def get_cityscapes_panoptic_files(image_dir, gt_dir, json_info):
files = []
# scan through the directory
cities = PathManager.ls(image_dir)
logger.info(f"{len(cities)} cities found in '{image_dir}'.")
image_dict = {}
for city in cities:
city_img_dir = os.path.join(image_dir, city)
for basename in PathManager.ls(city_img_dir):
image_file = os.path.join(city_img_dir, basename)
suffix = "_leftImg8bit.png"
assert basename.endswith(suffix), basename
basename = os.path.basename(basename)[: -len(suffix)]
image_dict[basename] = image_file
for ann in json_info["annotations"]:
image_file = image_dict.get(ann["image_id"], None)
assert image_file is not None, "No image {} found for annotation {}".format(
ann["image_id"], ann["file_name"]
)
label_file = os.path.join(gt_dir, ann["file_name"])
segments_info = ann["segments_info"]
files.append((image_file, label_file, segments_info))
assert len(files), "No images found in {}".format(image_dir)
assert PathManager.isfile(files[0][0]), files[0][0]
assert PathManager.isfile(files[0][1]), files[0][1]
return files
def load_cityscapes_panoptic(image_dir, gt_dir, gt_json, meta):
"""
Args:
image_dir (str): path to the raw dataset. e.g., "~/cityscapes/leftImg8bit/train".
gt_dir (str): path to the raw annotations. e.g.,
"~/cityscapes/gtFine/cityscapes_panoptic_train".
gt_json (str): path to the json file. e.g.,
"~/cityscapes/gtFine/cityscapes_panoptic_train.json".
meta (dict): dictionary containing "thing_dataset_id_to_contiguous_id"
and "stuff_dataset_id_to_contiguous_id" to map category ids to
contiguous ids for training.
Returns:
list[dict]: a list of dicts in Detectron2 standard format. (See
`Using Custom Datasets </tutorials/datasets.html>`_ )
"""
def _convert_category_id(segment_info, meta):
if segment_info["category_id"] in meta["thing_dataset_id_to_contiguous_id"]:
segment_info["category_id"] = meta["thing_dataset_id_to_contiguous_id"][
segment_info["category_id"]
]
else:
segment_info["category_id"] = meta["stuff_dataset_id_to_contiguous_id"][
segment_info["category_id"]
]
return segment_info
assert os.path.exists(
gt_json
), "Please run `python cityscapesscripts/preparation/createPanopticImgs.py` to generate label files." # noqa
with open(gt_json) as f:
json_info = json.load(f)
files = get_cityscapes_panoptic_files(image_dir, gt_dir, json_info)
ret = []
for image_file, label_file, segments_info in files:
sem_label_file = (
image_file.replace("leftImg8bit", "gtFine").split(".")[0] + "_labelTrainIds.png"
)
segments_info = [_convert_category_id(x, meta) for x in segments_info]
ret.append(
{
"file_name": image_file,
"image_id": "_".join(
os.path.splitext(os.path.basename(image_file))[0].split("_")[:3]
),
"sem_seg_file_name": sem_label_file,
"pan_seg_file_name": label_file,
"segments_info": segments_info,
}
)
assert len(ret), f"No images found in {image_dir}!"
assert PathManager.isfile(
ret[0]["sem_seg_file_name"]
), "Please generate labelTrainIds.png with cityscapesscripts/preparation/createTrainIdLabelImgs.py" # noqa
assert PathManager.isfile(
ret[0]["pan_seg_file_name"]
), "Please generate panoptic annotation with python cityscapesscripts/preparation/createPanopticImgs.py" # noqa
return ret
def load_coco_panoptic_json(json_file, image_dir, gt_dir, meta):
"""
Args:
image_dir (str): path to the raw dataset. e.g., "~/coco/train2017".
gt_dir (str): path to the raw annotations. e.g., "~/coco/panoptic_train2017".
json_file (str): path to the json file. e.g., "~/coco/annotations/panoptic_train2017.json".
