人脸检测、人脸定位、人脸对齐、MTCNN、人脸识别(衡量人脸的相似或不同：softmax、三元组损失Triplet Loss、中心损失Center Loss、ArcFace)日萌社

100 阅读 0 评论 66 点赞

我是靠谱客的博主无私皮卡丘，这篇文章主要介绍人脸检测、人脸定位、人脸对齐、MTCNN、人脸识别(衡量人脸的相似或不同：softmax、三元组损失Triplet Loss、中心损失Center Loss、ArcFace)日萌社，现在分享给大家，希望可以做个参考。

日萌社

人工智能AI：Keras PyTorch MXNet TensorFlow PaddlePaddle 深度学习实战（不定时更新）

复制代码

# ArcFace
class ArcMarginProduct(nn.Module):
    r"""Implement of large margin arc distance: :
        Args:
            in_features: size of each input sample
            out_features: size of each output sample
            s: norm of input feature
            m: margin

cos(theta + m)
        """

def __init__(self, in_features, out_features, s=30.0, m=0.50, easy_margin=False):
        super(ArcMarginProduct, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.s = s
        self.m = m
        # 初始化权重
        self.weight = Parameter(torch.FloatTensor(out_features, in_features))
        nn.init.xavier_uniform_(self.weight)

self.easy_margin = easy_margin
        self.cos_m = math.cos(m)
        self.sin_m = math.sin(m)
        self.th = math.cos(math.pi - m)
        self.mm = math.sin(math.pi - m) * m

def forward(self, input, label):
        # cos(theta) & phi(theta)
        # torch.nn.functional.linear(input, weight, bias=None)
        # y=x*W^T+b
        cosine = F.linear(F.normalize(input), F.normalize(self.weight))
        sine = torch.sqrt(1.0 - torch.pow(cosine, 2))
        # cos(a+b)=cos(a)*cos(b)-size(a)*sin(b)
        phi = cosine * self.cos_m - sine * self.sin_m
        if self.easy_margin:
            # torch.where(condition, x, y) → Tensor
            # condition (ByteTensor) – When True (nonzero), yield x, otherwise yield y
            # x (Tensor) – values selected at indices where condition is True
            # y (Tensor) – values selected at indices where condition is False
            # return:
            # A tensor of shape equal to the broadcasted shape of condition, x, y
            # cosine>0 means two class is similar, thus use the phi which make it
            phi = torch.where(cosine > 0, phi, cosine)
        else:
            phi = torch.where(cosine > self.th, phi, cosine - self.mm)
        # convert label to one-hot
        # one_hot = torch.zeros(cosine.size(), requires_grad=True, device='cuda')
        # 将cos(theta + m)更新到tensor相应的位置中
        one_hot = torch.zeros(cosine.size(), device='cuda')
        # scatter_(dim, index, src)
        one_hot.scatter_(1, label.view(-1, 1).long(), 1)
        # torch.where(out_i = {x_i if condition_i else y_i) 
        output = (one_hot * phi) + ((1.0 - one_hot) * cosine)
        output *= self.s

return output

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
# ArcFace
class ArcMarginProduct(nn.Module):
    r"""Implement of large margin arc distance: :
        Args:
            in_features: size of each input sample
            out_features: size of each output sample
            s: norm of input feature
            m: margin

            cos(theta + m)
        """

    def __init__(self, in_features, out_features, s=30.0, m=0.50, easy_margin=False):
        super(ArcMarginProduct, self).__init__()
        self.in_features = in_features
        self.out_features = out_features
        self.s = s
        self.m = m
        # 初始化权重
        self.weight = Parameter(torch.FloatTensor(out_features, in_features))
        nn.init.xavier_uniform_(self.weight)

        self.easy_margin = easy_margin
        self.cos_m = math.cos(m)
        self.sin_m = math.sin(m)
        self.th = math.cos(math.pi - m)
        self.mm = math.sin(math.pi - m) * m

