pytorch小tips

torch.nn.Conv2d()

CLASS torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)

x = torch.randn(2,1,7,3)

x
[ batch_size, channels, height_1, width_1 ]
batch_size 一个batch中样例的个数       2
channels 通道数，也就是当前层的深度 1
height_1, 图片的高                                 7
width_1, 图片的宽                                  3

conv = torch.nn.conv2d(1,8,(2,3))

参数：[ channels, output, height_2, width_2 ]

channels, 通道数，和上面保持一致，也就是当前层的深度  1
output 输出的深度                                                                 8
height_2, 过滤器filter的高                                                      2
width_2, 过滤器filter的宽                                                       3