def _datapipe(self, resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
archive_dp = resource_dps[0]
images_dp, scenes_dp = Demultiplexer(
archive_dp,
2,
self._classify_archive,
drop_none=True,
buffer_size=INFINITE_BUFFER_SIZE,
)
images_dp = Filter(images_dp, path_comparator("parent.name", self._split))
images_dp = hint_shuffling(images_dp)
images_dp = hint_sharding(images_dp)
if self._split != "test":
scenes_dp = Filter(scenes_dp, path_comparator("name", f"CLEVR_{self._split}_scenes.json"))
scenes_dp = JsonParser(scenes_dp)
scenes_dp = Mapper(scenes_dp, getitem(1, "scenes"))
scenes_dp = UnBatcher(scenes_dp)
dp = IterKeyZipper(
images_dp,
scenes_dp,
key_fn=path_accessor("name"),
ref_key_fn=getitem("image_filename"),
buffer_size=INFINITE_BUFFER_SIZE,
)
else:
dp = Mapper(images_dp, self._add_empty_anns)
return Mapper(dp, self._prepare_sample)
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
decoder: Optional[Callable[[io.IOBase], torch.Tensor]],
) -> IterDataPipe[Dict[str, Any]]:
images_dp, anns_dp = resource_dps
images_dp = Filter(images_dp, self._is_not_background_image)
images_dp = hint_sharding(images_dp)
images_dp = hint_shuffling(images_dp)
anns_dp = Filter(anns_dp, self._is_ann)
dp = IterKeyZipper(
images_dp,
anns_dp,
key_fn=self._images_key_fn,
ref_key_fn=self._anns_key_fn,
buffer_size=INFINITE_BUFFER_SIZE,
keep_key=True,
)
return Mapper(
dp,
functools.partial(self._collate_and_decode_sample,
decoder=decoder))
def _datapipe(self, resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
archive_dp = resource_dps[0]
split_dp, images_dp, anns_dp = Demultiplexer(
archive_dp,
3,
self._classify_archive,
drop_none=True,
buffer_size=INFINITE_BUFFER_SIZE,
)
split_dp = Filter(split_dp, functools.partial(self._is_in_folder, name=self._split_folder))
split_dp = Filter(split_dp, path_comparator("name", f"{self._split}.txt"))
split_dp = LineReader(split_dp, decode=True)
split_dp = hint_shuffling(split_dp)
split_dp = hint_sharding(split_dp)
dp = split_dp
for level, data_dp in enumerate((images_dp, anns_dp)):
dp = IterKeyZipper(
dp,
data_dp,
key_fn=getitem(*[0] * level, 1),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
return Mapper(dp, self._prepare_sample)
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
decoder: Optional[Callable[[io.IOBase], torch.Tensor]],
) -> IterDataPipe[Dict[str, Any]]:
images_dp, anns_dp = resource_dps
images_dp = Filter(images_dp, self._filter_images)
split_and_classification_dp, segmentations_dp = Demultiplexer(
anns_dp,
2,
self._classify_anns,
drop_none=True,
buffer_size=INFINITE_BUFFER_SIZE,
)
split_and_classification_dp = Filter(
split_and_classification_dp,
path_comparator("name", f"{config.split}.txt"))
split_and_classification_dp = CSVDictParser(
split_and_classification_dp,
fieldnames=("image_id", "label", "species"),
delimiter=" ")
split_and_classification_dp = hint_sharding(
split_and_classification_dp)
split_and_classification_dp = hint_shuffling(
split_and_classification_dp)
segmentations_dp = Filter(segmentations_dp, self._filter_segmentations)
anns_dp = IterKeyZipper(
split_and_classification_dp,
segmentations_dp,
key_fn=getitem("image_id"),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
dp = IterKeyZipper(
anns_dp,
images_dp,
key_fn=getitem(0, "image_id"),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
return Mapper(
dp,
functools.partial(self._collate_and_decode_sample,
decoder=decoder))
def _generate_categories(self) -> List[str]:
resources = self._resources()
dp = resources[1].load(self._root)
dp = Filter(dp, self._filter_split_and_classification_anns)
dp = Filter(dp, path_comparator("name", "trainval.txt"))
