-
Notifications
You must be signed in to change notification settings - Fork 50
/
model.py
156 lines (122 loc) · 5.65 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
148
149
150
151
152
153
154
155
156
import torch
import torch.nn as nn
import torch.nn.functional as F
def get_n_params(model):
pp=0
for p in list(model.parameters()):
nn=1
for s in list(p.size()):
nn = nn*s
pp += nn
return pp
class MHSA(nn.Module):
def __init__(self, n_dims, width=14, height=14, heads=4):
super(MHSA, self).__init__()
self.heads = heads
self.query = nn.Conv2d(n_dims, n_dims, kernel_size=1)
self.key = nn.Conv2d(n_dims, n_dims, kernel_size=1)
self.value = nn.Conv2d(n_dims, n_dims, kernel_size=1)
self.rel_h = nn.Parameter(torch.randn([1, heads, n_dims // heads, 1, height]), requires_grad=True)
self.rel_w = nn.Parameter(torch.randn([1, heads, n_dims // heads, width, 1]), requires_grad=True)
self.softmax = nn.Softmax(dim=-1)
def forward(self, x):
n_batch, C, width, height = x.size()
q = self.query(x).view(n_batch, self.heads, C // self.heads, -1)
k = self.key(x).view(n_batch, self.heads, C // self.heads, -1)
v = self.value(x).view(n_batch, self.heads, C // self.heads, -1)
content_content = torch.matmul(q.permute(0, 1, 3, 2), k)
content_position = (self.rel_h + self.rel_w).view(1, self.heads, C // self.heads, -1).permute(0, 1, 3, 2)
content_position = torch.matmul(content_position, q)
energy = content_content + content_position
attention = self.softmax(energy)
out = torch.matmul(v, attention.permute(0, 1, 3, 2))
out = out.view(n_batch, C, width, height)
return out
class Bottleneck(nn.Module):
expansion = 4
def __init__(self, in_planes, planes, stride=1, heads=4, mhsa=False, resolution=None):
super(Bottleneck, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
if not mhsa:
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1, stride=stride, bias=False)
else:
self.conv2 = nn.ModuleList()
self.conv2.append(MHSA(planes, width=int(resolution[0]), height=int(resolution[1]), heads=heads))
if stride == 2:
self.conv2.append(nn.AvgPool2d(2, 2))
self.conv2 = nn.Sequential(*self.conv2)
self.bn2 = nn.BatchNorm2d(planes)
self.conv3 = nn.Conv2d(planes, self.expansion * planes, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(self.expansion * planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = F.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
out += self.shortcut(x)
out = F.relu(out)
return out
# reference
# https://github.com/kuangliu/pytorch-cifar/blob/master/models/resnet.py
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=1000, resolution=(224, 224), heads=4):
super(ResNet, self).__init__()
self.in_planes = 64
self.resolution = list(resolution)
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
# self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
if self.conv1.stride[0] == 2:
self.resolution[0] /= 2
if self.conv1.stride[1] == 2:
self.resolution[1] /= 2
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) # for ImageNet
if self.maxpool.stride == 2:
self.resolution[0] /= 2
self.resolution[1] /= 2
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2, heads=heads, mhsa=True)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Sequential(
nn.Dropout(0.3), # All architecture deeper than ResNet-200 dropout_rate: 0.2
nn.Linear(512 * block.expansion, num_classes)
)
def _make_layer(self, block, planes, num_blocks, stride=1, heads=4, mhsa=False):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for idx, stride in enumerate(strides):
layers.append(block(self.in_planes, planes, stride, heads, mhsa, self.resolution))
if stride == 2:
self.resolution[0] /= 2
self.resolution[1] /= 2
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = self.relu(self.bn1(self.conv1(x)))
out = self.maxpool(out) # for ImageNet
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = self.avgpool(out)
out = torch.flatten(out, 1)
out = self.fc(out)
return out
def ResNet50(num_classes=1000, resolution=(224, 224), heads=4):
return ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, resolution=resolution, heads=heads)
def main():
x = torch.randn([2, 3, 224, 224])
model = ResNet50(resolution=tuple(x.shape[2:]), heads=8)
print(model(x).size())
print(get_n_params(model))
# if __name__ == '__main__':
# main()