【pytorch】卷积层输出尺寸的计算公式和分组卷积的weight尺寸的计算

参考链接，我真的觉得看官网就是最棒的参考！清清楚楚，明明白白

https://pytorch.org/docs/master/generated/torch.nn.Conv2d.html#torch.nn.Conv2d

 

# 测试一下输出尺寸

# With square kernels and equal stride
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))

print(m.weight.data.size())
input = torch.randn(20, 16, 50, 100)
output = m(input)
print(output.shape)

m = nn.Conv2d(16, 33, 3, stride=2) ====>

torch.Size([33, 16, 3, 3])
torch.Size([20, 33, 24, 49])

 

m = nn.Conv2d(16, 33, (3, 5), stride&