def subjectset(self, wordnetid):
"""Iterator for single subject"""
assert wordnetid in self.wordnetid_to_name().keys(
), 'Invalid wordnetid "%s"' % wordnetid
d = os.path.join(self.datadir, wordnetid)
for f in imlist(d):
yield ImageDetection(filename=f, category=filebase(d))
def dataset(self):
"""Return a generator to iterate over dataset"""
for d in dirlist(os.path.join(self.datadir, 'images')):
for f in imlist(d):
im = ImageDetection(filename=f, category=filebase(d))
im = im.boundingbox(xmin=float(im.width() - 256) / 2.0,
ymin=float(im.height() - 256.0) / 2.0,
xmax=256.0 + ((im.width() - 256.0) / 2.0),
ymax=256.0 + ((im.height() - 256.0) / 2.0))
im = im.boundingbox(dilate=0.875) # central 224x224
yield im
def take(self, n, wordnetid=None):
"""Randomly select n images from the dataset, or n images of a given subjectid"""
subjectid = np.random.choice(
self.subjects(), n) if wordnetid is None else [wordnetid] * n
takelist = []
for s in subjectid:
d = os.path.join(self.datadir, s)
f = np.random.choice(imlist(d), 1)[0]
im = ImageDetection(filename=f).category(filebase(d))
takelist.append(im)
return takelist
def take_per_subject(self, n):
"""Randomly select n images per subject from the dataset"""
subjectid = self.subjects()
takelist = []
for s in subjectid:
d = os.path.join(self.datadir, s)
for k in range(0, n):
f = np.random.choice(imlist(d), 1)[0]
im = ImageDetection(filename=f).category(filebase(d))
takelist.append(im)
return takelist
def videos(self, subject):
videos = {}
for d in dirlist(os.path.join(self.ytfdir, 'frame_images_DB',
subject)):
k_videoindex = filetail(d)
videos[k_videoindex] = []
for f in imlist(d):
videos[k_videoindex].append(
ImageCategory(filename=f, category=subject))
videos[k_videoindex] = sorted(videos[k_videoindex],
key=lambda im: im.filename())
return videos
def take(self, n):
S = np.random.choice(self.subjects(), n)
takelist = []
for d in dirlist(os.path.join(self.datadir, 'images')):
if filebase(d) in S:
f = np.random.choice(imlist(d), 1)[0]
im = ImageDetection(filename=f, category=filebase(d))
im = im.boundingbox(xmin=float(im.width() - 256) / 2.0,
ymin=float(im.height() - 256.0) / 2.0,
xmax=256.0 + ((im.width() - 256.0) / 2.0),
ymax=256.0 + ((im.height() - 256.0) / 2.0))
im = im.boundingbox(dilate=0.875) # central 224x224
takelist.append(im)
return takelist
def _trainset(self):
"""Save a csv file containing each image on a line for Megaface_Challenge_1M_disjoint_LOOSE.tar.gz"""
outfile = os.path.join(self.datadir,
'Megaface_Challenge_1M_disjoint_LOOSE.csv')
subdir = os.path.join(self.datadir,
'Megaface_Challenge_1M_disjoint_LOOSE')
D = dirlist(subdir)
filelist = []
for (k, d) in enumerate(D):
print('[MF2.trainset][%d/%d]: creating image list for "%s"' %
(k, len(D), d))
for f in imlist(d):
filelist.append((f, filebase(d)))
return writecsv(filelist, outfile)
def _imagelist(self):
"""Save a csv file containing each image on a line"""
if os.path.exists(os.path.join(self.datadir, 'megaface.csv')):
return (os.path.join(self.datadir, 'megaface.csv'))
else:
outfile = os.path.join(self.datadir, 'megaface.csv')
with open(outfile, 'w') as csv:
subdir = os.path.join(self.datadir, 'FlickrFinal2')
D = dirlist(subdir)
for (k, d) in enumerate(D):
print(
'[megaface.dataset][%d/%d]: creating image list for "%s"'
% (k, len(D), d))
for sd in dirlist(d):
for f in imlist(sd):
csv.write(f + '\n') # full path
return outfile
def dataset(self):
return [
ImageCategory(category=s, filename=f) for s in self.subjects()
for f in imlist(os.path.join(self.lfwdir, s))
]
def subject_images(self, subject):
"""List of Images of a subject"""
fnames = imlist(os.path.join(self.lfwdir, subject))
return [ImageCategory(category=subject, filename=f) for f in fnames]
def _parse(self):
outlist = []
id2name = {k:v for (k,v) in readcsv(os.path.join(self.datadir, 'names.txt'), separator=' ')}
for d in dirlist(self.datadir):
outlist = outlist + [ImageDetection(filename=imfile, category=id2name[str(filebase(d))], xmin=13, ymin=13, xmax=250 - 13, ymax=250 - 13) for imfile in imlist(d)]
return outlist
def by_subject(self, wordnetid):
d = os.path.join(self.datadir, 'images', wordnetid)
for f in imlist(d):
yield ImageDetection(filename=f, category=filebase(d))
def fastset(self):
"""Return a generator to iterate over dataset"""
for d in dirlist(os.path.join(self.datadir, 'images')):
for f in imlist(d):
im = ImageDetection(filename=f, category=filebase(d))
yield im
def dataset(self):
"""Return a generator to iterate over dataset"""
for d in dirlist(os.path.join(self.datadir)):
for f in imlist(d):
yield ImageDetection(filename=f).category(filebase(d))