t.py

import numpy as np
import time
import faiss
import os

#################################################################
# I/O functions
#################################################################

def ivecs_read(fname):
    a = np.fromfile(fname, dtype='int32')
    d = a[0]
    return a.reshape(-1, d + 1)[:, 1:].copy()

def fvecs_read(fname):
    return ivecs_read(fname).view('float32')


#################################################################
#  Main program
#################################################################

print "load data"

xt = fvecs_read("sift1M/sift_learn.fvecs")
xb = fvecs_read("sift1M/sift_base.fvecs")
xq = fvecs_read("sift1M/sift_query.fvecs")

nq, d = xq.shape

print "load GT"
gt = ivecs_read("sift1M/sift_groundtruth.ivecs")

# we need only a StandardGpuResources per GPU
res = faiss.StandardGpuResources()


#################################################################
#  Approximate search experiment
#################################################################

print "============ Approximate search"

co = faiss.GpuClonerOptions()

# here we are using a 64-byte PQ, so we must set the lookup tables to
# 16 bit float (this is due to the limited temporary memory).
co.useFloat16 = True
co.usePrecomputed = False

populated_index_path = 'index'

if os.path.exists(populated_index_path):
    print 'loading', populated_index_path
    index = faiss.read_index(populated_index_path)    # error happens here
    index = faiss.index_cpu_to_gpu(res, 0, index, co)
else:
    index = faiss.index_factory(d, "IVF4096,PQ64")

    # faster, uses more memory
    # index = faiss.index_factory(d, "IVF16384,Flat")

    index = faiss.index_cpu_to_gpu(res, 0, index, co)

    print "train"

    index.train(xt)

    print "add vectors to index"

    index.add(xb)

    print "save index"
    index_cpu = faiss.index_gpu_to_cpu(index)
    faiss.write_index(index_cpu, populated_index_path)

print "warmup"

index.search(xq, 123)

print "benchmark"

for lnprobe in range(10):
    nprobe = 1 << lnprobe
    index.setNumProbes(nprobe)
    t0 = time.time()
    D, I = index.search(xq, 100)
    t1 = time.time()

    print "nprobe=%4d %.3f s recalls=" % (nprobe, t1 - t0),
    for rank in 1, 10, 100:
        n_ok = (I[:, :rank] == gt[:, :1]).sum()
        print "%.4f" % (n_ok / float(nq)),
    print