def _init_data(self):
""" Store some metadata that needs to be known during training. In order to sample, the viable sequences
must be known. Sequences are viable if a snippet of given sample length can be selected, starting with
an annotated frame and containing at least one more annotated frame.
"""
print("-- YTVOS dataset initialization started.")
framework_path = os.path.join(os.path.dirname(__file__), '..')
cache_path = os.path.join(framework_path, 'cache', 'ytvos_v2_{}_100px_threshold.json'.format(self._split))
# First find visible objects in all annotated frames
if os.path.exists(cache_path):
with open(cache_path, 'r') as f:
self._visible_objects, self._resolutions = json.load(f)
self._visible_objects = {seqname: OrderedDict((int(idx), objlst) for idx, objlst in val.items())
for seqname, val in self._visible_objects.items()}
assert len(self._visible_objects) == len(self._resolutions)
print("Datafile {} loaded, describing {} sequences.".format(cache_path, len(self._visible_objects)))
else:
# Grab all sequences in dataset
seqnames = os.listdir(os.path.join(self._root_path, self._split, self._impath))
# Construct meta-info
self._visible_objects = {}
self._resolutions = {}
for seqname in tqdm.tqdm(seqnames):
anno_paths = sorted(glob.glob(self._full_anno_path(seqname, "*.png")))
self._visible_objects[seqname] = OrderedDict(
(self._frame_name_to_idx(os.path.basename(path)),
get_anno_ids(path, dataset_utils.LabelToLongTensor(), 100))
for path in anno_paths)
self._resolutions[seqname] = Image.open(anno_paths[0]).size[::-1]
# Save meta-info
if not os.path.exists(os.path.dirname(cache_path)):
os.makedirs(os.path.dirname(cache_path))
with open(cache_path, 'w') as f:
json.dump((self._visible_objects, self._resolutions), f)
print("Datafile {} was not found, creating it with {} sequences.".format(
cache_path, len(self._visible_objects)))
# Find sequences in the requested image_set
if self._split == 'train':
with open(os.path.join(self._root_path, "ImageSets", self._image_set + '.txt'), 'r') as f:
self._all_seqs = f.read().splitlines()
print("{} sequences found in image set \"{}\"".format(len(self._all_seqs), self._image_set))
else:
self._all_seqs = os.listdir(os.path.join(self._root_path, self._split, "Annotations"))
print("{} sequences found in the Annotations directory.".format(len(self._all_seqs)))
# Filter out sequences that are too short from first frame with object, to last annotation
self._nonempty_frame_ids = {seq: [frame_idx for frame_idx, obj_ids in lst.items() if len(obj_ids) >= self._min_num_objects]
for seq, lst in self._visible_objects.items()}
self._viable_seqs = [seq for seq in self._all_seqs if
len(self._nonempty_frame_ids[seq]) > 0
and len(self.get_image_frame_ids(seq)[min(self._nonempty_frame_ids[seq]) :
max(self._visible_objects[seq].keys()) + 1])
>= self._seqlen]
print("{} sequences remaining after filtering on length (from first anno obj appearance to last anno frame.".format(len(self._viable_seqs)))
def label_read(path):
if os.path.exists(path):
pic = Image.open(path)
transform = tv.transforms.Compose(
[tv.transforms.Resize(size, interpolation=Image.NEAREST),
dataset_utils.LabelToLongTensor()])
label = transform(pic)
else:
label = torch.LongTensor(1,*size).fill_(255) # Put label that will be ignored
return label
def _init_data(self):
framework_path = os.path.join(os.path.dirname(__file__), '..')
