cosine_scores defined in biencoder.py does not work

[xhluca]

Reference:

DPR/dpr/models/biencoder.py

Line 57 in d9f3e41

def cosine_scores(q_vector: T, ctx_vectors: T):

F.cosine_similarity will fail to compute the similarity along a specified dimension when the other dimensions differ. For example, if x is a 10x64 tensor, and y is a 20x64 tensor, then it is expected to get a 10x20 matrix when calling cosine_scores. However, that function won't work:

>>> x = torch.randn(10, 64)
>>> y = torch.randn(20, 64)
>>> F.cosine_similarity(x, y, dim=1)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
RuntimeError: The size of tensor a (10) must match the size of tensor b (20) at non-singleton dimension 0

Since it is not used anywhere else in the repo and the paper, maybe it would be a good idea to remove cosine_scores?