File size: 9,687 Bytes
e215925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
from __future__ import division, absolute_import
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.model_zoo as model_zoo

__all__ = ['xception']

pretrained_settings = {
    'xception': {
        'imagenet': {
            'url':
            'http://data.lip6.fr/cadene/pretrainedmodels/xception-43020ad28.pth',
            'input_space': 'RGB',
            'input_size': [3, 299, 299],
            'input_range': [0, 1],
            'mean': [0.5, 0.5, 0.5],
            'std': [0.5, 0.5, 0.5],
            'num_classes': 1000,
            'scale':
            0.8975 # The resize parameter of the validation transform should be 333, and make sure to center crop at 299x299
        }
    }
}


class SeparableConv2d(nn.Module):

    def __init__(
        self,
        in_channels,
        out_channels,
        kernel_size=1,
        stride=1,
        padding=0,
        dilation=1,
        bias=False
    ):
        super(SeparableConv2d, self).__init__()

        self.conv1 = nn.Conv2d(
            in_channels,
            in_channels,
            kernel_size,
            stride,
            padding,
            dilation,
            groups=in_channels,
            bias=bias
        )
        self.pointwise = nn.Conv2d(
            in_channels, out_channels, 1, 1, 0, 1, 1, bias=bias
        )

    def forward(self, x):
        x = self.conv1(x)
        x = self.pointwise(x)
        return x


class Block(nn.Module):

    def __init__(
        self,
        in_filters,
        out_filters,
        reps,
        strides=1,
        start_with_relu=True,
        grow_first=True
    ):
        super(Block, self).__init__()

        if out_filters != in_filters or strides != 1:
            self.skip = nn.Conv2d(
                in_filters, out_filters, 1, stride=strides, bias=False
            )
            self.skipbn = nn.BatchNorm2d(out_filters)
        else:
            self.skip = None

        self.relu = nn.ReLU(inplace=True)
        rep = []

        filters = in_filters
        if grow_first:
            rep.append(self.relu)
            rep.append(
                SeparableConv2d(
                    in_filters,
                    out_filters,
                    3,
                    stride=1,
                    padding=1,
                    bias=False
                )
            )
            rep.append(nn.BatchNorm2d(out_filters))
            filters = out_filters

        for i in range(reps - 1):
            rep.append(self.relu)
            rep.append(
                SeparableConv2d(
                    filters, filters, 3, stride=1, padding=1, bias=False
                )
            )
            rep.append(nn.BatchNorm2d(filters))

        if not grow_first:
            rep.append(self.relu)
            rep.append(
                SeparableConv2d(
                    in_filters,
                    out_filters,
                    3,
                    stride=1,
                    padding=1,
                    bias=False
                )
            )
            rep.append(nn.BatchNorm2d(out_filters))

        if not start_with_relu:
            rep = rep[1:]
        else:
            rep[0] = nn.ReLU(inplace=False)

        if strides != 1:
            rep.append(nn.MaxPool2d(3, strides, 1))
        self.rep = nn.Sequential(*rep)

    def forward(self, inp):
        x = self.rep(inp)

        if self.skip is not None:
            skip = self.skip(inp)
            skip = self.skipbn(skip)
        else:
            skip = inp

        x += skip
        return x


class Xception(nn.Module):
    """Xception.
    
    Reference:
        Chollet. Xception: Deep Learning with Depthwise
        Separable Convolutions. CVPR 2017.

    Public keys:
        - ``xception``: Xception.
    """

    def __init__(
        self, num_classes, loss, fc_dims=None, dropout_p=None, **kwargs
    ):
        super(Xception, self).__init__()
        self.loss = loss

        self.conv1 = nn.Conv2d(3, 32, 3, 2, 0, bias=False)
        self.bn1 = nn.BatchNorm2d(32)

        self.conv2 = nn.Conv2d(32, 64, 3, bias=False)
        self.bn2 = nn.BatchNorm2d(64)

        self.block1 = Block(
            64, 128, 2, 2, start_with_relu=False, grow_first=True
        )
        self.block2 = Block(
            128, 256, 2, 2, start_with_relu=True, grow_first=True
        )
        self.block3 = Block(
            256, 728, 2, 2, start_with_relu=True, grow_first=True
        )

