Shape error when making out-of-sample predictions

Questions version agnostic
,
8

Replace N_int = np.int64(N.get_value()) by N_int = N.astype("int")

And output = np.ones((N_int,))*factors to output = pm.math.ones((N_int,)) * factors

Can’t you pass dtype="int" directly to pm.MutableData to avoid having to convert it?

1 Like