def _load(self):
with open(self.txt_filelist, "r") as f:
self.relpaths = f.read().splitlines()
l1 = len(self.relpaths)
self.relpaths = self._filter_relpaths(self.relpaths)
print("Removed {} files from filelist during filtering.".format(l1 - len(self.relpaths)))
self.synsets = [p.split("/")[0] for p in self.relpaths]
self.abspaths = [os.path.join(self.datadir, p) for p in self.relpaths]
unique_synsets = np.unique(self.synsets)
class_dict = dict((synset, i) for i, synset in enumerate(unique_synsets))
self.class_labels = [class_dict[s] for s in self.synsets]
with open(self.human_dict, "r") as f:
human_dict = f.read().splitlines()
human_dict = dict(line.split(maxsplit=1) for line in human_dict)
self.human_labels = [human_dict[s] for s in self.synsets]
labels = {
"relpath": np.array(self.relpaths),
"synsets": np.array(self.synsets),
"class_label": np.array(self.class_labels),
"human_label": np.array(self.human_labels),
}
self.data = ImagePaths(self.abspaths,
labels=labels,
size=retrieve(self.config, "size", default=0),
random_crop=self.random_crop)
def _prepare(self):
self.random_crop = retrieve(self.config,
"ImageNetValidation/random_crop",
default=False)
cachedir = os.environ.get("XDG_CACHE_HOME",
os.path.expanduser("~/.cache"))
self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
self.datadir = os.path.join(self.root, "data")
self.txt_filelist = os.path.join(self.root, "filelist.txt")
self.expected_length = 50000
if not bdu.is_prepared(self.root):
# prep
print("Preparing dataset {} in {}".format(self.NAME, self.root))
datadir = self.datadir
if not os.path.exists(datadir):
path = os.path.join(self.root, self.FILES[0])
if not os.path.exists(path) or not os.path.getsize(
path) == self.SIZES[0]:
import academictorrents as at
atpath = at.get(self.AT_HASH, datastore=self.root)
assert atpath == path
print("Extracting {} to {}".format(path, datadir))
os.makedirs(datadir, exist_ok=True)
with tarfile.open(path, "r:") as tar:
tar.extractall(path=datadir)
#indent here
vspath = os.path.join(self.root, self.FILES[1])
if not os.path.exists(vspath) or not os.path.getsize(
vspath) == self.SIZES[1]:
download(self.VS_URL, vspath)
with open(vspath, "r") as f:
synset_dict = f.read().splitlines()
synset_dict = dict(line.split() for line in synset_dict)
print("Reorganizing into synset folders")
synsets = np.unique(list(synset_dict.values()))
for s in synsets:
os.makedirs(os.path.join(datadir, s), exist_ok=True)
for k, v in synset_dict.items():
src = os.path.join(datadir, k)
dst = os.path.join(datadir, v)
shutil.move(src, dst)
filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
filelist = [os.path.relpath(p, start=datadir) for p in filelist]
filelist = sorted(filelist)
filelist = "\n".join(filelist) + "\n"
with open(self.txt_filelist, "w") as f:
f.write(filelist)
bdu.mark_prepared(self.root)
def _prepare(self):
self.random_crop = retrieve(self.config,
"ImageNetTrain/random_crop",
default=True)
cachedir = os.environ.get("XDG_CACHE_HOME",
os.path.expanduser("~/.cache"))
self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
self.datadir = os.path.join(self.root, "data")
self.txt_filelist = os.path.join(self.root, "filelist.txt")
self.expected_length = 1281167
if not bdu.is_prepared(self.root):
# prep
print("Preparing dataset {} in {}".format(self.NAME, self.root))
datadir = self.datadir
if not os.path.exists(datadir):
path = os.path.join(self.root, self.FILES[0])
if not os.path.exists(path) or not os.path.getsize(
path) == self.SIZES[0]:
import academictorrents as at
atpath = at.get(self.AT_HASH, datastore=self.root)
assert atpath == path
print("Extracting {} to {}".format(path, datadir))
os.makedirs(datadir, exist_ok=True)
with tarfile.open(path, "r:") as tar:
tar.extractall(path=datadir)
print("Extracting sub-tars.")
subpaths = sorted(glob.glob(os.path.join(datadir, "*.tar")))
for subpath in tqdm(subpaths):
subdir = subpath[:-len(".tar")]
os.makedirs(subdir, exist_ok=True)
with tarfile.open(subpath, "r:") as tar:
tar.extractall(path=subdir)
filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
filelist = [os.path.relpath(p, start=datadir) for p in filelist]
filelist = sorted(filelist)
filelist = "\n".join(filelist) + "\n"
with open(self.txt_filelist, "w") as f:
f.write(filelist)
bdu.mark_prepared(self.root)