def register_all_cityscapes(root=osp.join(
osp.split(osp.split(dl_lib.__file__)[0])[0], "datasets")):
for key, (image_dir, gt_dir) in _RAW_CITYSCAPES_SPLITS.items():
meta = _get_builtin_metadata("cityscapes")
image_dir = os.path.join(root, image_dir)
gt_dir = os.path.join(root, gt_dir)
inst_key = key.format(task="instance_seg")
DatasetCatalog.register(
inst_key,
lambda x=image_dir, y=gt_dir: load_cityscapes_instances(
x, y, from_json=True, to_polygons=True),
)
MetadataCatalog.get(inst_key).set(image_dir=image_dir,
gt_dir=gt_dir,
evaluator_type="cityscapes",
**meta)
sem_key = key.format(task="sem_seg")
DatasetCatalog.register(
sem_key,
lambda x=image_dir, y=gt_dir: load_cityscapes_semantic(x, y))
MetadataCatalog.get(sem_key).set(image_dir=image_dir,
gt_dir=gt_dir,
evaluator_type="sem_seg",
**meta)
def register_coco_panoptic_separated(name, metadata, image_root, panoptic_root,
panoptic_json, sem_seg_root,
instances_json):
"""
Register a COCO panoptic segmentation dataset named `name`.
The annotations in this registered dataset will contain both instance annotations and
semantic annotations, each with its own contiguous ids. Hence it's called "separated".
It follows the setting used by the PanopticFPN paper:
1. The instance annotations directly come from polygons in the COCO
instances annotation task, rather than from the masks in the COCO panoptic annotations.
The two format have small differences:
Polygons in the instance annotations may have overlaps.
The mask annotations are produced by labeling the overlapped polygons
with depth ordering.
2. The semantic annotations are converted from panoptic annotations, where
all "things" are assigned a semantic id of 0.
All semantic categories will therefore have ids in contiguous
range [1, #stuff_categories].
This function will also register a pure semantic segmentation dataset
named ``name + '_stuffonly'``.
Args:
name (str): the name that identifies a dataset,
e.g. "coco_2017_train_panoptic"
metadata (dict): extra metadata associated with this dataset.
image_root (str): directory which contains all the images
panoptic_root (str): directory which contains panoptic annotation images
panoptic_json (str): path to the json panoptic annotation file
sem_seg_root (str): directory which contains all the ground truth segmentation annotations.
instances_json (str): path to the json instance annotation file
"""
panoptic_name = name + "_separated"
DatasetCatalog.register(
panoptic_name,
lambda: merge_to_panoptic(
load_coco_json(instances_json, image_root, panoptic_name),
load_sem_seg(sem_seg_root, image_root),
),
)
MetadataCatalog.get(panoptic_name).set(
panoptic_root=panoptic_root,
image_root=image_root,
panoptic_json=panoptic_json,
sem_seg_root=sem_seg_root,
json_file=instances_json, # TODO rename
evaluator_type="coco_panoptic_seg",
**metadata)
semantic_name = name + "_stuffonly"
DatasetCatalog.register(semantic_name,
lambda: load_sem_seg(sem_seg_root, image_root))
MetadataCatalog.get(semantic_name).set(sem_seg_root=sem_seg_root,
image_root=image_root,
evaluator_type="sem_seg",
**metadata)
def register_coco_instances(name, metadata, json_file, image_root):
"""
Register a dataset in COCO's json annotation format for
instance detection, instance segmentation and keypoint detection.
(i.e., Type 1 and 2 in http://cocodataset.org/#format-data.
`instances*.json` and `person_keypoints*.json` in the dataset).
This is an example of how to register a new dataset.
You can do something similar to this function, to register new datasets.
Args:
name (str): the name that identifies a dataset, e.g. "coco_2014_train".
metadata (dict): extra metadata associated with this dataset. You can
leave it as an empty dict.
json_file (str): path to the json instance annotation file.
image_root (str): directory which contains all the images.
"""
# 1. register a function which returns dicts
DatasetCatalog.register(
name, lambda: load_coco_json(json_file, image_root, name))
# 2. Optionally, add metadata about this dataset,
# since they might be useful in evaluation, visualization or logging
MetadataCatalog.get(name).set(json_file=json_file,
image_root=image_root,
evaluator_type="coco",
**metadata)
def register_all_rock(root=osp.join(
osp.split(osp.split(dl_lib.__file__)[0])[0], "datasets")):
#for key, (image_dir, gt_dir) in _RAW_ROCK_SPLITS.items():
_voc_root = os.path.join(root, BASE_DIR)
_cat_dir = os.path.join(_voc_root,
'SegmentationClass') # each class each color
_image_dir = os.path.join(_voc_root, 'JPEGImages')
_splits_dir = os.path.join(_voc_root, 'ImageSets', 'Segmentation')
key = "rock_{task}"
for _splits_file in os.listdir(_splits_dir):
_format_key = key.format(task=os.path.splitext(_splits_file)[0])
DatasetCatalog.register(
_format_key,
lambda x=_image_dir, y=_cat_dir, z=os.path.join(
_splits_dir, _splits_file): load_rock_semantic(x, y, z))
MetadataCatalog.get(_format_key).set(
image_dir=_image_dir,
gt_dir=_cat_dir,
evaluator_type="sem_seg",
)
def __init__(self,
dataset_name,
distributed,
num_classes,
ignore_label=255,
output_dir=None):
"""
Args:
dataset_name (str): name of the dataset to be evaluated.
distributed (True): if True, will collect results from all ranks for evaluation.
Otherwise, will evaluate the results in the current process.
num_classes (int): number of classes
ignore_label (int): value in semantic segmentation ground truth. Predictions for the
corresponding pixels should be ignored.
output_dir (str): an output directory to dump results.
"""
self._dataset_name = dataset_name
self._distributed = distributed
self._output_dir = output_dir
self._num_classes = num_classes
self._ignore_label = ignore_label
self._N = num_classes + 1
self._cpu_device = torch.device("cpu")
self._logger = logging.getLogger(__name__)
self.input_file_to_gt_file = {
dataset_record["file_name"]: dataset_record["sem_seg_file_name"]
for dataset_record in DatasetCatalog.get(dataset_name)
}
meta = MetadataCatalog.get(dataset_name)
# Dict that maps contiguous training ids to COCO category ids
try:
c2d = meta.stuff_dataset_id_to_contiguous_id
self._contiguous_id_to_dataset_id = {v: k for k, v in c2d.items()}
except AttributeError:
self._contiguous_id_to_dataset_id = None
def register_pascal_voc(name, dirname, split, year):
DatasetCatalog.register(name, lambda: load_voc_instances(dirname, split))
MetadataCatalog.get(name).set(thing_classes=CLASS_NAMES,
dirname=dirname,
year=year,
split=split)