Function Description

The AscendIndexIVFSQC class contains the IVFSQ with dimension reduction algorithms. Two parameters need to be passed to specify the dimension information before and after dimension reduction. The reduced dimension must be divided by the dimension before dimension reduction. The corresponding operators before and after the operation must be generated based on the IVFSQ operator generation method.

It also provides the fuzzy clustering function. Use the fuzzyK and threshold parameters to control the fuzziness before vectors enter the bucket.

• fuzzyK indicates the maximum value of each vector in the bucket. 3 is recommended.
• threshold indicates the threshold for determining whether a vector enters multiple buckets. [1.0, 1.5] is recommended.