Returns:
list[dict]: a list of dicts in Detectron2 standard format. (See
`Using Custom Datasets </tutorials/datasets.html>`_ )
"""
def _convert_category_id(segment_info, meta):
if segment_info["category_id"] in meta[
"thing_dataset_id_to_contiguous_id"]:
segment_info["category_id"] = meta[
"thing_dataset_id_to_contiguous_id"][
segment_info["category_id"]]
segment_info["isthing"] = True
else:
segment_info["category_id"] = meta[
"stuff_dataset_id_to_contiguous_id"][
segment_info["category_id"]]
segment_info["isthing"] = False
return segment_info
with PathManager.open(json_file) as f:
json_info = json.load(f)
ret = []
for ann in json_info["annotations"]:
image_id = int(ann["image_id"])
# TODO: currently we assume image and label has the same filename but
# different extension, and images have extension ".jpg" for COCO. Need
# to make image extension a user-provided argument if we extend this
# function to support other COCO-like datasets.
image_file = os.path.join(
image_dir,
os.path.splitext(ann["file_name"])[0] + ".jpg")
assert PathManager.isfile(image_file), image_file
label_file = os.path.join(gt_dir, ann["file_name"])
assert PathManager.isfile(label_file), label_file
segments_info = [
_convert_category_id(x, meta) for x in ann["segments_info"]
]
ret.append({
"file_name": image_file,
"image_id": image_id,
"pan_seg_file_name": label_file,
"segments_info": segments_info,
})
assert len(ret), f"No images found in {image_dir}!"
assert PathManager.isfile(
ret[0]["pan_seg_file_name"]), ret[0]["pan_seg_file_name"]
return ret
def setUp(self):
json_file = MetadataCatalog.get("coco_2017_val_100").json_file
if not PathManager.isfile(json_file):
raise unittest.SkipTest("{} not found".format(json_file))
with contextlib.redirect_stdout(io.StringIO()):
json_file = PathManager.get_local_path(json_file)
self.coco = COCO(json_file)
def _get_cityscapes_files(image_dir, gt_dir):
files = []
# scan through the directory
cities = PathManager.ls(image_dir)
logger.info(f"{len(cities)} cities found in '{image_dir}'.")
for city in cities:
city_img_dir = os.path.join(image_dir, city)
city_gt_dir = os.path.join(gt_dir, city)
for basename in PathManager.ls(city_img_dir):
image_file = os.path.join(city_img_dir, basename)
suffix = "leftImg8bit.png"
assert basename.endswith(suffix), basename
basename = basename[:-len(suffix)]
instance_file = os.path.join(city_gt_dir,
basename + "gtFine_instanceIds.png")
label_file = os.path.join(city_gt_dir,
basename + "gtFine_labelIds.png")
json_file = os.path.join(city_gt_dir,
basename + "gtFine_polygons.json")
files.append((image_file, instance_file, label_file, json_file))
assert len(files), "No images found in {}".format(image_dir)
for f in files[0]:
assert PathManager.isfile(f), f
return files
def load_cityscapes_semantic(image_dir, gt_dir):
"""
Args:
image_dir (str): path to the raw dataset. e.g., "~/cityscapes/leftImg8bit/train".
gt_dir (str): path to the raw annotations. e.g., "~/cityscapes/gtFine/train".
Returns:
list[dict]: a list of dict, each has "file_name" and
"sem_seg_file_name".
"""
ret = []
# gt_dir is small and contain many small files. make sense to fetch to local first
gt_dir = PathManager.get_local_path(gt_dir)
for image_file, _, label_file, json_file in _get_cityscapes_files(
image_dir, gt_dir):
label_file = label_file.replace("labelIds", "labelTrainIds")
with PathManager.open(json_file, "r") as f:
jsonobj = json.load(f)
ret.append({
"file_name": image_file,
"sem_seg_file_name": label_file,
"height": jsonobj["imgHeight"],
"width": jsonobj["imgWidth"],
})
assert len(ret), f"No images found in {image_dir}!"
assert PathManager.isfile(
ret[0]["sem_seg_file_name"]
), "Please generate labelTrainIds.png with cityscapesscripts/preparation/createTrainIdLabelImgs.py" # noqa
return ret
def merge_from_file(self,
cfg_filename: str,
allow_unsafe: bool = True) -> None:
"""
Load content from the given config file and merge it into self.
