def hyrule_vocab_test():
from yael.yutils import load_ext
from os.path import join
import sklearn.cluster
dbdir = ut.truepath('/raid/work/Oxford/')
datadir = dbdir + '/smk_data_iccv_2013/data/'
# Files storing descriptors/geometry for Oxford5k dataset
test_sift_fname = join(datadir, 'oxford_sift.uint8')
# test_nf_fname = join(datadir, 'oxford_nsift.uint32')
all_vecs = load_ext(test_sift_fname, ndims=128,
verbose=True).astype(np.float32)
logger.info(ut.print_object_size(all_vecs))
# nfeats_list = load_ext(test_nf_fname, verbose=True)
with ut.embed_on_exception_context:
rng = np.random.RandomState(13421421)
# init_size = int(config['num_words'] * 8)
num_words = int(2**16)
init_size = num_words * 4
# converged after 26043 iterations
minibatch_params = dict(
n_clusters=num_words,
init='k-means++',
# init='random',
init_size=init_size,
n_init=1,
max_iter=100,
batch_size=1000,
tol=0.0,
max_no_improvement=10,
reassignment_ratio=0.01,
)
clusterer = sklearn.cluster.MiniBatchKMeans(compute_labels=False,
random_state=rng,
verbose=1,
**minibatch_params)
clusterer.fit(all_vecs)
words = clusterer.cluster_centers_
logger.info(words.shape)
def load_oxford_2013():
"""
Found this data in README of SMK publication
https://hal.inria.fr/hal-00864684/document
http://people.rennes.inria.fr/Herve.Jegou/publications.html
with download script
CommandLine:
# Download oxford13 data
cd ~/work/Oxford
mkdir -p smk_data_iccv_2013
cd smk_data_iccv_2013
wget -nH --cut-dirs=4 -r -Pdata/ ftp://ftp.irisa.fr/local/texmex/corpus/iccv2013/
This dataset has 5063 images wheras 07 has 5062
This dataset seems to contain an extra junk image:
ashmolean_000214
# Remember that matlab is 1 indexed!
# DONT FORGET TO CONVERT TO 0 INDEXING!
"""
from yael.ynumpy import fvecs_read
from yael.yutils import load_ext
import scipy.io
import vtool as vt
from os.path import join
dbdir = ut.truepath('/raid/work/Oxford/')
datadir = dbdir + '/smk_data_iccv_2013/data/'
# we are not retraining, so this is unused
# # Training data descriptors for Paris6k dataset
# train_sift_fname = join(datadir, 'paris_sift.uint8') # NOQA
# # File storing visual words of Paris6k descriptors used in our ICCV paper
# train_vw_fname = join(datadir, 'clust_preprocessed/oxford_train_vw.int32')
# Pre-learned quantizer used in ICCV paper (used if docluster=false)
codebook_fname = join(datadir, 'clust_preprocessed/oxford_codebook.fvecs')
# Files storing descriptors/geometry for Oxford5k dataset
test_sift_fname = join(datadir, 'oxford_sift.uint8')
test_geom_fname = join(datadir, 'oxford_geom_sift.float')
test_nf_fname = join(datadir, 'oxford_nsift.uint32')
# File storing visual words of Oxford5k descriptors used in our ICCV paper
test_vw_fname = join(datadir, 'clust_preprocessed/oxford_vw.int32')
# Ground-truth for Oxford dataset
gnd_fname = join(datadir, 'gnd_oxford.mat')
oxford_vecs = load_ext(test_sift_fname, ndims=128, verbose=True)
oxford_nfeats = load_ext(test_nf_fname, verbose=True)
oxford_words = fvecs_read(codebook_fname)
oxford_wids = load_ext(test_vw_fname, verbose=True) - 1
test_geom_invV_fname = test_geom_fname + '.invV.pkl'
try:
all_kpts = ut.load_data(test_geom_invV_fname)
logger.info('loaded invV keypoints')
except IOError:
oxford_kptsZ = load_ext(test_geom_fname, ndims=5, verbose=True)
logger.info('converting to invV keypoints')
all_kpts = vt.convert_kptsZ_to_kpts(oxford_kptsZ)
ut.save_data(test_geom_invV_fname, all_kpts)
gnd_ox = scipy.io.loadmat(gnd_fname)
imlist = [x[0][0] for x in gnd_ox['imlist']]
qx_to_dx = gnd_ox['qidx'] - 1
data_uri_order = imlist
query_uri_order = ut.take(data_uri_order, qx_to_dx)
offset_list = np.hstack(([0], oxford_nfeats.cumsum())).astype(np.int64)
# query_gnd = gnd_ox['gnd'][0][0]
# bboxes = query_gnd[0]
# qx_to_ok_gtidxs1 = [x[0] for x in query_gnd[1][0]]
# qx_to_junk_gtidxs2 = [x[0] for x in query_gnd[2][0]]
# # ut.depth_profile(qx_to_gtidxs1)
# # ut.depth_profile(qx_to_gtidxs2)
assert sum(oxford_nfeats) == len(oxford_vecs)
assert offset_list[-1] == len(oxford_vecs)
assert len(oxford_wids) == len(oxford_vecs)
assert oxford_wids.max() == len(oxford_words) - 1
data = {
'offset_list': offset_list,
'all_kpts': all_kpts,
'all_vecs': oxford_vecs,
'words': oxford_words,
'idx_to_wx': oxford_wids,
'data_uri_order': data_uri_order,
'query_uri_order': query_uri_order,
}
return data