cache_path = os.path.join(
framework_path, 'cache',
'davis17_v2_visible_objects_100px_threshold.json')
if os.path.exists(cache_path):
with open(cache_path, 'r') as f:
self._visible_objects = json.load(f)
self._visible_objects = {
seqname: OrderedDict(
(int(idx), objlst) for idx, objlst in val.items())
for seqname, val in self._visible_objects.items()
}
else:
seqnames = os.listdir(
os.path.join(self._root_path, 'JPEGImages', '480p'))
self._visible_objects = {}
for seqname in seqnames:
anno_paths = sorted(
glob.glob(self._full_anno_path(seqname, '*.png')))
self._visible_objects[seqname] = OrderedDict(
(self._frame_name_to_idx(os.path.basename(path)),
get_anno_ids(path, dataset_utils.LabelToLongTensor(), 100)
) for path in anno_paths)
if not os.path.exists(os.path.dirname(cache_path)):
os.makedirs(os.path.dirname(cache_path))
with open(cache_path, 'w') as f:
json.dump(self._visible_objects, f)
print("Datafile {} was not found, creating it with {} sequences.".
format(cache_path, len(self._visible_objects)))
with open(
os.path.join(self._root_path, 'ImageSets', self._version,
self._image_set + '.txt'), 'r') as f:
self._all_seqs = f.read().splitlines()
self._nonempty_frame_ids = {
seq: [
frame_idx for frame_idx, obj_ids in lst.items()
if len(obj_ids) >= self._min_num_objects
]
for seq, lst in self._visible_objects.items()
}
self._viable_seqs = [
seq for seq in self._all_seqs
if len(self._nonempty_frame_ids[seq]) > 0 and len(
self.get_image_frame_ids(seq)
[min(self._nonempty_frame_ids[seq]
):max(self._visible_objects[seq].keys()) +
1]) >= self._seqlen
]
def _init_data(self):
""" Store some metadata that needs to be known during training. In order to sample, the viable sequences
must be known. Sequences are viable if a snippet of given sample length can be selected, starting with
an annotated frame and containing at least one more annotated frame.
"""
print("-- DAVIS17 dataset initialization started.")
framework_path = os.path.join(os.path.dirname(__file__), "..")
cache_path = os.path.join(
framework_path, "cache", "davis17_v2_visible_objects_100px_threshold.json"
)
# First find visible objects in all annotated frames
if os.path.exists(cache_path):
with open(cache_path, "r") as f:
self._visible_objects = json.load(f)
self._visible_objects = {
seqname: OrderedDict(
(int(idx), objlst) for idx, objlst in val.items()
)
for seqname, val in self._visible_objects.items()
}
print(
"Datafile {} loaded, describing {} sequences.".format(
cache_path, len(self._visible_objects)
)
)
else:
# Grab all sequences in dataset
seqnames = os.listdir(os.path.join(self._root_path, "JPEGImages", "480p"))
# Construct meta-info
self._visible_objects = {}
for seqname in seqnames:
anno_paths = sorted(glob.glob(self._full_anno_path(seqname, "*.png")))
self._visible_objects[seqname] = OrderedDict(
(
self._frame_name_to_idx(os.path.basename(path)),
get_anno_ids(path, dataset_utils.LabelToLongTensor(), 100),
)
for path in anno_paths
)
if not os.path.exists(os.path.dirname(cache_path)):
os.makedirs(os.path.dirname(cache_path))
with open(cache_path, "w") as f:
json.dump(self._visible_objects, f)
print(
"Datafile {} was not found, creating it with {} sequences.".format(
cache_path, len(self._visible_objects)
)
)
# Find sequences in the requested image_set
with open(
os.path.join(
self._root_path, "ImageSets", self._version, self._image_set + ".txt"
),
"r",
) as f:
self._all_seqs = f.read().splitlines()
print(
'{} sequences found in image set "{}"'.format(
len(self._all_seqs), self._image_set
)
)
# Filter out sequences that are too short from first frame with object, to last annotation
self._nonempty_frame_ids = {
seq: [
frame_idx
for frame_idx, obj_ids in lst.items()
if len(obj_ids) >= self._min_num_objects
]
for seq, lst in self._visible_objects.items()
}
self._viable_seqs = [
seq
for seq in self._all_seqs
if len(self._nonempty_frame_ids[seq]) > 0
and len(
self.get_image_frame_ids(seq)[
min(self._nonempty_frame_ids[seq]) : max(
self._visible_objects[seq].keys()
)
+ 1
]
)
>= self._seqlen
]
print(
"{} sequences remaining after filtering on length (from first anno obj appearance to last anno frame.".format(
len(self._viable_seqs)
)
)