    def forward(self, input, label):
        # cos(theta) & phi(theta)
        # torch.nn.functional.linear(input, weight, bias=None)
        # y=x*W^T+b
        cosine = F.linear(F.normalize(input), F.normalize(self.weight))
        sine = torch.sqrt(1.0 - torch.pow(cosine, 2))
        # cos(a+b)=cos(a)*cos(b)-size(a)*sin(b)
        phi = cosine * self.cos_m - sine * self.sin_m
        if self.easy_margin:
            # torch.where(condition, x, y) → Tensor
            # condition (ByteTensor) – When True (nonzero), yield x, otherwise yield y
            # x (Tensor) – values selected at indices where condition is True
            # y (Tensor) – values selected at indices where condition is False
            # return:
            # A tensor of shape equal to the broadcasted shape of condition, x, y
            # cosine>0 means two class is similar, thus use the phi which make it
            phi = torch.where(cosine > 0, phi, cosine)
        else:
            phi = torch.where(cosine > self.th, phi, cosine - self.mm)
        # convert label to one-hot
        # one_hot = torch.zeros(cosine.size(), requires_grad=True, device='cuda')
        # 将cos(theta + m)更新到tensor相应的位置中
        one_hot = torch.zeros(cosine.size(), device='cuda')
        # scatter_(dim, index, src)
        one_hot.scatter_(1, label.view(-1, 1).long(), 1)
        # torch.where(out_i = {x_i if condition_i else y_i) 
        output = (one_hot * phi) + ((1.0 - one_hot) * cosine)
        output *= self.s

        return output

复制代码

1
2
3
4
5
6
7
8
from PIL import Image
from detector import detect_faces
from visualization_utils import show_results

img = Image.open('some_img.jpg') # modify the image path to yours
bounding_boxes, landmarks = detect_faces(img) # detect bboxes and landmarks for all faces in the image
show_results(img, bounding_boxes, landmarks) # visualize the results

复制代码

1
2
3
4
5
6
7
8
from PIL import Image
from face_dect_recong.align.detector import detect_faces
from face_dect_recong.align.visualization_utils import show_results
%matplotlib inline

img = Image.open('./data/other_my_face/my/my/myf112.jpg') 
bounding_boxes, landmarks = detect_faces(img) # detect bboxes and landmarks for all faces in the image
show_results(img, bounding_boxes, landmarks) # visualize the results

复制代码

1
2
3
4
5
6
7
8
9
from PIL import Image
from face_dect_recong.align.detector import detect_faces
from face_dect_recong.align.visualization_utils import show_results
%matplotlib inline

img = Image.open('./data/other_my_face/others/Woody_Allen/Woody_Allen_0001.jpg') 
bounding_boxes, landmarks = detect_faces(img) 
show_results(img, bounding_boxes, landmarks)

复制代码

1
2
3
4
5
6
7
#对其他人的图像进行检测
%run face_dect_recong/align/face_align.py -source_root './data/other_my_face/others/' -dest_root './data/other_my_face_align/others' -crop_size 128


#对我的图像进行检测
%run face_dect_recong/align/face_align.py -source_root './data/other_my_face/my/' -dest_root './data/other_my_face_align/others/' -crop_size 128

复制代码

1
2
3
4
5
6
7
import matplotlib.pyplot as plt
from matplotlib.image import imread
%matplotlib inline

img=imread('./data/other_my_face_align/others/my/myf112.jpg')
plt.imshow(img)
plt.show

复制代码

1
2
3
img=imread('./data/other_my_face_align/others/Woody_Allen/Woody_Allen_0002.jpg')
plt.imshow(img)
plt.show

复制代码

1
2
3
4
5
6
#删除小于4张的一些人
%run face_dect_recong/balance/remove_lowshot.py -root './data/other_my_face_align/others' -min_num 4

img=imread('./data/dataset/lfw/lfw-align-128/Zico/Zico_0001.jpg')
plt.imshow(img)
plt.show

复制代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
class Config(object):
    env = 'default'
    backbone = 'resnet18'
    classify = 'softmax'
    
    metric = 'arc_margin'
    easy_margin = False
    #是否使用压缩奖惩网络模块（Squeeze-and-Excitation Blocks）
    use_se = False
    loss = 'focal_loss'

    display = False
    finetune = False
 
    lfw_root = '/home/wumg/data/data/other_my_face_align/others'
 
    lfw_test_list = '/home/wumg/data/data/other_my_face_align/others_test_pair.txt'
    test_model_path = '/home/wumg/data/data/dataset/lfw/resnet18_110.pth'
    save_interval = 10

    train_batch_size = 16  # batch size
    test_batch_size = 60

    input_shape = (1, 128, 128)

    optimizer = 'sgd'

    use_gpu = True  # use GPU or not
    gpu_id = '0, 1'
    num_workers = 4  # how many workers for loading data
   
    max_epoch = 2
    lr = 1e-1  # initial learning rate
    lr_step = 10
    lr_decay = 0.95  # when val_loss increase, lr = lr*lr_decay
    weight_decay = 5e-4

