class torch.nn.Conv2d(
in_channels,
out_channels,
kernel_size,
stride=1,
padding=0,
dilation=1,
groups=1,
bias=True)
输入: (N,C_in,L_in)
输出: (N,C_out,L_out)
输入输出的计算方式：
Lout=floor((Lin+2padding−dilation(kernerlsize−1)−1)/stride+1)L_{out}=floor((L_{in}+2padding-dilation(kernerl_size-1)-1)/stride+1)
dilation表示卷积核各个元素之间的膨胀大小，间隔大小，默认为1
class torch.nn.MaxPool2d(
kernel_size,
stride=None, #默认值是kernel_size
padding=0,
dilation=1,
return_indices=False,
ceil_mode=False)
shape:
输入: (N,C,H_{in},W_in)
输出: (N,C,H_out,W_out)
Hout=floor((Hin+2padding[0]−dilation[0](kernelsize[0]−1)−1)/stride[0]+1H_{out}=floor((H_{in} + 2padding[0] – dilation[0](kernel_size[0] – 1) – 1)/stride[0] + 1
Wout=floor((Win+2padding[1]−dilation[1](kernelsize[1]−1)−1)/stride[1]+1W_{out}=floor((W_{in} + 2padding[1] – dilation[1](kernel_size[1] – 1) – 1)/stride[1] + 1
