问题描述
我要在网络中放置两个不同大小的张量。
C = nn.Conv1d(1,1,kernel_size=1,stride=2)
TC = nn.ConvTranspose1d(1,stride=2)
a = torch.rand(1,100)
b = torch.rand(1,101)
a_out,b_out = TC(C(a)),TC(C(b))
结果是
a_out = torch.size([1,99]) # What I want is [1,100]
b_out = torch.size([1,101])
解决方法
根据documentation,这是预期的行为。当检测到偶数输入长度与输入长度相同时,可以使用填充。
类似这样的东西
class PadEven(nn.Module):
def __init__(self,conv,deconv,pad_value=0,padding=(0,1)):
super().__init__()
self.conv = conv
self.deconv = deconv
self.pad = nn.ConstantPad1d(padding=padding,value=pad_value)
def forward(self,x):
nd = x.size(-1)
x = self.deconv(self.conv(x))
if nd % 2 == 0:
x = self.pad(x)
return x
C = nn.Conv1d(1,1,kernel_size=1,stride=2)
TC = nn.ConvTranspose1d(1,stride=2)
P = PadEven(C,TC)
a = torch.rand(1,100)
b = torch.rand(1,101)
a_out,b_out = P(a),P(b)