nn.Conv2d()参数详解

Pytorch中nn.Conv2d()包含9个参数,分别是:

in_channels(int): Number of channels in the input image

out_channels (int): Number of channels produced by the convolution

kernel_size(int or tuple): Size of the convolving kernel

stride (int or tuple, optional): stride of the convolution. Default: 1

padding (int or tuple, optional)Zero-padding added to both sides of the input, Default: 0

padding_mode(string,optional).Accepted values 'zeros' 'circular' 'reflect' and 'replicate' Default:'zeros'

dilation (int or tuple, optional): Spacing between kernel elements. Default: 1

groups (int, optional): Number of blocked connections from input channels to output channels, Default:1

bias(bool, optional): If "True", adds a learnable bias to the output. Default: "True"

前四个参数就是输入通道数输出通道数，卷积核尺寸和步长，只需要知道输入通道数大小等于卷积核通道数大小，输出通道数大小等于卷积核个数即可

padding参数

代表填充形状，输入张量的填充大小。可以是一个整数，表示在输入的高度和宽度的周围添加的零填充的像素数，或者是一个元组 (h, w)，表示在高度和宽度方向上的填充数。默认0填充，就是不填充

padding_mode参数

代表填充内容，可选项有4种：'zeros', 'reflect','replicate' or 'circular'，其默认选项为'zeros'

原始图像为