复制代码

from __future__ import print_function
import os
import cv2
from models import *
import torch
import torch.nn as nn
import numpy as np
import time
from torch.nn import DataParallel
import torch.utils.model_zoo as model_zoo
import torch.nn.functional as F

model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth'
    }

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)

class BasicBlock(nn.Module):
    expansion = 1

def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

def forward(self, x):
        residual = x

out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

out = self.conv2(out)
        out = self.bn2(out)

if self.downsample is not None:
            residual = self.downsample(x)

out += residual
        out = self.relu(out)

return out
    
class IRBlock(nn.Module):
    expansion = 1

def __init__(self, inplanes, planes, stride=1, downsample=None, use_se=True):
        super(IRBlock, self).__init__()
        self.bn0 = nn.BatchNorm2d(inplanes)
        self.conv1 = conv3x3(inplanes, inplanes)
        self.bn1 = nn.BatchNorm2d(inplanes)
        self.prelu = nn.PReLU()
        self.conv2 = conv3x3(inplanes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride
        self.use_se = use_se
        if self.use_se:
            self.se = SEBlock(planes)

def forward(self, x):
        residual = x
        out = self.bn0(x)
        out = self.conv1(out)
        out = self.bn1(out)
        out = self.prelu(out)

out = self.conv2(out)
        out = self.bn2(out)
        if self.use_se:
            out = self.se(out)

if self.downsample is not None:
            residual = self.downsample(x)

out += residual
        out = self.prelu(out)

return out

class ResNetFace(nn.Module):
    def __init__(self, block, layers, use_se=True):
        self.inplanes = 64
        self.use_se = use_se
        super(ResNetFace, self).__init__()
        self.conv1 = nn.Conv2d(1, 64, kernel_size=3, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.prelu = nn.PReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.bn4 = nn.BatchNorm2d(512)
        self.dropout = nn.Dropout()
        self.fc5 = nn.Linear(512 * 8 * 8, 512)
        self.bn5 = nn.BatchNorm1d(512)

for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.xavier_normal_(m.weight)
            elif isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.xavier_normal_(m.weight)
                nn.init.constant_(m.bias, 0)

def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )
        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample, use_se=self.use_se))
        self.inplanes = planes
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, use_se=self.use_se))

return nn.Sequential(*layers)

def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.prelu(x)
        x = self.maxpool(x)

x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.bn4(x)
        x = self.dropout(x)
        x = x.view(x.size(0), -1)
        x = self.fc5(x)
        x = self.bn5(x)

return x

class ResNet(nn.Module):

def __init__(self, block, layers):
        self.inplanes = 64
        super(ResNet, self).__init__()
        # self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
        #                        bias=False)
        self.conv1 = nn.Conv2d(1, 64, kernel_size=3, stride=1, padding=1,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        # self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0], stride=2)
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.fc5 = nn.Linear(512 * 8 * 8, 512)

for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

return nn.Sequential(*layers)

def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        # x = self.maxpool(x)

x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        # x = nn.AvgPool2d(kernel_size=x.size()[2:])(x)
        # x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc5(x)

return x

def resnet18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
    return model

def resnet_face18(use_se=True, **kwargs):
    model = ResNetFace(IRBlock, [2, 2, 2, 2], use_se=use_se, **kwargs)
    return model