dp = CSVDictParser(dp, fieldnames=("image_id", "label"), delimiter=" ")
raw_categories_and_labels = {(data["image_id"].rsplit("_", 1)[0], data["label"]) for data in dp}
raw_categories, _ = zip(
*sorted(raw_categories_and_labels, key=lambda raw_category_and_label: int(raw_category_and_label[1]))
)
return [" ".join(part.title() for part in raw_category.split("_")) for raw_category in raw_categories]
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
decoder: Optional[Callable[[io.IOBase], torch.Tensor]],
) -> IterDataPipe[Dict[str, Any]]:
archive_dp = resource_dps[0]
splits_dp, joint_categories_dp, images_dp = Demultiplexer(
archive_dp, 3, self._classify_archive, drop_none=True, buffer_size=INFINITE_BUFFER_SIZE
)
splits_dp = Filter(splits_dp, path_comparator("name", f"{config.split}{config.fold}.txt"))
splits_dp = LineReader(splits_dp, decode=True, return_path=False)
splits_dp = Shuffler(splits_dp, buffer_size=INFINITE_BUFFER_SIZE)
splits_dp = hint_sharding(splits_dp)
joint_categories_dp = CSVParser(joint_categories_dp, delimiter=" ")
dp = IterKeyZipper(
splits_dp,
joint_categories_dp,
key_fn=getitem(),
ref_key_fn=getitem(0),
buffer_size=INFINITE_BUFFER_SIZE,
)
dp = IterKeyZipper(
dp,
images_dp,
key_fn=getitem(0),
ref_key_fn=self._image_key_fn,
buffer_size=INFINITE_BUFFER_SIZE,
)
return Mapper(dp, functools.partial(self._collate_and_decode_sample, decoder=decoder))
def _generate_categories(self) -> List[str]:
resources = self._resources()
dp = resources[0].load(self._root)
dp = Filter(dp, self._is_not_background_image)
return sorted({pathlib.Path(path).parent.name for path, _ in dp})
def _generate_categories(self, root: pathlib.Path) -> List[str]:
resources = self.resources(self.default_config)
dp = resources[0].load(root)
dp = Filter(dp, self._filter_images)
return sorted({pathlib.Path(path).parent.name for path, _ in dp})
def _generate_categories(self, root: pathlib.Path) -> List[str]:
config = self.default_config
dp = self.resources(config)[1].load(pathlib.Path(root) / self.name)
dp = Filter(dp, self._filter_split_and_classification_anns)
dp = Filter(dp, path_comparator("name", f"{config.split}.txt"))
dp = CSVDictParser(dp, fieldnames=("image_id", "label"), delimiter=" ")
raw_categories_and_labels = {(data["image_id"].rsplit("_", 1)[0],
data["label"])
for data in dp}
raw_categories, _ = zip(*sorted(
raw_categories_and_labels,
key=lambda raw_category_and_label: int(raw_category_and_label[1])))
return [
" ".join(part.title() for part in raw_category.split("_"))
for raw_category in raw_categories
]
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
) -> IterDataPipe[Dict[str, Any]]:
archive_dp, extra_split_dp = resource_dps
archive_dp = resource_dps[0]
split_dp, images_dp, anns_dp = Demultiplexer(
archive_dp,
3,
self._classify_archive,
buffer_size=INFINITE_BUFFER_SIZE,
drop_none=True,
)
if config.split == "train_noval":
split_dp = extra_split_dp
split_dp = Filter(split_dp,
path_comparator("name", f"{config.split}.txt"))
split_dp = LineReader(split_dp, decode=True)
split_dp = hint_sharding(split_dp)
split_dp = hint_shuffling(split_dp)
dp = split_dp
for level, data_dp in enumerate((images_dp, anns_dp)):
dp = IterKeyZipper(
dp,
data_dp,
key_fn=getitem(*[0] * level, 1),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
return Mapper(dp, self._prepare_sample)
def _generate_categories(self) -> Tuple[Tuple[str, str]]:
self._annotations = "instances"
resources = self._resources()
dp = resources[1].load(self._root)
dp = Filter(dp, self._filter_meta_files)
dp = JsonParser(dp)
_, meta = next(iter(dp))
# List[Tuple[super_category, id, category]]
label_data = [
cast(Tuple[str, int, str], tuple(info.values()))
for info in meta["categories"]
]
