def main(imagedir, sim=0.5):
"""Example main app using this library.
Parameters
----------
imagedir : str
path to directory with images
sim : float (0..1)
similarity index (see imagecluster.cluster())
"""
dbfn = pj(imagedir, ic_base_dir, 'fingerprints.pk')
# print("dbfn= " + dbfn)
if not os.path.exists(dbfn):
os.makedirs(os.path.dirname(dbfn), exist_ok=True)
print("no fingerprints database {} found".format(dbfn))
files = co.get_files(imagedir)
model = ic.get_model()
print("running all images through NN model ...".format(dbfn))
fps = ic.fingerprints(files, model, size=(224, 224))
# print(fps)
co.write_pk(fps, dbfn)
else:
print("loading fingerprints database {} ...".format(dbfn))
fps = co.read_pk(dbfn)
print("clustering ...")
print(len(fps))
clusters = ic.cluster(fps, sim)
help(imagedir, clusters)
ic.make_links(ic.cluster(fps, sim), pj(imagedir, ic_base_dir, 'clusters'))
def linkParts(ic_base_dir=ic_base_dir, sim=sim):
"""
Link all divided part by each divided finger-print
:param ic_base_dir:
:param sim:
:return:
"""
for dirpath, dirnames, filenames in os.walk(ic_base_dir):
dircs = dirnames
break
if dircs.__len__() == 0:
print('Try to link images , no former folder found !')
spiltFP(fpdir=fingerPrintDir, ic_base_dir=ic_base_dir)
for dirpath, dirnames, filenames in os.walk(ic_base_dir):
dircs = dirnames
break
i = 0
for f_dir in dircs:
fpdict = co.read_pk(ic_base_dir + '/' + f_dir + '/fingerprints.pk')
print("[dict%d] with %d is clusting [sim=%f]" %
(i, fpdict.__len__(), sim))
ic.make_links(ic.cluster(dict(fpdict), sim, method='average'),
ic_base_dir + '/part' + str(i) + '/cluster')
i += 1
del fpdict
def main(imagedir, processingDir, similarity=.4):
imageFeaturePath = pathJoin(processingDir, 'imagefeatures.pk')
if not os.path.exists(imageFeaturePath):
common.makeDir(imageFeaturePath)
print("No imagefeatures database {} found".format(imageFeaturePath))
files = common.get_files(imagedir)
model = imagecluster.get_model()
fps = imagecluster.fingerprints(files, model, size=(224, 224))
common.write_pk(fps, imageFeaturePath)
else:
print("loading fingerprints database {} ...".format(imageFeaturePath))
fps = common.read_pk(imageFeaturePath)
print("clustering ...")
imagecluster.make_links(imagecluster.cluster(fps, similarity),
pathJoin(imagedir, processingDir, 'clusters'))
def cluster(df, dbfn):
print("> Clustering ...")
fingerprint_column = 'cropped_fingerprints'
sim = 0.5
fingerprintdict = df.set_index('filename')[fingerprint_column].to_dict()
# cluster and save files in folders
ic.make_links(ic.cluster(fingerprintdict, sim), os.path.join(imagedir, ic_base_dir, 'clusters'))
# cluster and save results in dataframe
fps = df[fingerprint_column]
dfps = distance.pdist(np.array(list(fps)), metric='euclidean')
Z = hierarchy.linkage(dfps, method='average', metric='euclidean')
cut = hierarchy.fcluster(Z, t=dfps.max()*(1.0-sim), criterion='distance')
df['cluster'] = cut
# save database to file
co.write_pk(df, dbfn)
print("done.")
def linkTest(ic_base_dir=ic_base_dir, sim=sim):
"""
Random link a divided part by its divided finger-print
:param ic_base_dir:
:param sim:
:return:
"""
for dirpath, dirnames, filenames in os.walk(ic_base_dir):
dircs = dirnames
break
if dircs.__len__() == 0:
print('no former folder found !')
spiltFP()
print('Link test')
f_dir = dircs[random.randint(0, dircs.__len__() - 1)]
fpdict = co.read_pk(ic_base_dir + '/' + f_dir + '/fingerprints.pk')
print("[%s] with %d is clusting " % (f_dir, fpdict.__len__()))
ic.make_links(ic.cluster(dict(fpdict), sim, method='average'),
ic_base_dir + '/' + f_dir + '/cluster')
del fpdict
gc.collect()