forked from CVHub520/Convolution
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Deformable Convolution.py
128 lines (102 loc) · 5.34 KB
/
Deformable Convolution.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
from torch.autograd import Variable, Function
import torch
from torch import nn
import numpy as np
# source: https://github.com/ChunhuanLin/deform_conv_pytorch
class DeformConv2D(nn.Module):
def __init__(self, inc, outc, kernel_size=3, padding=1, bias=None):
super(DeformConv2D, self).__init__()
self.kernel_size = kernel_size
self.padding = padding
self.zero_padding = nn.ZeroPad2d(padding)
self.conv_kernel = nn.Conv2d(inc, outc, kernel_size=kernel_size, stride=kernel_size, bias=bias)
def forward(self, x, offset):
dtype = offset.data.type()
ks = self.kernel_size
N = offset.size(1) // 2
# Change offset's order from [x1, x2, ..., y1, y2, ...] to [x1, y1, x2, y2, ...]
# Codes below are written to make sure same results of MXNet implementation.
# You can remove them, and it won't influence the module's performance.
offsets_index = Variable(torch.cat([torch.arange(0, 2*N, 2), torch.arange(1, 2*N+1, 2)]), requires_grad=False).type_as(x).long()
offsets_index = offsets_index.unsqueeze(dim=0).unsqueeze(dim=-1).unsqueeze(dim=-1).expand(*offset.size())
offset = torch.gather(offset, dim=1, index=offsets_index)
# ------------------------------------------------------------------------
if self.padding:
x = self.zero_padding(x)
# (b, 2N, h, w)
p = self._get_p(offset, dtype)
# (b, h, w, 2N)
p = p.contiguous().permute(0, 2, 3, 1)
q_lt = Variable(p.data, requires_grad=False).floor()
q_rb = q_lt + 1
q_lt = torch.cat([torch.clamp(q_lt[..., :N], 0, x.size(2)-1), torch.clamp(q_lt[..., N:], 0, x.size(3)-1)], dim=-1).long()
q_rb = torch.cat([torch.clamp(q_rb[..., :N], 0, x.size(2)-1), torch.clamp(q_rb[..., N:], 0, x.size(3)-1)], dim=-1).long()
q_lb = torch.cat([q_lt[..., :N], q_rb[..., N:]], -1)
q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], -1)
# (b, h, w, N)
mask = torch.cat([p[..., :N].lt(self.padding)+p[..., :N].gt(x.size(2)-1-self.padding),
p[..., N:].lt(self.padding)+p[..., N:].gt(x.size(3)-1-self.padding)], dim=-1).type_as(p)
mask = mask.detach()
floor_p = p - (p - torch.floor(p))
p = p*(1-mask) + floor_p*mask
p = torch.cat([torch.clamp(p[..., :N], 0, x.size(2)-1), torch.clamp(p[..., N:], 0, x.size(3)-1)], dim=-1)
# bilinear kernel (b, h, w, N)
g_lt = (1 + (q_lt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_lt[..., N:].type_as(p) - p[..., N:]))
g_rb = (1 - (q_rb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_rb[..., N:].type_as(p) - p[..., N:]))
g_lb = (1 + (q_lb[..., :N].type_as(p) - p[..., :N])) * (1 - (q_lb[..., N:].type_as(p) - p[..., N:]))
g_rt = (1 - (q_rt[..., :N].type_as(p) - p[..., :N])) * (1 + (q_rt[..., N:].type_as(p) - p[..., N:]))
# (b, c, h, w, N)
x_q_lt = self._get_x_q(x, q_lt, N)
x_q_rb = self._get_x_q(x, q_rb, N)
x_q_lb = self._get_x_q(x, q_lb, N)
x_q_rt = self._get_x_q(x, q_rt, N)
# (b, c, h, w, N)
x_offset = g_lt.unsqueeze(dim=1) * x_q_lt + \
g_rb.unsqueeze(dim=1) * x_q_rb + \
g_lb.unsqueeze(dim=1) * x_q_lb + \
g_rt.unsqueeze(dim=1) * x_q_rt
x_offset = self._reshape_x_offset(x_offset, ks)
out = self.conv_kernel(x_offset)
return out
def _get_p_n(self, N, dtype):
p_n_x, p_n_y = np.meshgrid(range(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1),
range(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1), indexing='ij')
# (2N, 1)
p_n = np.concatenate((p_n_x.flatten(), p_n_y.flatten()))
p_n = np.reshape(p_n, (1, 2*N, 1, 1))
p_n = Variable(torch.from_numpy(p_n).type(dtype), requires_grad=False)
return p_n
@staticmethod
def _get_p_0(h, w, N, dtype):
p_0_x, p_0_y = np.meshgrid(range(1, h+1), range(1, w+1), indexing='ij')
p_0_x = p_0_x.flatten().reshape(1, 1, h, w).repeat(N, axis=1)
p_0_y = p_0_y.flatten().reshape(1, 1, h, w).repeat(N, axis=1)
p_0 = np.concatenate((p_0_x, p_0_y), axis=1)
p_0 = Variable(torch.from_numpy(p_0).type(dtype), requires_grad=False)
return p_0
def _get_p(self, offset, dtype):
N, h, w = offset.size(1)//2, offset.size(2), offset.size(3)
# (1, 2N, 1, 1)
p_n = self._get_p_n(N, dtype)
# (1, 2N, h, w)
p_0 = self._get_p_0(h, w, N, dtype)
p = p_0 + p_n + offset
return p
def _get_x_q(self, x, q, N):
b, h, w, _ = q.size()
padded_w = x.size(3)
c = x.size(1)
# (b, c, h*w)
x = x.contiguous().view(b, c, -1)
# (b, h, w, N)
index = q[..., :N]*padded_w + q[..., N:] # offset_x*w + offset_y
# (b, c, h*w*N)
index = index.contiguous().unsqueeze(dim=1).expand(-1, c, -1, -1, -1).contiguous().view(b, c, -1)
x_offset = x.gather(dim=-1, index=index).contiguous().view(b, c, h, w, N)
return x_offset
@staticmethod
def _reshape_x_offset(x_offset, ks):
b, c, h, w, N = x_offset.size()
x_offset = torch.cat([x_offset[..., s:s+ks].contiguous().view(b, c, h, w*ks) for s in range(0, N, ks)], dim=-1)
x_offset = x_offset.contiguous().view(b, c, h*ks, w*ks)
return x_offset