溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
最近使用pytorch時，需要用到一個預訓練好的人臉識別模型提取人臉ID特征，想到很多人都在用用vgg-face，但是vgg-face沒有pytorch的模型，于是寫個vgg-face.mat轉到pytorch模型的代碼
#!/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
以上這篇把vgg-face.mat權重遷移到pytorch模型示例就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支持億速云。
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
