tic_toc_print('Working on %s (%d/%d)' % (impath, qcurcount+1, len(qimgs)))
h = hashes[qid]
D = scipy.spatial.distance.cdist(h[np.newaxis, :], hashes, 'hamming')
m = np.argsort(D)
top_matches = m[0, :nResort]
if args['considerRadius'] > 0:
top_matches = np.unique(np.concatenate((top_matches,
np.arange(qid, qid-args['considerRadius'], -1),
np.arange(qid, qid+args['considerRadius'], 1)), axis=0))
tic_toc_print('Re-ranking %d images' % len(top_matches))
actFeat = []
for tm in top_matches.tolist():
try:
feat = load_feat(os.path.join(args['featdir'], imgslist[tm] + '.h5'))
feat_dim = np.shape(feat)[0]
except:
sys.stderr.write('Unable to read feature from %s' % imgslist[tm])
feat = np.zeros((feat_dim, 1))
actFeat.append(feat)
actFeat = np.squeeze(np.array(actFeat))
# the top feature is not necessarily the one I want, so can't just take actFeat[0] (multiple could have hamming 0)
try:
qFeat = load_feat(os.path.join(args['featdir'], impath + '.h5')).reshape((1,-1))
except:
sys.stderr.write('Unable to read QUERY feature from %s' % imname)
qFeat = np.zeros((feat_dim, 1))
D2 = scipy.spatial.distance.cdist(qFeat, actFeat, 'cosine')
m2 = np.argsort(D2)
final = zip(imgslist_np[top_matches[m2]].tolist()[0], D2[0,m2].astype('float').tolist()[0]) # always store as 1-indexed
with h5py.File(args["paramfile"], "r") as f:
R = f["R"].value
pc = f["pc"].value
mean = f["mean"].value
if os.path.exists(args["outpath"]):
print("Reading the existing features")
with h5py.File(args["outpath"], "r") as f:
allhashes = f["hashes"].value.tolist()
else:
allhashes = []
nDone = len(allhashes)
for i in range(nDone, len(imgslist)):
impath = imgslist[i]
tic_toc_print("Done %d / %d features" % (i, len(imgslist)))
try:
featpath = os.path.join(args["dir"], impath + ".h5")
feat = load_feat(featpath, args["fracfeat"]).transpose()
# Normalize this feature (that's how its used in training)
feat = feat / np.linalg.norm(feat)
hash = ITQ.hash(feat, pc, mean, R)
allhashes.append(hash)
except:
continue
allhashes = np.squeeze(np.array(allhashes)).astype("bool")
with h5py.File(args["outpath"], "w") as f:
f.create_dataset("hashes", data=allhashes, compression="gzip", compression_opts=9)
outfpath = args['outpath']
if not outfpath.endswith('.h5'):
outfpath += '.h5'
with open(args['list']) as f:
imgslist = f.read().splitlines()
random.shuffle(imgslist)
nFeat = args['numfeat']
allfeats = []
for impath in imgslist:
tic_toc_print('Read %d features' % len(allfeats))
try:
featpath = os.path.join(args['dir'], impath + '.h5')
feat = load_feat(featpath, args['featfrac']).transpose()
allfeats.append(feat)
except Exception, e:
tic_toc_print(e)
continue
if len(allfeats) >= nFeat:
break
allfeats = np.squeeze(np.array(allfeats)).astype(np.float64)
allfeats[np.isnan(allfeats)] = 0
allfeats[np.isinf(allfeats)] = 0
# V.IMP to normalize each row by L2 norm, else mean/PCA etc calculations get screwed due to overflows
norms = np.sum(np.abs(allfeats)**2,axis=-1)**(1./2)
allfeats = allfeats / norms[:, np.newaxis]