普通卷积使用nn.Conv2d(),一般还会接上BN和ReLu参数量NNCin*Cout+Cout(如果有bias,相对来说表示
普通卷积
使用nn.Conv2d(),一般还会接上BN和ReLu
参数量NNCin*Cout+Cout(如果有bias,相对来说表示对参数量影响很小,所以后面不考虑)
class ConvBNReLU(nn.Module):
def __init__(self, C_in, C_out, kernel_size, stride, padding, affine=True):
super(ConvBNReLU, self).__init__()
self.op = nn.Sequential(
nn.Conv2d(C_in, C_out, kernel_size, stride=stride, padding=padding, bias=False),
nn.BatchNorm2d(C_out, eps=1e-3, affine=affine),
nn.ReLU(inplace=False)
)
def forward(self, x):
return self.op(x)
深度可分离卷积depthwise separable convolution
卷积操作可以分为NN 的Depthwise卷积(不改变通道数)和11的Pointwise卷积(改变为输出通道数),同样后接BN,ReLU。参数量明显减少
参数量:
NNCin+Cin11*Cout
class SepConv(nn.Module):
def __init__(self, C_in, C_out, kernel_size, stride, padding, affine=True):
super(SepConv, self).__init__()
self.op = nn.Sequential(
nn.ReLU(inplace=False),
nn.Conv2d(C_in, C_in, kernel_size=kernel_size, stride=stride, padding=padding, groups=C_in, bias=False),
nn.Conv2d(C_in, C_out, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(C_out, eps=1e-3, affine=affine)
)
def forward(self, x):
return self.op(x)
空洞卷积dilated convolution
空洞卷积(dilated convolution)是针对图像语义分割问题中下采样会降低图像分辨率、丢失信息而提出的一种卷积思路。利用添加空洞扩大感受野。
参数量不变,但感受野增大(可结合深度可分离卷积实现)
class DilConv(nn.Module):
def __init__(self, C_in, C_out, kernel_size, stride, padding, dilation, affine=True):
super(DilConv, self).__init__()
self.op = nn.Sequential(
nn.ReLU(inplace=False),
nn.Conv2d(C_in, C_in, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups=C_in, bias=False),
nn.Conv2d(C_in, C_out, kernel_size=1, padding=0, bias=False),
nn.BatchNorm2d(C_out, eps=1e-3, affine=affine),
)
def forward(self, x):
return self.op(x)
Identity
这个其实不算卷积操作,但是在实现跨层传递捷径
class Identity(nn.Module):
def __init__(self):
super(Identity, self).__init__()
def forward(self, x):
return x
以上这篇Pytorch实现各种2d卷积示例就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持脚本之家。
Pytorch 2d 卷积