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 get_fp(imagedir,ic_base_dir = 'imagecluster'):
dbfn = pj(ic_base_dir, 'fingerprints.pk')
if os.path.exists(os.path.dirname(dbfn)):
shutil.rmtree(os.path.dirname(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))
co.write_pk(fps, dbfn)
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 spiltFP(fpdir=fingerPrintDir, ic_base_dir=ic_base_dir):
"""
Spilt a large finger-print file to several smaller ones
:param fpdir: The source finger-print file direction
:param ic_base_dir: Divided ones root location
:param spiltnum: The num to spilt the source file
:return: nothing
"""
fps = co.read_pk(fpdir + '/fingerprints.pk')
print('total num of fingerprints : %d' % fps.__len__())
step = stepNum # Pre-set step
len = fps.__len__()
spiltnum = len / step
if spiltnum > 1 and (len - step * (spiltnum - 1)) < step / 2:
spiltnum -= 1
step = math.ceil(len * 1.0 / spiltnum)
dicts = [{}]
i = 0
count = 0
for k, v in fps.items():
dicts[i][k] = v
count += 1
if (count == step):
i += 1
count = 0
dicts.append({})
print('Spilt fps in %d dicts ' % (i + 1))
i = 0
for fpdict in dicts:
fp_newdir = ic_base_dir + '/part' + str(i) + '/fingerprints.pk'
print("[dict%d] has %d element writen in %s " %
(i, fpdict.__len__(), fp_newdir))
if not os.path.exists(ic_base_dir + '/part' + str(i)):
os.makedirs(ic_base_dir + '/part' + str(i))
co.write_pk(fpdict, fp_newdir)
i += 1
del fps, dicts
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 init_df():
# initialize dataframe and run pipeline
dbfn = os.path.join(imagedir, ic_base_dir, 'db.pk')
if not os.path.exists(dbfn):
os.makedirs(os.path.dirname(dbfn), exist_ok=True)
print("no fingerprints database found in {}".format(dbfn))
#fps = ic.fingerprints(files, model, size=(input_size,input_size), modelname=modelname)
df_exists = 'df' in locals() or 'df' in globals()
if not df_exists:
print("Running processing pipeline ...")
df = process_dataset(imagedir)
else:
print("df exists already.")
print("writing {}".format(dbfn))
co.write_pk(df, dbfn)
else:
print("loading fingerprints database {} ...".format(dbfn))
df = co.read_pk(dbfn)
print("done.")
return df, dbfn