Convolution - Deconvolution for even and odd size

user_7789027 0
Viewed 503

I have two different size tensors to put in the network.

C = nn.Conv1d(1, 1, kernel_size=1, stride=2)
TC = nn.ConvTranspose1d(1, 1, kernel_size=1, stride=2)

a = torch.rand(1, 1, 100)
b = torch.rand(1, 1, 101)

a_out, b_out = TC(C(a)), TC(C(b))

The results are

a_out = torch.size([1, 1, 99]) # What I want is [1, 1, 100]
b_out = torch.size([1, 1, 101])

Is there any method to handle this problem?
I need your help.
Thanks

deconvolution pytorch convolution
1 Answers

It is expected behaviour as per documentation. May be padding can be used when even input length is detected to get same length as input.

Something like this

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, 1, kernel_size=1, stride=2)
P = PadEven(C, TC)

a = torch.rand(1, 1, 100)
b = torch.rand(1, 1, 101)

a_out, b_out = P(a), P(b)
user_96479510
Related