File size: 7,596 Bytes
bd096d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
### Taken from https://github.com/deepinsight/insightface/blob/master/recognition/arcface_torch/backbones/iresnet.py

import os

import torch
from loguru import logger
from torch import nn

__all__ = ['iresnet18', 'iresnet34', 'iresnet50', 'iresnet100', 'iresnet200']


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


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes,
                     out_planes,
                     kernel_size=1,
                     stride=stride,
                     bias=False)


class IBasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None,
                 groups=1, base_width=64, dilation=1):
        super(IBasicBlock, self).__init__()
        if groups != 1 or base_width != 64:
            raise ValueError('BasicBlock only supports groups=1 and base_width=64')
        if dilation > 1:
            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
        self.bn1 = nn.BatchNorm2d(inplanes, eps=1e-05, )
        self.conv1 = conv3x3(inplanes, planes)
        self.bn2 = nn.BatchNorm2d(planes, eps=1e-05, )
        self.prelu = nn.PReLU(planes)
        self.conv2 = conv3x3(planes, planes, stride)
        self.bn3 = nn.BatchNorm2d(planes, eps=1e-05, )
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x
        out = self.bn1(x)
        out = self.conv1(out)
        out = self.bn2(out)
        out = self.prelu(out)
        out = self.conv2(out)
        out = self.bn3(out)
        if self.downsample is not None:
            identity = self.downsample(x)
        out += identity
        return out


class IResNet(nn.Module):
    fc_scale = 7 * 7

    def __init__(self,
                 block, layers, dropout=0, num_features=512, zero_init_residual=False,
                 groups=1, width_per_group=64, replace_stride_with_dilation=None, fp16=False):
        super(IResNet, self).__init__()
        self.fp16 = fp16
        self.inplanes = 64
        self.dilation = 1
        self.block = block
        if replace_stride_with_dilation is None:
            replace_stride_with_dilation = [False, False, False]
        if len(replace_stride_with_dilation) != 3:
            raise ValueError("replace_stride_with_dilation should be None "
                             "or a 3-element tuple, got {}".format(replace_stride_with_dilation))
        self.groups = groups
        self.base_width = width_per_group
        self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(self.inplanes, eps=1e-05)
        self.prelu = nn.PReLU(self.inplanes)
        self.layer1 = self._make_layer(block, 64, layers[0], stride=2)
        self.layer2 = self._make_layer(block,
                                       128,
                                       layers[1],
                                       stride=2,
                                       dilate=replace_stride_with_dilation[0])
        self.layer3 = self._make_layer(block,
                                       256,
                                       layers[2],
                                       stride=2,
                                       dilate=replace_stride_with_dilation[1])
        self.layer4 = self._make_layer(block,
                                       512,
                                       layers[3],
                                       stride=2,
                                       dilate=replace_stride_with_dilation[2])
        self.bn2 = nn.BatchNorm2d(512 * block.expansion, eps=1e-05, )
        self.dropout = nn.Dropout(p=dropout, inplace=True)
        self.fc = nn.Linear(512 * block.expansion * self.fc_scale, num_features)
        self.features = nn.BatchNorm1d(num_features, eps=1e-05)
        nn.init.constant_(self.features.weight, 1.0)
        self.features.weight.requires_grad = False

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.normal_(m.weight, 0, 0.1)
            elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)

        if zero_init_residual:
            for m in self.modules():
                if isinstance(m, IBasicBlock):
                    nn.init.constant_(m.bn2.weight, 0)

    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
        downsample = None
        previous_dilation = self.dilation
        if dilate:
            self.dilation *= stride
            stride = 1
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                conv1x1(self.inplanes, planes * block.expansion, stride),
                nn.BatchNorm2d(planes * block.expansion, eps=1e-05, ),
            )
        layers = []
        layers.append(
            block(self.inplanes, planes, stride, downsample, self.groups,
                  self.base_width, previous_dilation))
        self.inplanes = planes * block.expansion
        for _ in range(1, blocks):
            layers.append(
                block(self.inplanes,
                      planes,
                      groups=self.groups,
                      base_width=self.base_width,
                      dilation=self.dilation))

        return nn.Sequential(*layers)

    def forward(self, x):
        with torch.cuda.amp.autocast(self.fp16):
            x = self.conv1(x)
            x = self.bn1(x)
            x = self.prelu(x)
            x = self.layer1(x)
            x = self.layer2(x)
            x = self.layer3(x)
            x = self.layer4(x)
            x = self.bn2(x)
            x = torch.flatten(x, 1)
            x = self.dropout(x)
        x = self.fc(x.float() if self.fp16 else x)
        x = self.features(x)
        return x


class Arcface(IResNet):
    def __init__(self, pretrained_path=None, **kwargs):
        super(Arcface, self).__init__(IBasicBlock, [3, 13, 30, 3], **kwargs)
        if pretrained_path is not None and os.path.exists(pretrained_path):
            logger.info(f'[Arcface] Initializing from insightface model from {pretrained_path}.')
            self.load_state_dict(torch.load(pretrained_path))
        self.freezer([self.layer1, self.layer2, self.layer3, self.conv1, self.bn1, self.prelu])

    def freezer(self, layers):
        for layer in layers:
            for block in layer.parameters():
                block.requires_grad = False

    def forward(self, images):
        x = self.forward_arcface(images)
        return x

    def forward_arcface(self, x):
        with torch.cuda.amp.autocast(self.fp16):
            ### FROZEN ###
            with torch.no_grad():
                x = self.conv1(x)
                x = self.bn1(x)
                x = self.prelu(x)
                x = self.layer1(x)
                x = self.layer2(x)
                x = self.layer3(x)

            x = self.layer4(x)
            x = self.bn2(x)
            x = torch.flatten(x, 1)
            x = self.dropout(x)
        x = self.fc(x.float() if self.fp16 else x)
        x = self.features(x)
        return x