When I used MithralMatmul, an error occurred. The code I used:
input1 = np.random.rand(3, 4)
input2 = np.random.rand(4)
mm = MithralMatmul(ncodebooks=4)
result = mm(input1, input2)
The error occurs on the following line:
|
def encode_X(self, X): |
|
idxs = clusterize.mithral_encode(X, self.splits_lists) |
|
return idxs + self.offsets |
I'm sorry, but I'm not very familiar with Maddness.
Do you have any suggestions for a solution?