Spatial Average Pooling has same implementation for pooling and unpooling?

[joverwey]

Is this intended?

class S_AvgPool(nn.Module):
    def __init__(self):
        super(S_AvgPool, self).__init__()

    def forward(self, x, M):
        x = torch.einsum('nctv,vw->nctw', x, M)
        return x.contiguous()


class S_AvgUnpool(nn.Module):
    def __init__(self):
        super(S_AvgUnpool, self).__init__()

    def forward(self, x, M):
        x = torch.einsum('nctv,vw->nctw', x, M)
        return x.contiguous()

[soomean]

�It is implemented in this manner just for maintaining consistency with the temporal pooling/unpooling methods, even if both methods require the same operation.

[joverwey]

I see, otherwise you would have to name it AvgPoolOrUnpool, which would be confusing to read. This way you can see the intension while reading the code.