Error of dimmensions while upsampling in class Unet1D

[anshumansinha16]

I am getting the following error in the upsampling of class Unet1D : x = torch.cat((x, h.pop()), dim = 1) . Is it related to conditional generation? If yes, then where exactly we give the condition? I have a (1,15) dim 1D input and (1) dim condition.

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
[<ipython-input-145-f3b72fab93a4>](https://localhost:8080/#) in <cell line: 1>()
     13           continue
     14 
---> 15         z = unet(batch_noisy, t)
     16 
     17         predicted_noise = z

1 frames
[<ipython-input-139-5da71058ec56>](https://localhost:8080/#) in forward(self, x, time, x_self_cond)
    118             print(h[len(h)-1])
    119 
--> 120             x = torch.cat((x, h.pop()), dim = 1)
    121             x = block1(x, t)
    122 

RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 2 but got size 3 for tensor number 1 in the list.

[Adversarian]

Are you referring to x_self_cond? Because I can't find a label condition under Unet1D. If so, it appears according to line 348 here, if x_self_cond is not None, its shape must match that of your input x.

[yysxiaoyu]

I have the same question, do you solve it? If so, plz tell me how can I fix the problem.