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
from __future__ import print_function
import os
import cv2
from models import *
import torch
import torch.nn as nn
import numpy as np
import time
from torch.nn import DataParallel
import torch.utils.model_zoo as model_zoo
import torch.nn.functional as F

model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth'
    }

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out
    
class IRBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, use_se=True):
        super(IRBlock, self).__init__()
        self.bn0 = nn.BatchNorm2d(inplanes)
        self.conv1 = conv3x3(inplanes, inplanes)
        self.bn1 = nn.BatchNorm2d(inplanes)
        self.prelu = nn.PReLU()
        self.conv2 = conv3x3(inplanes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride
        self.use_se = use_se
        if self.use_se:
            self.se = SEBlock(planes)

    def forward(self, x):
        residual = x
        out = self.bn0(x)
        out = self.conv1(out)
        out = self.bn1(out)
        out = self.prelu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        if self.use_se:
            out = self.se(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.prelu(out)

        return out


class ResNetFace(nn.Module):
    def __init__(self, block, layers, use_se=True):
        self.inplanes = 64
        self.use_se = use_se
        super(ResNetFace, self).__init__()
        self.conv1 = nn.Conv2d(1, 64, kernel_size=3, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.prelu = nn.PReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.bn4 = nn.BatchNorm2d(512)
        self.dropout = nn.Dropout()
        self.fc5 = nn.Linear(512 * 8 * 8, 512)
        self.bn5 = nn.BatchNorm1d(512)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.xavier_normal_(m.weight)
            elif isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.xavier_normal_(m.weight)
                nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )
        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample, use_se=self.use_se))
        self.inplanes = planes
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, use_se=self.use_se))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.prelu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.bn4(x)
        x = self.dropout(x)
        x = x.view(x.size(0), -1)
        x = self.fc5(x)
        x = self.bn5(x)

        return x



class ResNet(nn.Module):

    def __init__(self, block, layers):
        self.inplanes = 64
        super(ResNet, self).__init__()
        # self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
        #                        bias=False)
        self.conv1 = nn.Conv2d(1, 64, kernel_size=3, stride=1, padding=1,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        # self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0], stride=2)
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.fc5 = nn.Linear(512 * 8 * 8, 512)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        # x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        # x = nn.AvgPool2d(kernel_size=x.size()[2:])(x)
        # x = self.avgpool(x)
        x = x.view(x.size(0), -1)
        x = self.fc5(x)

        return x


def resnet18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
    return model

def resnet_face18(use_se=True, **kwargs):
    model = ResNetFace(IRBlock, [2, 2, 2, 2], use_se=use_se, **kwargs)
    return model

复制代码

def get_lfw_list(pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()
    data_list = []
    for pair in pairs:
        splits = pair.split()

if splits[0] not in data_list:
            data_list.append(splits[0])

if splits[1] not in data_list:
            data_list.append(splits[1])
    return data_list

def load_image(img_path):
    image = cv2.imread(img_path, 0)
    if image is None:
        return None
    image = np.dstack((image, np.fliplr(image)))
    image = image.transpose((2, 0, 1))
    image = image[:, np.newaxis, :, :]
    image = image.astype(np.float32, copy=False)
    image -= 127.5
    image /= 127.5
    return image

def get_featurs(model, test_list, batch_size=10):
    images = None
    features = None
    cnt = 0
    for i, img_path in enumerate(test_list):
        image = load_image(img_path)
        if image is None:
            print('read {} error'.format(img_path))

if images is None:
            images = image
        else:
            images = np.concatenate((images, image), axis=0)

if images.shape[0] % batch_size == 0 or i == len(test_list) - 1:
            cnt += 1

data = torch.from_numpy(images)
            data = data.to(device)
            output = model(data)
            output = output.data.cpu().numpy()

fe_1 = output[::2]
            fe_2 = output[1::2]
            feature = np.hstack((fe_1, fe_2))
            # print(feature.shape)

if features is None:
                features = feature
            else:
                features = np.vstack((features, feature))

images = None

return features, cnt

def load_model(model, model_path):
    model_dict = model.state_dict()
    pretrained_dict = torch.load(model_path)
    pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
    model_dict.update(pretrained_dict)
    model.load_state_dict(model_dict)

def get_feature_dict(test_list, features):
    fe_dict = {}
    for i, each in enumerate(test_list):
        # key = each.split('/')[1]
        fe_dict[each] = features[i]
    return fe_dict

def cosin_metric(x1, x2):
    return np.dot(x1, x2) / (np.linalg.norm(x1) * np.linalg.norm(x2))

