Hi,
I am using the transformer example from https://pytorch.org/tutorials/beginner/transformer_tutorial.html
I noticed that if ‘d_model’ in PositionalEncoding function is an odd number, then it throws an error.
‘*** RuntimeError: The expanded size of the tensor (31) must match the existing size (32) at non-singleton dimension 1. Target sizes: [5000, 31]. Tensor sizes: [5000, 32]’
So, are we supposed to use only even numbered ‘d_dim’ or is it an issue with the function?
Thanks,
Interesting observation! The reason it’s happening is:
pe[:, 0::2] = torch.sin(position * div_term)
pe[:, 1::2] = torch.cos(position * div_term)
Here, torch.sin
is used for the even indexes and torch.cos
is used for the odd indexes of the input dimension (size = d_model). So, if d_model is odd, there will be a dimension size mismatch (division by 2 leaves a remainder).
1 Like
I changed the function like this and removed the error.
class PositionalEncoding(nn.Module):
def __init__(self, d_model, dropout=0.1, max_len=5000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = torch.zeros(max_len, d_model)
position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
pe[:, 0::2] = torch.sin(position * div_term)
if d_model%2 != 0:
pe[:, 1::2] = torch.cos(position * div_term)[:,0:-1]
else:
pe[:, 1::2] = torch.cos(position * div_term)
pe = pe.unsqueeze(0).transpose(0, 1)
self.register_buffer('pe', pe)
def forward(self, x):
x = x + self.pe[:x.size(0), :]
return self.dropout(x)
1 Like
Still not fixed in Pytorch 1.9. If even d_model values are required then this should be an “assert …” line in the code. As it is the error message isn’t helpful