ComputeDistance

APP_ERROR ComputeDistance(int n, const float16_t *queries, float *distances, unsigned int tableLen = 0, const float *table = nullptr)

Queries the distances between n feature vectors and all feature vectors in the base library. For example, if a valid mapping table (tableLen > 0 and *table is a non-null pointer) is passed, the distance after mapping is output.

int n: number of feature vectors to be queried.

const float16_t *queries: feature vectors to be queried. The length is n x vector dimension dim.

unsigned int tableLen: length of the mapping table. The default value is 0, indicating that no mapping is performed. Currently, the mapping table length can be set to 10000.

const float *table: pointer of the mapping table, pointing to the storage space of valid mapping values with the tableLen length. Currently, the supported redundancy length is 48, that is, the length of the space to which *table points is 10048 x sizeof(float) bytes.

float *distances: external memory, which stores the distance between the query vector and the base library vector.

APP_ERROR: return status. For details, see Return Code Reference.

• n: The value range is [0, capacity].
• *distances: The space length to be provided is n x ntotalPad. (ntotalPad = (ntotal + 15)/16 x 16. That is, the result is 16-padded by ntotal. The valid query comparison distance is stored in the space of the first ntotal. The padded value does not provide any significance.)

  aclrtmalloc is recommended, which can allocate the total physical memory to optimize delay processing.

• If both TableLen and *table meet the requirements during the parameter pass, the API maps the calculated distance.

  First, the distance value is normalized to a floating point number f1 in the range of [0, 1], and then f1 is multiplied by tableLen and rounded up to obtain an integer index between [0, tableLen]. Then, the integer index is used as an offset to obtain the corresponding score from the memory space pointed to by *table. The mapping is completed, and score is saved to *distance .

  The index mapping formula is as follows: ((CosDistance + 1)/2) x tableLen