def cal_accuracy(y_score, y_true):
    y_score = np.asarray(y_score)
    y_true = np.asarray(y_true)
    best_acc = 0
    best_th = 0
    for i in range(len(y_score)):
        th = y_score[i]
        y_test = (y_score >= th)
        acc = np.mean((y_test == y_true).astype(int))
        if acc > best_acc:
            best_acc = acc
            best_th = th

return (best_acc, best_th)

def test_performance(fe_dict, pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()

sims = []
    labels = []
    for pair in pairs:
        splits = pair.split()
        fe_1 = fe_dict[splits[0]]
        fe_2 = fe_dict[splits[1]]
        label = int(splits[2])
        sim = cosin_metric(fe_1, fe_2)

sims.append(sim)
        labels.append(label)

acc, th = cal_accuracy(sims, labels)
    return acc, th

def lfw_test(model, img_paths, identity_list, compair_list, batch_size):
    s = time.time()
    features, cnt = get_featurs(model, img_paths, batch_size=batch_size)
    #print(features.shape)
    t = time.time() - s
    #print('共用时间 {}, average time is {}'.format(t, t / cnt))
    fe_dict = get_feature_dict(identity_list, features)
    acc, th = test_performance(fe_dict, compair_list)
    print('准确率: ', acc, '阀值: ', th)
    return acc

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
def get_lfw_list(pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()
    data_list = []
    for pair in pairs:
        splits = pair.split()

        if splits[0] not in data_list:
            data_list.append(splits[0])

        if splits[1] not in data_list:
            data_list.append(splits[1])
    return data_list


def load_image(img_path):
    image = cv2.imread(img_path, 0)
    if image is None:
        return None
    image = np.dstack((image, np.fliplr(image)))
    image = image.transpose((2, 0, 1))
    image = image[:, np.newaxis, :, :]
    image = image.astype(np.float32, copy=False)
    image -= 127.5
    image /= 127.5
    return image


def get_featurs(model, test_list, batch_size=10):
    images = None
    features = None
    cnt = 0
    for i, img_path in enumerate(test_list):
        image = load_image(img_path)
        if image is None:
            print('read {} error'.format(img_path))

        if images is None:
            images = image
        else:
            images = np.concatenate((images, image), axis=0)

        if images.shape[0] % batch_size == 0 or i == len(test_list) - 1:
            cnt += 1

            data = torch.from_numpy(images)
            data = data.to(device)
            output = model(data)
            output = output.data.cpu().numpy()

            fe_1 = output[::2]
            fe_2 = output[1::2]
            feature = np.hstack((fe_1, fe_2))
            # print(feature.shape)

            if features is None:
                features = feature
            else:
                features = np.vstack((features, feature))

            images = None

    return features, cnt


def load_model(model, model_path):
    model_dict = model.state_dict()
    pretrained_dict = torch.load(model_path)
    pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
    model_dict.update(pretrained_dict)
    model.load_state_dict(model_dict)


def get_feature_dict(test_list, features):
    fe_dict = {}
    for i, each in enumerate(test_list):
        # key = each.split('/')[1]
        fe_dict[each] = features[i]
    return fe_dict


def cosin_metric(x1, x2):
    return np.dot(x1, x2) / (np.linalg.norm(x1) * np.linalg.norm(x2))


def cal_accuracy(y_score, y_true):
    y_score = np.asarray(y_score)
    y_true = np.asarray(y_true)
    best_acc = 0
    best_th = 0
    for i in range(len(y_score)):
        th = y_score[i]
        y_test = (y_score >= th)
        acc = np.mean((y_test == y_true).astype(int))
        if acc > best_acc:
            best_acc = acc
            best_th = th

    return (best_acc, best_th)


def test_performance(fe_dict, pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()

    sims = []
    labels = []
    for pair in pairs:
        splits = pair.split()
        fe_1 = fe_dict[splits[0]]
        fe_2 = fe_dict[splits[1]]
        label = int(splits[2])
        sim = cosin_metric(fe_1, fe_2)

        sims.append(sim)
        labels.append(label)

    acc, th = cal_accuracy(sims, labels)
    return acc, th


def lfw_test(model, img_paths, identity_list, compair_list, batch_size):
    s = time.time()
    features, cnt = get_featurs(model, img_paths, batch_size=batch_size)
    #print(features.shape)
    t = time.time() - s
    #print('共用时间 {}, average time is {}'.format(t, t / cnt))
    fe_dict = get_feature_dict(identity_list, features)
    acc, th = test_performance(fe_dict, compair_list)
    print('准确率: ', acc, '阀值: ', th)
    return acc

