官方解释:
torch.nn.Conv2d()函数详解
参数详解:
torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)
参数dilation——扩张卷积(也叫空洞卷积)
dilation操作动图演示如下:
Dilated Convolution with a 3 x 3 kernel and dilation rate 2
扩张卷积核为3×3,扩张率为2
参数groups——分组卷积
标签:kernel,函数,nn,卷积,torch,Conv2d,dilation From: https://www.cnblogs.com/yuxiyuxi/p/17016866.html