def get_invlist(invlists, l):
""" returns the inverted lists content as a pair of (list_ids, list_codes).
The codes are reshaped to a proper size
"""
invlists = faiss.downcast_InvertedLists(invlists)
ls = invlists.list_size(l)
list_ids = np.zeros(ls, dtype='int64')
ids = codes = None
try:
ids = invlists.get_ids(l)
if ls > 0:
faiss.memcpy(faiss.swig_ptr(list_ids), ids, list_ids.nbytes)
codes = invlists.get_codes(l)
if invlists.code_size != faiss.InvertedLists.INVALID_CODE_SIZE:
list_codes = np.zeros((ls, invlists.code_size), dtype='uint8')
else:
# it's a BlockInvertedLists
npb = invlists.n_per_block
bs = invlists.block_size
ls_round = (ls + npb - 1) // npb
list_codes = np.zeros((ls_round, bs // npb, npb), dtype='uint8')
if ls > 0:
faiss.memcpy(faiss.swig_ptr(list_codes), codes, list_codes.nbytes)
finally:
if ids is not None:
invlists.release_ids(l, ids)
if codes is not None:
invlists.release_codes(l, codes)
return list_ids, list_codes
def test_equiv_pq(self):
ds = datasets.SyntheticDataset(32, 2000, 200, 4)
index = faiss.index_factory(32, "IVF1,PQ16x4np")
index.by_residual = False
# force coarse quantizer
index.quantizer.add(np.zeros((1, 32), dtype='float32'))
index.train(ds.get_train())
index.add(ds.get_database())
Dref, Iref = index.search(ds.get_queries(), 4)
index_pq = faiss.index_factory(32, "PQ16x4np")
index_pq.pq = index.pq
index_pq.is_trained = True
index_pq.codes = faiss.downcast_InvertedLists(
index.invlists).codes.at(0)
index_pq.ntotal = index.ntotal
Dnew, Inew = index_pq.search(ds.get_queries(), 4)
np.testing.assert_array_equal(Iref, Inew)
np.testing.assert_array_equal(Dref, Dnew)
index_pq2 = faiss.IndexPQFastScan(index_pq)
index_pq2.implem = 12
Dref, Iref = index_pq2.search(ds.get_queries(), 4)
index2 = faiss.IndexIVFPQFastScan(index)
index2.implem = 12
Dnew, Inew = index2.search(ds.get_queries(), 4)
np.testing.assert_array_equal(Iref, Inew)
np.testing.assert_array_equal(Dref, Dnew)
def get_ids(invlists, list_no: int):
invlists = faiss.downcast_InvertedLists(invlists)
ls = invlists.list_size(list_no)
list_ids = np.zeros(ls, dtype='int64')
ids = None
origin_ids = None
try:
ids = invlists.get_ids(list_no)
origin_ids = np.array(faiss.rev_swig_ptr(ids, ls))
except Exception as e:
print("get_ids failed ", e)
finally:
if ids is not None:
invlists.release_ids(list_no, ids)
return origin_ids
index = faiss.read_index(
fname, faiss.IO_FLAG_MMAP | faiss.IO_FLAG_READ_ONLY)
except RuntimeError as e:
print('could not load %s: %s' % (fname, e))
return fname, None
print(" %d entries" % index.ntotal)
return fname, index
index0 = None
for _, index in pool.imap(load_index, args.inputs):
if index is None:
continue
index_ivf = faiss.extract_index_ivf(index)
il = faiss.downcast_InvertedLists(index_ivf.invlists)
index_ivf.invlists = None
il.this.own()
ils_dont_dealloc.append(il)
if (args.l0, args.l1) != (0, -1):
print('restricting to lists %d:%d' % (args.l0, args.l1))
# il = faiss.SliceInvertedLists(il, args.l0, args.l1)
il.crop_invlists(args.l0, args.l1)
ils_dont_dealloc.append(il)
ils.push_back(il)
if index0 is None:
index0 = index
print("loaded %d invlists" % ils.size())
def set_prefetch_nthread(self, nt):
for idx in self.indexes:
il = faiss.downcast_InvertedLists(
faiss.extract_index_ivf(idx).invlists)
il.prefetch_nthread
il.prefetch_nthread = nt