复制代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
opt = Config()
model = resnet_face18(opt.use_se)
#采用多GPU的数据并行处理机制
model = DataParallel(model)
#装载预训练模型
model.load_state_dict(torch.load(opt.test_model_path))
model.to(device)

identity_list = get_lfw_list(opt.lfw_test_list)
img_paths = [os.path.join(opt.lfw_root, each) for each in identity_list]

model.eval()
lfw_test(model, img_paths, identity_list, opt.lfw_test_list, opt.test_batch_size)

复制代码

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
#img_path='/home/wumg/data/data/other_my_face_align/others/Wen_Jiabao/Wen_Jiabao_0002.jpg'
img_path='/home/wumg/data/data/other_my_face_align/others/my/myf241.jpg'
#img_path='/home/wumg/data/data/dataset/lfw/lfw-align-128/Wen_Jiabao/Wen_Jiabao_0002.jpg'
image = cv2.imread(img_path, 0)
if image is None:
    print("ok")

image = np.dstack((image, np.fliplr(image)))
image = image.transpose((2, 0, 1))
image = image[:, np.newaxis, :, :]
image = image.astype(np.float32, copy=False)
image -= 127.5
image /= 127.5

image.shape

复制代码

from __future__ import print_function
import os
import cv2
from models import *
import torch
import numpy as np
import time
#from config import Config
from torch.nn import DataParallel

def get_lfw_list(pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()
    data_list = []
    for pair in pairs:
        splits = pair.split()

if splits[0] not in data_list:
            data_list.append(splits[0])

if splits[1] not in data_list:
            data_list.append(splits[1])
    return data_list

if images is None:
            images = image
        else:
            images = np.concatenate((images, image), axis=0)

if images.shape[0] % batch_size == 0 or i == len(test_list) - 1:
            cnt += 1

data = torch.from_numpy(images)
            data = data.to(torch.device("cuda"))
            output = model(data)
            output = output.data.cpu().numpy()

fe_1 = output[::2]
            fe_2 = output[1::2]
            feature = np.hstack((fe_1, fe_2))
            # print(feature.shape)

if features is None:
                features = feature
            else:
                features = np.vstack((features, feature))

images = None

return features, cnt

def get_feature_dict(test_list, features):
    fe_dict = {}
    for i, each in enumerate(test_list):
        # key = each.split('/')[1]
        fe_dict[each] = features[i]
    return fe_dict

def cosin_metric(x1, x2):
    return np.dot(x1, x2) / (np.linalg.norm(x1) * np.linalg.norm(x2))

return (best_acc, best_th)

def test_performance(fe_dict, pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()

sims.append(sim)
        labels.append(label)

acc, th = cal_accuracy(sims, labels)
    return acc, th

def lfw_test(model, img_paths, identity_list, compair_list, batch_size):
    s = time.time()
    features, cnt = get_featurs(model, img_paths, batch_size=batch_size)
    print(features.shape)
    t = time.time() - s
    print('total time is {}, average time is {}'.format(t, t / cnt))
    fe_dict = get_feature_dict(identity_list, features)
    acc, th = test_performance(fe_dict, compair_list)
    print('lfw face verification accuracy: ', acc, 'threshold: ', th)
    return acc

if __name__ == '__main__':

opt = Config()
    if opt.backbone == 'resnet18':
        model = resnet_face18(opt.use_se)
    elif opt.backbone == 'resnet34':
        model = resnet34()
    elif opt.backbone == 'resnet50':
        model = resnet50()

model = DataParallel(model)
    # load_model(model, opt.test_model_path)
    model.load_state_dict(torch.load(opt.test_model_path))
    model.to(torch.device("cuda"))

identity_list = get_lfw_list(opt.lfw_test_list)
    img_paths = [os.path.join(opt.lfw_root, each) for each in identity_list]

model.eval()
    lfw_test(model, img_paths, identity_list, opt.lfw_test_list, opt.test_batch_size)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
from __future__ import print_function
import os
import cv2
from models import *
import torch
import numpy as np
import time
#from config import Config
from torch.nn import DataParallel