Args:
cfg_filename: config filename
allow_unsafe: allow unsafe yaml syntax
"""
assert PathManager.isfile(
cfg_filename), f"Config file '{cfg_filename}' does not exist!"
loaded_cfg = self.load_yaml_with_base(cfg_filename,
allow_unsafe=allow_unsafe)
loaded_cfg = type(self)(loaded_cfg)
# defaults.py needs to import CfgNode
from .defaults import _C
latest_ver = _C.VERSION
assert (
latest_ver == self.VERSION
), "CfgNode.merge_from_file is only allowed on a config object of latest version!"
logger = logging.getLogger(__name__)
loaded_ver = loaded_cfg.get("VERSION", None)
if loaded_ver is None:
from .compat import guess_version
loaded_ver = guess_version(loaded_cfg, cfg_filename)
assert loaded_ver <= self.VERSION, "Cannot merge a v{} config into a v{} config.".format(
loaded_ver, self.VERSION)
if loaded_ver == self.VERSION:
self.merge_from_other_cfg(loaded_cfg)
else:
# compat.py needs to import CfgNode
from .compat import upgrade_config, downgrade_config
logger.warning(
"Loading an old v{} config file '{}' by automatically upgrading to v{}. "
"See docs/CHANGELOG.md for instructions to update your files.".
format(loaded_ver, cfg_filename, self.VERSION))
# To convert, first obtain a full config at an old version
old_self = downgrade_config(self, to_version=loaded_ver)
old_self.merge_from_other_cfg(loaded_cfg)
new_config = upgrade_config(old_self)
self.clear()
self.update(new_config)
def find_relative_file(original_file, relative_import_path, level):
cur_file = os.path.dirname(original_file)
for _ in range(level - 1):
cur_file = os.path.dirname(cur_file)
cur_name = relative_import_path.lstrip(".")
for part in cur_name.split("."):
cur_file = os.path.join(cur_file, part)
# NOTE: directory import is not handled. Because then it's unclear
# if such import should produce python module or DictConfig. This can
# be discussed further if needed.
if not cur_file.endswith(".py"):
cur_file += ".py"
if not PathManager.isfile(cur_file):
raise ImportError(
f"Cannot import name {relative_import_path} from "
f"{original_file}: {cur_file} has to exist.")
return cur_file
def inject_gan_datasets(cfg):
if cfg.D2GO_DATA.DATASETS.GAN_INJECTION.ENABLE:
name = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.NAME
cfg.merge_from_list(
["DATASETS.TRAIN", [name], "DATASETS.TEST", [name]])
json_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.JSON_PATH
assert PathManager.isfile(json_path), (
"{} is not valid!".format(json_path))
input_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.INPUT_SRC_DIR
assert PathManager.isfile(input_src_path), (
"{} is not valid!".format(input_src_path))
input_folder = "/tmp/{}/input".format(name)
gt_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.GT_SRC_DIR
if PathManager.isfile(gt_src_path):
gt_folder = "/tmp/{}/gt".format(name)
else:
gt_src_path = None
gt_folder = None
mask_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.MASK_SRC_DIR
if PathManager.isfile(mask_src_path):
mask_folder = "/tmp/{}/mask".format(name)
else:
mask_src_path = None
mask_folder = None
real_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.REAL_SRC_DIR
if PathManager.isfile(real_src_path):
real_folder = "/tmp/{}/mask".format(name)
real_json_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.REAL_JSON_PATH
assert PathManager.isfile(real_json_path), (
"{} is not valid!".format(real_json_path))
else:
real_src_path = None
real_folder = None
real_json_path = None
register_folder_dataset(
name,
json_path,
input_folder,
gt_folder,
mask_folder,
input_src_path,
gt_src_path,
mask_src_path,
real_json_path,
real_folder,
real_src_path,
)
def _get_kitti2cityscapes_files(image_dir, gt_dir, istest):
files = []
# scan through the directory
cities = PathManager.ls(image_dir)
logger.info(f"{len(cities)} cities found in '{image_dir}'.")