        self.block4 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )
        self.block5 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )
        self.block6 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )
        self.block7 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )

        self.block8 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )
        self.block9 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )
        self.block10 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )
        self.block11 = Block(
            728, 728, 3, 1, start_with_relu=True, grow_first=True
        )

        self.block12 = Block(
            728, 1024, 2, 2, start_with_relu=True, grow_first=False
        )

        self.conv3 = SeparableConv2d(1024, 1536, 3, 1, 1)
        self.bn3 = nn.BatchNorm2d(1536)

        self.conv4 = SeparableConv2d(1536, 2048, 3, 1, 1)
        self.bn4 = nn.BatchNorm2d(2048)

        self.global_avgpool = nn.AdaptiveAvgPool2d(1)
        self.feature_dim = 2048
        self.fc = self._construct_fc_layer(fc_dims, 2048, dropout_p)
        self.classifier = nn.Linear(self.feature_dim, num_classes)

        self._init_params()

    def _construct_fc_layer(self, fc_dims, input_dim, dropout_p=None):
        """Constructs fully connected layer.

        Args:
            fc_dims (list or tuple): dimensions of fc layers, if None, no fc layers are constructed
            input_dim (int): input dimension
            dropout_p (float): dropout probability, if None, dropout is unused
        """
        if fc_dims is None:
            self.feature_dim = input_dim
            return None

        assert isinstance(
            fc_dims, (list, tuple)
        ), 'fc_dims must be either list or tuple, but got {}'.format(
            type(fc_dims)
        )

        layers = []
        for dim in fc_dims:
            layers.append(nn.Linear(input_dim, dim))
            layers.append(nn.BatchNorm1d(dim))
            layers.append(nn.ReLU(inplace=True))
            if dropout_p is not None:
                layers.append(nn.Dropout(p=dropout_p))
            input_dim = dim

        self.feature_dim = fc_dims[-1]

        return nn.Sequential(*layers)

    def _init_params(self):
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(
                    m.weight, mode='fan_out', nonlinearity='relu'
                )
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.BatchNorm1d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.normal_(m.weight, 0, 0.01)
                if m.bias is not None:
                    nn.init.constant_(m.bias, 0)

    def featuremaps(self, input):
        x = self.conv1(input)
        x = self.bn1(x)
        x = F.relu(x, inplace=True)

        x = self.conv2(x)
        x = self.bn2(x)
        x = F.relu(x, inplace=True)

        x = self.block1(x)
        x = self.block2(x)
        x = self.block3(x)
        x = self.block4(x)
        x = self.block5(x)
        x = self.block6(x)
        x = self.block7(x)
        x = self.block8(x)
        x = self.block9(x)
        x = self.block10(x)
        x = self.block11(x)
        x = self.block12(x)

        x = self.conv3(x)
        x = self.bn3(x)
        x = F.relu(x, inplace=True)

        x = self.conv4(x)
        x = self.bn4(x)
        x = F.relu(x, inplace=True)
        return x

    def forward(self, x):
        f = self.featuremaps(x)
        v = self.global_avgpool(f)
        v = v.view(v.size(0), -1)

        if self.fc is not None:
            v = self.fc(v)

        if not self.training:
            return v

        y = self.classifier(v)

        if self.loss == 'softmax':
            return y
        elif self.loss == 'triplet':
            return y, v
        else:
            raise KeyError('Unsupported loss: {}'.format(self.loss))


def init_pretrained_weights(model, model_url):
    """Initialize models with pretrained weights.
    
    Layers that don't match with pretrained layers in name or size are kept unchanged.
    """
    pretrain_dict = model_zoo.load_url(model_url)
    model_dict = model.state_dict()
    pretrain_dict = {
        k: v
        for k, v in pretrain_dict.items()
        if k in model_dict and model_dict[k].size() == v.size()
    }
    model_dict.update(pretrain_dict)
    model.load_state_dict(model_dict)


def xception(num_classes, loss='softmax', pretrained=True, **kwargs):
    model = Xception(num_classes, loss, fc_dims=None, dropout_p=None, **kwargs)
    if pretrained:
        model_url = pretrained_settings['xception']['imagenet']['url']
        init_pretrained_weights(model, model_url)
    return model