
Mar 23 Python
django 解决manage.py migrate无效的问题
May 27 Python
Python shutil模块用法实例分析
Oct 02 Python
python ftplib模块使用代码实例
Dec 31 Python
TensorFlow加载模型时出错的解决方式
Feb 06 Python
python模式 工厂模式原理及实例详解
Feb 11 Python
python GUI库图形界面开发之PyQt5多线程中信号与槽的详细使用方法与实例
Mar 08 Python
Python生成器常见问题及解决方案
Mar 21 Python
基于tf.shape(tensor)和tensor.shape()的区别说明
Jun 30 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
幻读(5) 间隙锁(2) dll(1) 历史记录(1) 经纬度(1) innoDB(3) ctypes(1) MVCC(4) html标准库(1) C/C++(1)
You might like
PHP随机字符串生成代码(包括大小写字母)
2013/06/24 PHP
php读取图片内容并输出到浏览器的实现代码
2013/08/08 PHP
浅析linux下apache服务器的配置和管理
2013/08/10 PHP
php使用pdo连接sqlite3的配置示例
2016/05/27 PHP
浅谈PHP的排列组合(如输入a,b,c 输出他们的全部组合)
2017/03/14 PHP
PHP实现用session来实现记录用户登陆信息
2018/10/15 PHP
url 特殊字符 传递参数解决方法
2010/01/01 Javascript
jquery ajax请求方式与提示用户正在处理请稍等
2014/09/01 Javascript
javascript获取flash版本号的方法
2014/11/20 Javascript
js中跨域方法原理详解
2015/07/19 Javascript
Bootstrap3学习笔记(三)之表格
2016/05/20 Javascript
Laydate时间组件在火狐浏览器下有多时间输入框时只能给第一个输入框赋值的解决方法
2016/08/18 Javascript
Javascript中引用类型传递的知识点小结
2017/03/06 Javascript
Node.js之网络通讯模块实现浅析
2017/04/01 Javascript
Node.js发送HTTP客户端请求并显示响应结果的方法示例
2017/04/12 Javascript
vue服务端渲染的实例代码
2017/08/28 Javascript
详解利用 Vue.js 实现前后端分离的RBAC角色权限管理
2017/09/15 Javascript
Vue自定义弹窗指令的实现代码
2018/08/13 Javascript
微信小程序框架wepy之动态控制类名
2018/09/14 Javascript
python爬虫框架talonspider简单介绍
2017/06/09 Python
Python基于正则表达式实现检查文件内容的方法【文件检索】
2017/08/30 Python
python实现在pandas.DataFrame添加一行
2018/04/04 Python
Python设计模式之迭代器模式原理与用法实例分析
2019/01/10 Python
python,Django实现的淘宝客登录功能示例
2019/06/12 Python
Django错误：TypeError at / 'bool' object is not callable解决
2019/08/16 Python
tensorflow模型继续训练 fineturn实例
2020/01/21 Python
解决python运行效率不高的问题
2020/07/20 Python
python 实现的IP 存活扫描脚本
2020/12/10 Python
HTML5实现锚点时请使用id取代name
2013/09/06 HTML / CSS
毕业生自我推荐
2013/11/04 职场文书
会计学习心得体会
2014/09/09 职场文书
2016年秋季运动会加油稿
2015/12/21 职场文书
如何起草一份正确的合伙创业协议书？
2019/07/04 职场文书
html实现随机点名器的示例代码
2021/04/02 Javascript
面试必问:圣杯布局和双飞翼布局的区别
2021/05/13 HTML / CSS
给numpy.array增加维度的超简单方法
2021/06/02 Python