def get_lfw_list(pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()
    data_list = []
    for pair in pairs:
        splits = pair.split()

        if splits[0] not in data_list:
            data_list.append(splits[0])

        if splits[1] not in data_list:
            data_list.append(splits[1])
    return data_list


def load_image(img_path):
    image = cv2.imread(img_path, 0)
    if image is None:
        return None
    image = np.dstack((image, np.fliplr(image)))
    image = image.transpose((2, 0, 1))
    image = image[:, np.newaxis, :, :]
    image = image.astype(np.float32, copy=False)
    image -= 127.5
    image /= 127.5
    return image


def get_featurs(model, test_list, batch_size=10):
    images = None
    features = None
    cnt = 0
    for i, img_path in enumerate(test_list):
        image = load_image(img_path)
        if image is None:
            print('read {} error'.format(img_path))

        if images is None:
            images = image
        else:
            images = np.concatenate((images, image), axis=0)

        if images.shape[0] % batch_size == 0 or i == len(test_list) - 1:
            cnt += 1

            data = torch.from_numpy(images)
            data = data.to(torch.device("cuda"))
            output = model(data)
            output = output.data.cpu().numpy()

            fe_1 = output[::2]
            fe_2 = output[1::2]
            feature = np.hstack((fe_1, fe_2))
            # print(feature.shape)

            if features is None:
                features = feature
            else:
                features = np.vstack((features, feature))

            images = None

    return features, cnt


def load_model(model, model_path):
    model_dict = model.state_dict()
    pretrained_dict = torch.load(model_path)
    pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
    model_dict.update(pretrained_dict)
    model.load_state_dict(model_dict)


def get_feature_dict(test_list, features):
    fe_dict = {}
    for i, each in enumerate(test_list):
        # key = each.split('/')[1]
        fe_dict[each] = features[i]
    return fe_dict


def cosin_metric(x1, x2):
    return np.dot(x1, x2) / (np.linalg.norm(x1) * np.linalg.norm(x2))


def cal_accuracy(y_score, y_true):
    y_score = np.asarray(y_score)
    y_true = np.asarray(y_true)
    best_acc = 0
    best_th = 0
    for i in range(len(y_score)):
        th = y_score[i]
        y_test = (y_score >= th)
        acc = np.mean((y_test == y_true).astype(int))
        if acc > best_acc:
            best_acc = acc
            best_th = th

    return (best_acc, best_th)


def test_performance(fe_dict, pair_list):
    with open(pair_list, 'r') as fd:
        pairs = fd.readlines()

    sims = []
    labels = []
    for pair in pairs:
        splits = pair.split()
        fe_1 = fe_dict[splits[0]]
        fe_2 = fe_dict[splits[1]]
        label = int(splits[2])
        sim = cosin_metric(fe_1, fe_2)

        sims.append(sim)
        labels.append(label)

    acc, th = cal_accuracy(sims, labels)
    return acc, th


def lfw_test(model, img_paths, identity_list, compair_list, batch_size):
    s = time.time()
    features, cnt = get_featurs(model, img_paths, batch_size=batch_size)
    print(features.shape)
    t = time.time() - s
    print('total time is {}, average time is {}'.format(t, t / cnt))
    fe_dict = get_feature_dict(identity_list, features)
    acc, th = test_performance(fe_dict, compair_list)
    print('lfw face verification accuracy: ', acc, 'threshold: ', th)
    return acc


if __name__ == '__main__':

    opt = Config()
    if opt.backbone == 'resnet18':
        model = resnet_face18(opt.use_se)
    elif opt.backbone == 'resnet34':
        model = resnet34()
    elif opt.backbone == 'resnet50':
        model = resnet50()

    model = DataParallel(model)
    # load_model(model, opt.test_model_path)
    model.load_state_dict(torch.load(opt.test_model_path))
    model.to(torch.device("cuda"))

    identity_list = get_lfw_list(opt.lfw_test_list)
    img_paths = [os.path.join(opt.lfw_root, each) for each in identity_list]

    model.eval()
    lfw_test(model, img_paths, identity_list, opt.lfw_test_list, opt.test_batch_size)