import torch
from torch import nn
class DeformConv2d(nn.Module):
def __init__(self, inc, outc, kernel_size=3, padding=1, stride=1, bias=None, modulation=False):
"""
Args:
modulation (bool, optional): If True, Modulated Defomable Convolution (Deformable ConvNets v2).
modulation 表示 DCNV1还是DCNV2的开关
"""
super(DeformConv2d, self).__init__()
self.kernel_size = kernel_size
self.padding = padding
self.stride = stride
self.zero_padding = nn.ZeroPad2d(padding)
self.conv = nn.Conv2d(inc, outc, kernel_size=kernel_size, stride=kernel_size, bias=bias)
# 用于获取偏置项 卷积核的通道数应该为2xkernel_sizexkernel_size
# 结果为[b,2xkernel_sizexkernel_size,h,w]
self.p_conv = nn.Conv2d(inc, 2*kernel_size*kernel_size, kernel_size=3, padding=1, stride=stride)
# 将权重用0来进行填充
nn.init.constant_(self.p_conv.weight, 0)
self.p_conv.register_backward_hook(self._set_lr)
self.modulation = modulation
if modulation:
self.m_conv = nn.Conv2d(inc, kernel_size*kernel_size, kernel_size=3, padding=1, stride=stride)
nn.init.constant_(self.m_conv.weight, 0)
self.m_conv.register_backward_hook(self._set_lr)
@staticmethod
def _set_lr(module, grad_input, grad_output):
grad_input = (grad_input[i] * 0.1 for i in range(len(grad_input)))
grad_output = (grad_output[i] * 0.1 for i in range(len(grad_output)))
def forward(self, x):
offset = self.p_conv(x)
if self.modulation:
m = torch.sigmoid(self.m_conv(x))
dtype = offset.data.type()
ks = self.kernel_size
N = offset.size(1) // 2
# 原来输入为[1,3,32,32]---->[1,3,34,34]
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 = p.detach().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:]], dim=-1)
q_rt = torch.cat([q_rb[..., :N], q_lt[..., N:]], dim=-1)
# clip p
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
# modulation
if self.modulation:
m = m.contiguous().permute(0, 2, 3, 1)
m = m.unsqueeze(dim=1)
m = torch.cat([m for _ in range(x_offset.size(1))], dim=1)
x_offset *= m
x_offset = self._reshape_x_offset(x_offset, ks)
out = self.conv(x_offset)
return out
def _get_p_n(self, N, dtype):
# 生成卷积核的矩阵
p_n_x, p_n_y = torch.meshgrid(
torch.arange(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1),#[-1,1]
torch.arange(-(self.kernel_size-1)//2, (self.kernel_size-1)//2+1))#[-1,1]
# (2N, 1)
p_n = torch.cat([torch.flatten(p_n_x), torch.flatten(p_n_y)], 0)
p_n = p_n.view(1, 2*N, 1, 1).type(dtype)
# 以卷积核中心为原点，然后生成相对坐标
return p_n
def _get_p_0(self, h, w, N, dtype):
p_0_x, p_0_y = torch.meshgrid(
torch.arange(1, h*self.stride+1, self.stride),
torch.arange(1, w*self.stride+1, self.stride))
p_0_x = torch.flatten(p_0_x).view(1, 1, h, w).repeat(1, N, 1, 1)#相当于在第二个维度上重复N次
p_0_y = torch.flatten(p_0_y).view(1, 1, h, w).repeat(1, N, 1, 1)
p_0 = torch.cat([p_0_x, p_0_y], 1).type(dtype)
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
if __name__ == '__main__':
a=torch.randn(1,3,32,32)
model=DeformConv2d(3,3,3)
out=model(a)
print(out.shape)
import torch.nn as nn
import torch
from deform_conv_v2 import DeformConv2d
class ConvNet(nn.Module):
def __init__(self):
super(ConvNet, self).__init__()
self.relu = nn.ReLU(inplace=True)
self.pool = nn.MaxPool2d((2, 2))
self.avg_pool = nn.AdaptiveAvgPool2d(1)
self.conv1 = nn.Conv2d(3, 32, 3, padding=1)
self.bn1 = nn.BatchNorm2d(32)
self.conv2 = DeformConv2d(32, 64, 3, padding=1, modulation=True)
self.bn2 = nn.BatchNorm2d(64)
self.fc = nn.Linear(64, 10)
def forward(self, x):
x = self.relu(self.bn1(self.conv1(x)))
x = self.pool(x)
x = self.relu(self.bn2(self.conv2(x)))
x = self.avg_pool(x)
x = x.view(x.shape[0], -1)
x = self.fc(x)
return x
if __name__ == '__main__':
a=torch.randn(1,3,32,32)
model=ConvNet()
out=model(a)
print(out.shape)
