File size: 9,874 Bytes
2252f3d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# This script is borrowed from https://github.com/nkolot/SPIN/blob/master/models/hmr.py

import torch
import torch.nn as nn
import torchvision.models.resnet as resnet
import numpy as np
import math
from lib.net.geometry import rot6d_to_rotmat

import logging

logger = logging.getLogger(__name__)

BN_MOMENTUM = 0.1


class Bottleneck(nn.Module):
    """ Redefinition of Bottleneck residual block
        Adapted from the official PyTorch implementation
    """
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super().__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)
        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)
        out = self.relu(out)

        out = self.conv3(out)
        out = self.bn3(out)

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

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

        return out


class ResNet_Backbone(nn.Module):
    """ Feature Extrator with ResNet backbone
    """
    def __init__(self, model='res50', pretrained=True):
        if model == 'res50':
            block, layers = Bottleneck, [3, 4, 6, 3]
        else:
            pass    # TODO

        self.inplanes = 64
        super().__init__()
        npose = 24 * 6
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, 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])
        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.avgpool = nn.AvgPool2d(7, stride=1)

        if pretrained:
            resnet_imagenet = resnet.resnet50(pretrained=True)
            self.load_state_dict(resnet_imagenet.state_dict(), strict=False)
            logger.info('loaded resnet50 imagenet pretrained model')

    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 _make_deconv_layer(self, num_layers, num_filters, num_kernels):
        assert num_layers == len(num_filters), \
            'ERROR: num_deconv_layers is different len(num_deconv_filters)'
        assert num_layers == len(num_kernels), \
            'ERROR: num_deconv_layers is different len(num_deconv_filters)'

        def _get_deconv_cfg(deconv_kernel, index):
            if deconv_kernel == 4:
                padding = 1
                output_padding = 0
            elif deconv_kernel == 3:
                padding = 1
                output_padding = 1
            elif deconv_kernel == 2:
                padding = 0
                output_padding = 0

            return deconv_kernel, padding, output_padding

        layers = []
        for i in range(num_layers):
            kernel, padding, output_padding = _get_deconv_cfg(num_kernels[i], i)

            planes = num_filters[i]
            layers.append(
                nn.ConvTranspose2d(
                    in_channels=self.inplanes,
                    out_channels=planes,
                    kernel_size=kernel,
                    stride=2,
                    padding=padding,
                    output_padding=output_padding,
                    bias=self.deconv_with_bias
                )
            )
            layers.append(nn.BatchNorm2d(planes, momentum=BN_MOMENTUM))
            layers.append(nn.ReLU(inplace=True))
            self.inplanes = planes

        return nn.Sequential(*layers)

    def forward(self, x):

        batch_size = x.shape[0]

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

        x1 = self.layer1(x)
        x2 = self.layer2(x1)
        x3 = self.layer3(x2)
        x4 = self.layer4(x3)

        xf = self.avgpool(x4)
        xf = xf.view(xf.size(0), -1)

        x_featmap = x4

        return x_featmap, xf


class HMR(nn.Module):
    """ SMPL Iterative Regressor with ResNet50 backbone
    """
    def __init__(self, block, layers, smpl_mean_params):
        self.inplanes = 64
        super().__init__()
        npose = 24 * 6
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, 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])
        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.avgpool = nn.AvgPool2d(7, stride=1)
        self.fc1 = nn.Linear(512 * block.expansion + npose + 13, 1024)
        self.drop1 = nn.Dropout()
        self.fc2 = nn.Linear(1024, 1024)
        self.drop2 = nn.Dropout()
        self.decpose = nn.Linear(1024, npose)
        self.decshape = nn.Linear(1024, 10)
        self.deccam = nn.Linear(1024, 3)
        nn.init.xavier_uniform_(self.decpose.weight, gain=0.01)
        nn.init.xavier_uniform_(self.decshape.weight, gain=0.01)
        nn.init.xavier_uniform_(self.deccam.weight, gain=0.01)

        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))
            elif isinstance(m, nn.BatchNorm2d):
                m.weight.data.fill_(1)
                m.bias.data.zero_()

        mean_params = np.load(smpl_mean_params)
        init_pose = torch.from_numpy(mean_params['pose'][:]).unsqueeze(0)
        init_shape = torch.from_numpy(mean_params['shape'][:].astype('float32')).unsqueeze(0)
        init_cam = torch.from_numpy(mean_params['cam']).unsqueeze(0)
        self.register_buffer('init_pose', init_pose)
        self.register_buffer('init_shape', init_shape)
        self.register_buffer('init_cam', init_cam)

    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, init_pose=None, init_shape=None, init_cam=None, n_iter=3):

        batch_size = x.shape[0]

        if init_pose is None:
            init_pose = self.init_pose.expand(batch_size, -1)
        if init_shape is None:
            init_shape = self.init_shape.expand(batch_size, -1)
        if init_cam is None:
            init_cam = self.init_cam.expand(batch_size, -1)

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

        x1 = self.layer1(x)
        x2 = self.layer2(x1)
        x3 = self.layer3(x2)
        x4 = self.layer4(x3)

        xf = self.avgpool(x4)
        xf = xf.view(xf.size(0), -1)

        pred_pose = init_pose
        pred_shape = init_shape
        pred_cam = init_cam
        for i in range(n_iter):
            xc = torch.cat([xf, pred_pose, pred_shape, pred_cam], 1)
            xc = self.fc1(xc)
            xc = self.drop1(xc)
            xc = self.fc2(xc)
            xc = self.drop2(xc)
            pred_pose = self.decpose(xc) + pred_pose
            pred_shape = self.decshape(xc) + pred_shape
            pred_cam = self.deccam(xc) + pred_cam

        pred_rotmat = rot6d_to_rotmat(pred_pose).view(batch_size, 24, 3, 3)

        return pred_rotmat, pred_shape, pred_cam


def hmr(smpl_mean_params, pretrained=True, **kwargs):
    """ Constructs an HMR model with ResNet50 backbone.
    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = HMR(Bottleneck, [3, 4, 6, 3], smpl_mean_params, **kwargs)
    if pretrained:
        resnet_imagenet = resnet.resnet50(pretrained=True)
        model.load_state_dict(resnet_imagenet.state_dict(), strict=False)
    return model