-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmodel.py
147 lines (119 loc) · 5.05 KB
/
model.py
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
import math
import torch
from torch import nn
from backbone.repvgg import get_RepVGG_func_by_name
import utils
class RepNet6D(nn.Module):
def __init__(self,
backbone_name, backbone_file, deploy,
pretrained=True):
super(RepNet6D, self).__init__()
repvgg_fn = get_RepVGG_func_by_name(backbone_name)
backbone = repvgg_fn(deploy)
if pretrained:
checkpoint = torch.load(backbone_file)
if 'state_dict' in checkpoint:
checkpoint = checkpoint['state_dict']
ckpt = {k.replace('module.', ''): v for k,
v in checkpoint.items()} # strip the names
backbone.load_state_dict(ckpt)
self.layer0, self.layer1, self.layer2, self.layer3, self.layer4 = backbone.stage0, backbone.stage1, backbone.stage2, backbone.stage3, backbone.stage4
self.gap = nn.AdaptiveAvgPool2d(output_size=1)
last_channel = 0
for n, m in self.layer4.named_modules():
if ('rbr_dense' in n or 'rbr_reparam' in n) and isinstance(m, nn.Conv2d):
last_channel = m.out_channels
fea_dim = last_channel
self.linear_reg = nn.Linear(fea_dim, 6)
def forward(self, x):
x = self.layer0(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.gap(x)
x = torch.flatten(x, 1)
x = self.linear_reg(x)
return utils.compute_rotation_matrix_from_ortho6d(x)
class RepNet5D(nn.Module):
def __init__(self,
backbone_name, backbone_file, deploy,
pretrained=True):
super(RepNet5D, self).__init__()
repvgg_fn = get_RepVGG_func_by_name(backbone_name)
backbone = repvgg_fn(deploy)
if pretrained:
checkpoint = torch.load(backbone_file)
if 'state_dict' in checkpoint:
checkpoint = checkpoint['state_dict']
ckpt = {k.replace('module.', ''): v for k,
v in checkpoint.items()} # strip the names
backbone.load_state_dict(ckpt)
self.layer0, self.layer1, self.layer2, self.layer3, self.layer4 = backbone.stage0, backbone.stage1, backbone.stage2, backbone.stage3, backbone.stage4
self.gap = nn.AdaptiveAvgPool2d(output_size=1)
last_channel = 0
for n, m in self.layer4.named_modules():
if ('rbr_dense' in n or 'rbr_reparam' in n) and isinstance(m, nn.Conv2d):
last_channel = m.out_channels
fea_dim = last_channel
self.linear_reg = nn.Linear(fea_dim, 5) # 5
def forward(self, x):
x = self.layer0(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.gap(x)
x = torch.flatten(x, 1)
x = self.linear_reg(x)
return utils.compute_rotation_matrix_from_ortho5d(x)
class Resnet5D(nn.Module):
def __init__(self, block, layers, fc_layers=1):
self.inplanes = 64
super(Resnet5D, self).__init__()
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)
self.linear_reg = nn.Linear(512 * block.expansion, 5)
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_()
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 = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.linear_reg(x)
out = utils.compute_rotation_matrix_from_ortho5d(x)
return out