# COCO actually defines 91 categories, but only 80 of them have instances. Still, the category_id refers to the
# full set. To keep the labels dense, we fill the gaps with N/A. Note that there are only 10 gaps, so the total
# number of categories is 90 rather than 91.
_, ids, _ = zip(*label_data)
missing_ids = set(range(1, max(ids) + 1)) - set(ids)
label_data.extend([("N/A", id, "N/A") for id in missing_ids])
# We also add a background category to be used during segmentation.
label_data.append(("N/A", 0, "__background__"))
super_categories, _, categories = zip(
*sorted(label_data, key=lambda info: info[1]))
return cast(Tuple[Tuple[str, str]],
tuple(zip(categories, super_categories)))
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
decoder: Optional[Callable[[io.IOBase], torch.Tensor]],
) -> IterDataPipe[Dict[str, Any]]:
if config.split == "train":
images_dp, ann_dp = Demultiplexer(resource_dps[0],
2,
self._classify_train_archive,
drop_none=True,
buffer_size=INFINITE_BUFFER_SIZE)
else:
images_dp, ann_dp = resource_dps
images_dp = Filter(images_dp, path_comparator("suffix", ".ppm"))
# The order of the image files in the the .zip archives perfectly match the order of the entries in
# the (possibly concatenated) .csv files. So we're able to use Zipper here instead of a IterKeyZipper.
ann_dp = CSVDictParser(ann_dp, delimiter=";")
dp = Zipper(images_dp, ann_dp)
dp = hint_sharding(dp)
dp = hint_shuffling(dp)
dp = Mapper(dp, partial(self._collate_and_decode, decoder=decoder))
return dp
def from_data_folder(
root: Union[str, pathlib.Path],
*,
decoder: Optional[Callable[[io.IOBase], torch.Tensor]] = None,
valid_extensions: Optional[Collection[str]] = None,
recursive: bool = True,
) -> Tuple[IterDataPipe, List[str]]:
root = pathlib.Path(root).expanduser().resolve()
categories = sorted(entry.name for entry in os.scandir(root)
if entry.is_dir())
masks: Union[List[str], str] = [f"*.{ext}" for ext in valid_extensions
] if valid_extensions is not None else ""
dp = FileLister(str(root), recursive=recursive, masks=masks)
dp: IterDataPipe = Filter(
dp, functools.partial(_is_not_top_level_file, root=root))
dp = hint_sharding(dp)
dp = Shuffler(dp, buffer_size=INFINITE_BUFFER_SIZE)
dp = FileOpener(dp, mode="rb")
return (
Mapper(
dp,
functools.partial(_collate_and_decode_data,
root=root,
categories=categories,
decoder=decoder)),
categories,
)
def _datapipe(self, resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
dp = resource_dps[0]
dp = Filter(dp, self._is_data_file)
dp = Mapper(dp, self._unpickle)
dp = CifarFileReader(dp, labels_key=self._LABELS_KEY)
dp = hint_shuffling(dp)
dp = hint_sharding(dp)
return Mapper(dp, self._prepare_sample)
def _datapipe(
self,
resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
dp = resource_dps[0]
dp = Filter(dp, self._is_not_rogue_file)
dp = hint_shuffling(dp)
dp = hint_sharding(dp)
return Mapper(dp, self._prepare_sample)
def _generate_categories(self) -> List[str]:
resources = self._resources()
devkit_dp = resources[1].load(self._root)
meta_dp = Filter(devkit_dp, path_comparator("name", "cars_meta.mat"))
_, meta_file = next(iter(meta_dp))
return list(read_mat(meta_file, squeeze_me=True)["class_names"])
def _generate_categories(self) -> List[str]:
resources = self._resources()
