本篇内容主要讲解“Pytorch:Conv2d卷积前后尺寸怎么设置”，感兴趣的朋友不妨来看看。本文介绍的方法操作简单快捷，实用性强。下面就让小编来带大家学习“Pytorch:Conv2d卷积前后尺寸怎么设置”吧!
Pytorch:Conv2d卷积前后尺寸
Conv2d参数
尺寸变化
卷积前的尺寸为(N,C,W,H) ，卷积后尺寸为(N,F,W_n,H_n)
-
W_n = (W-F+S+2P)/S 向下取整
-
H_n = (H-F+S+2P)/S
示例
# m = nn.Conv2d(16, 33, 3, stride=2)
# non-square kernels and unequal stride and with padding
m = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2))
# non-square kernels and unequal stride and with padding and dilation
# m = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2), dilation=(3, 1))
input = torch.randn(20, 16, 50, 100)
print(input.size())
output = m(input)
print(output.size())反卷积（转置卷积）Conv2DTranspose 输出的尺寸大小
keras的Conv2DTranspose
The size of the input feature map: (N, N)
Conv2dTranspose(kernel_size=k, padding, strides=s)
padding=‘same' ，输出尺寸 = N × s
padding=‘valid'，输出尺寸 = (N-1) × s + k