def put_images(imagedir, replace=False):
success_count = 0
filenames = os.listdir(imagedir)
old_hashes = set(cass.get_image_hashes() if not replace else [])
for filename in filenames:
try:
with open(os.path.join(imagedir, filename), "r") as f:
data = f.read()
import StringIO
s = StringIO.StringIO(data)
im = Image.open(s)
im.verify()
except IOError:
print "couldn't load image: %s" % filename
continue
md5hash = hashlib.md5(data).hexdigest()
if md5hash in old_hashes:
continue
# Store the image file indexed by hash
cass.put_image(md5hash, data, metadata={"filename": filename})
success_count += 1
print "Put %s (%s)" % (filename, md5hash)
total = len(list(cass.get_image_hashes()))
print "Successfully put %d images (total %d)" % (success_count, total)
def put_features(feature_str, hashes=None, replace=False):
feature = eval(feature_str, {"imfeat": imfeat})
print ("Feature: %s (%s)" % (feature_str, feature))
# Compute feature on all available images by default
if hashes is None:
hashes = cass.get_image_hashes()
# Optionally try not to replace existing features
if replace:
print "Replacing all existing features for %s" % feature_str
else:
old_hashes = cass.get_feature_hashes(feature_str)
# Get an estimate of the number of images by counting
# FIXME This requires cass to load the whole row, twice
if 1:
print ("Computing feature for %d images" % len(list(cass.get_feature_hashes(feature_str))))
success_count = 0
start_time = time.time()
_hashes = hashes if replace else cass.sorted_iter_diff(hashes, old_hashes)
for md5hash in _hashes:
data = cass.get_imagedata(md5hash)
import StringIO
s = StringIO.StringIO(data)
try:
im = Image.open(s)
im.load()
# Guard for small images that break GIST
if im.size[0] < 10 or im.size[1] < 10 or im.size[0] > 1000 or im.size[1] > 1000:
print (
"Skipping small image (%d, %d) because of \
GIST segfault"
% im.size
)
continue
except IOError:
print "couldn't load image: %s" % md5hash
continue
# FIXME this seems to be necessary for many features
# e.g. imfeat.Moments and imfeat.GIST()
im = im.convert("RGB")
# Only for catching segfaults
print ("hash: ", md5hash)
# Compute the feature
value = imfeat.compute(feature, im)
ret = cass.put_feature_value(feature_str, md5hash, value)
print ("Put feature_value([%s], [%s]): %d" % (feature_str, md5hash, ret))
success_count += 1
stop_time = time.time()
print ("Finished %d features in %.2f seconds" % (success_count, stop_time - start_time))