dp = resources[0].load(self._root)
dp = Filter(dp, path_comparator("name", self._META_FILE_NAME))
dp = Mapper(dp, self._unpickle)
return cast(List[str], next(iter(dp))[self._CATEGORIES_KEY])
def _make_datapipe(
self, resource_dps: List[IterDataPipe], *, config: DatasetConfig
) -> IterDataPipe[Dict[str, Any]]:
dp = resource_dps[0]
dp = Filter(dp, path_comparator("parent.parent.name", self._SPLIT_NAME_MAPPER[config.split]))
dp = hint_sharding(dp)
dp = hint_shuffling(dp)
return Mapper(dp, self._prepare_sample)
def _datapipe(
self,
resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
images_dp, anns_dp = resource_dps
images_dp = Filter(images_dp, self._filter_images)
split_and_classification_dp, segmentations_dp = Demultiplexer(
anns_dp,
2,
self._classify_anns,
drop_none=True,
buffer_size=INFINITE_BUFFER_SIZE,
)
split_and_classification_dp = Filter(
split_and_classification_dp,
path_comparator("name", f"{self._split}.txt"))
split_and_classification_dp = CSVDictParser(
split_and_classification_dp,
fieldnames=("image_id", "label", "species"),
delimiter=" ")
split_and_classification_dp = hint_shuffling(
split_and_classification_dp)
split_and_classification_dp = hint_sharding(
split_and_classification_dp)
segmentations_dp = Filter(segmentations_dp, self._filter_segmentations)
anns_dp = IterKeyZipper(
split_and_classification_dp,
segmentations_dp,
key_fn=getitem("image_id"),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
dp = IterKeyZipper(
anns_dp,
images_dp,
key_fn=getitem(0, "image_id"),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
return Mapper(dp, self._prepare_sample)
def _generate_categories(self, root: pathlib.Path) -> List[str]:
config = self.info.make_config(task="detection")
resource = self.resources(config)[0]
dp = resource.load(pathlib.Path(root) / self.name)
dp = Filter(dp, self._filter_detection_anns, fn_kwargs=dict(config=config))
dp = Mapper(dp, self._parse_detection_ann, input_col=1)
return sorted({instance["name"] for _, anns in dp for instance in anns["object"]})
def _datapipe(
self,
resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
dp = resource_dps[0]
dp = Filter(
dp, path_comparator("parent.parent.name", self._split_folder_name))
dp = hint_shuffling(dp)
dp = hint_sharding(dp)
return Mapper(dp, self._prepare_sample)
def _generate_categories(self, root: pathlib.Path) -> List[str]:
config = self.info.make_config(split="train")
resources = self.resources(config)
devkit_dp = resources[1].load(root)
meta_dp = Filter(devkit_dp, path_comparator("name", "cars_meta.mat"))
_, meta_file = next(iter(meta_dp))
return list(read_mat(meta_file, squeeze_me=True)["class_names"])
def _datapipe(self, resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
images_dp, targets_dp = resource_dps
if self._split == "train":
targets_dp = Filter(targets_dp, path_comparator("name", "cars_train_annos.mat"))
targets_dp = StanfordCarsLabelReader(targets_dp)
dp = Zipper(images_dp, targets_dp)
dp = hint_shuffling(dp)
dp = hint_sharding(dp)
return Mapper(dp, self._prepare_sample)
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
) -> IterDataPipe[Dict[str, Any]]:
archive_dp = resource_dps[0]
split_dp, images_dp, anns_dp = Demultiplexer(
archive_dp,
3,