for city in cities:
city_img_dir = os.path.join(image_dir, city)
city_gt_dir = os.path.join(gt_dir, city)
for basename in PathManager.ls(city_img_dir):
image_file = os.path.join(city_img_dir, basename)
suffix = "leftImg8bit.png"
if basename.endswith(suffix) == basename:
basename = basename[:-len(suffix)]
if istest:
instance_file = None
json_file = None
foldname = os.path.basename(city_img_dir)
date = foldname[0:10]
seq = foldname[0:26]
# target_root = '/scratch1/zhusheng/kitti_eigen_inspred'
# target_root = '/media/shengjie/c9c81c9f-511c-41c6-bfe0-2fc19666fb32/Data/kitti_eigen_inspred'
# inspredpath = os.path.join(target_root, date, seq, 'insmap/image_02', basename)
# semanpredpath = os.path.join(target_root, date, seq, 'semanmap/image_02', basename)
# if os.path.exists(inspredpath) and os.path.exists(semanpredpath):
# continue
else:
instance_file = os.path.join(
city_gt_dir, basename + "gtFine_instanceIds.png")
json_file = os.path.join(city_gt_dir,
basename + "gtFine_polygons.json")
files.append((image_file, instance_file, json_file))
assert len(files), "No images found in {}".format(image_dir)
for f in files[0]:
if f is None:
continue
assert PathManager.isfile(f), f
return files
def inject_gan_datasets(cfg):
if cfg.D2GO_DATA.DATASETS.GAN_INJECTION.ENABLE:
name = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.NAME
cfg.merge_from_list([
"DATASETS.TRAIN",
list(cfg.DATASETS.TRAIN) + [name + "_train"], "DATASETS.TEST",
list(cfg.DATASETS.TEST) + [name + "_test"]
])
json_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.JSON_PATH
assert PathManager.isfile(json_path), (
"{} is not valid!".format(json_path))
image_dir = Path(tempfile.mkdtemp())
input_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.INPUT_SRC_DIR
assert PathManager.isfile(input_src_path), (
"{} is not valid!".format(input_src_path))
input_folder = os.path.join(image_dir, name, "input")
gt_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.GT_SRC_DIR
if PathManager.isfile(gt_src_path):
gt_folder = os.path.join(image_dir, name, "gt")
else:
gt_src_path = None
gt_folder = None
mask_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.MASK_SRC_DIR
if PathManager.isfile(mask_src_path):
mask_folder = os.path.join(image_dir, name, "mask")
else:
mask_src_path = None
mask_folder = None
real_src_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.REAL_SRC_DIR
if PathManager.isfile(real_src_path):
real_folder = os.path.join(image_dir, name, "real")
real_json_path = cfg.D2GO_DATA.DATASETS.GAN_INJECTION.REAL_JSON_PATH
assert PathManager.isfile(real_json_path), (
"{} is not valid!".format(real_json_path))
else:
real_src_path = None
real_folder = None
real_json_path = None
register_folder_dataset(
name + "_train",
json_path,
input_folder,
gt_folder,
mask_folder,
input_src_path,
gt_src_path,
mask_src_path,
real_json_path,
real_folder,
real_src_path,
)
register_folder_dataset(
name + "_test",
json_path,
input_folder,
gt_folder,
mask_folder,
input_src_path,
gt_src_path,
mask_src_path,
real_json_path,
real_folder,
real_src_path,
max_num=5000,
)