I’ m runing the code:
te_y = torch.ones([1,4,10]) # torch.Size([1, 4, 10])
operator = torch.tensor([[[1.0, -2.0, 1.0]]]) # torch.Size([1, 1, 3])
torch.nn.functional.conv1d(te_y, operator, padding=1, groups=4)
get the error reporting with:
Given groups=4, expected weight to be at least 4 at dimension 0, but got weight of size [1, 1, 3] instead
But as the docs say:
It should be no error. I want to preform the 1d conv in the each 4 in_channels with the same weight by set the groups as the 4.
In the code you actually pass
groups=1 to nn.functional.conv1d, did you mean to write
Just to clarify, what part of the docs suggest there should be no error? If
in_channels=4, then the 2nd dimension of weight needs to be 2 (=in_channels/groups), in your case it is 1.
For instance, this works:
B = 1 # minibatch
IC = 4 # in-channels
G = 2 # groups
OC = 2 # out-channels, multiple of groups
N = 10 # spatial dimension of orig tensor
W = 3 # spatial dimension of convolution
te_y = torch.ones([B, IC, N])
operator = torch.rand(OC, IC//G, W)
torch.nn.functional.conv1d(te_y, operator, padding=1, groups=G)
tensor([[[2.7952, 4.2234, 4.2234, 4.2234, 4.2234, 4.2234, 4.2234, 4.2234,
[1.9053, 3.6016, 3.6016, 3.6016, 3.6016, 3.6016, 3.6016, 3.6016,
Thanks for your answer! I know how to revised my code. I should to set the out_channel to the 4.
It’s my fault to explain my question wrongly and I have revised the question. I want to perform the 1d conv in the each 4 in_channels with the groups = 4.
Thank you again.