functools.partial(self._classify_archive, config=config),
drop_none=True,
buffer_size=INFINITE_BUFFER_SIZE,
)
split_dp = Filter(
split_dp,
functools.partial(self._is_in_folder,
name=self._SPLIT_FOLDER[config.task]))
split_dp = Filter(split_dp,
path_comparator("name", f"{config.split}.txt"))
split_dp = LineReader(split_dp, decode=True)
split_dp = hint_sharding(split_dp)
split_dp = hint_shuffling(split_dp)
dp = split_dp
for level, data_dp in enumerate((images_dp, anns_dp)):
dp = IterKeyZipper(
dp,
data_dp,
key_fn=getitem(*[0] * level, 1),
ref_key_fn=path_accessor("stem"),
buffer_size=INFINITE_BUFFER_SIZE,
)
return Mapper(
dp,
functools.partial(
self._prepare_sample,
prepare_ann_fn=self._prepare_detection_ann if config.task
== "detection" else self._prepare_segmentation_ann,
),
)
def _generate_categories(self) -> List[str]:
self._year = "2011"
resources = self._resources()
dp = resources[0].load(self._root)
dp = Filter(dp, path_comparator("name", "classes.txt"))
dp = CSVDictParser(dp,
fieldnames=("label", "category"),
dialect="cub200")
return [row["category"].split(".")[1] for row in dp]
def _datapipe(
self,
resource_dps: List[IterDataPipe]) -> IterDataPipe[Dict[str, Any]]:
images_dp, anns_dp = resource_dps
images_dp = Filter(images_dp, self._is_not_background_image)
images_dp = hint_shuffling(images_dp)
images_dp = hint_sharding(images_dp)
anns_dp = Filter(anns_dp, self._is_ann)
dp = IterKeyZipper(
images_dp,
anns_dp,
key_fn=self._images_key_fn,
ref_key_fn=self._anns_key_fn,
buffer_size=INFINITE_BUFFER_SIZE,
keep_key=True,
)
return Mapper(dp, self._prepare_sample)
def _generate_categories(self, root: pathlib.Path) -> List[str]:
config = self.info.make_config(year="2011")
resources = self.resources(config)
dp = resources[0].load(root)
dp = Filter(dp, path_comparator("name", "classes.txt"))
dp = CSVDictParser(dp,
fieldnames=("label", "category"),
dialect="cub200")
return [row["category"].split(".")[1] for row in dp]
def _generate_categories(self) -> List[Tuple[str, ...]]:
self._split = "val"
resources = self._resources()
devkit_dp = resources[1].load(self._root)
meta_dp = Filter(devkit_dp, self._filter_meta)
meta_dp = Mapper(meta_dp, self._extract_categories_and_wnids)
categories_and_wnids = cast(List[Tuple[str, ...]], next(iter(meta_dp)))
categories_and_wnids.sort(key=lambda category_and_wnid: category_and_wnid[1])
return categories_and_wnids
def _make_datapipe(
self,
resource_dps: List[IterDataPipe],
*,
config: DatasetConfig,
) -> IterDataPipe[Dict[str, Any]]:
dp = resource_dps[0]
dp = Filter(dp, functools.partial(self._is_data_file, split=config.split))
dp = Mapper(dp, self._unpickle)
dp = CifarFileReader(dp, labels_key=self._LABELS_KEY)
dp = hint_sharding(dp)
dp = hint_shuffling(dp)
return Mapper(dp, self._prepare_sample)
def _generate_categories(self,
root: pathlib.Path) -> List[Tuple[str, ...]]:
config = self.info.make_config(split="val")
resources = self.resources(config)
devkit_dp = resources[1].load(root)
meta_dp = Filter(devkit_dp, path_comparator("name", "meta.mat"))
meta_dp = Mapper(meta_dp, self._extract_categories_and_wnids)
categories_and_wnids = cast(List[Tuple[str, ...]], next(iter(meta_dp)))
categories_and_wnids.sort(
key=lambda category_and_wnid: category_and_wnid[1])
return categories_and_wnids