def build_evaluator(cls, cfg, dataset_name, output_folder=None):
"""
Create evaluator(s) for a given dataset.
This uses the special metadata "evaluator_type" associated with each builtin dataset.
For your own dataset, you can simply create an evaluator manually in your
script and do not have to worry about the hacky if-else logic here.
"""
if output_folder is None:
output_folder = os.path.join(cfg.OUTPUT_DIR, "inference")
evaluator_list = []
evaluator_type = MetadataCatalog.get(dataset_name).evaluator_type
if evaluator_type in ["sem_seg", "coco_panoptic_seg"]:
evaluator_list.append(
SemSegEvaluator(
dataset_name,
distributed=True,
output_dir=output_folder,
))
if evaluator_type in ["coco", "coco_panoptic_seg"]:
evaluator_list.append(
COCOEvaluator(dataset_name, output_dir=output_folder))
if evaluator_type == "coco_panoptic_seg":
evaluator_list.append(
COCOPanopticEvaluator(dataset_name, output_folder))
if evaluator_type == "cityscapes_instance":
assert (
torch.cuda.device_count() >= comm.get_rank()
), "CityscapesEvaluator currently do not work with multiple machines."
return CityscapesInstanceEvaluator(dataset_name)
if evaluator_type == "cityscapes_sem_seg":
assert (
torch.cuda.device_count() >= comm.get_rank()
), "CityscapesEvaluator currently do not work with multiple machines."
return CityscapesSemSegEvaluator(dataset_name)
elif evaluator_type == "pascal_voc":
return PascalVOCDetectionEvaluator(dataset_name)
elif evaluator_type == "lvis":
return LVISEvaluator(dataset_name, output_dir=output_folder)
if len(evaluator_list) == 0:
raise NotImplementedError(
"no Evaluator for the dataset {} with the type {}".format(
dataset_name, evaluator_type))
elif len(evaluator_list) == 1:
return evaluator_list[0]
return DatasetEvaluators(evaluator_list)
def setup(args):
cfg = get_cfg()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
default_setup(cfg, args)
setup_logger(output=cfg.OUTPUT_DIR,
distributed_rank=comm.get_rank(),
name="masktextspotter")
return cfg
def log_info(cfg, runner):
num_processes = get_num_processes_per_machine()
logger.info(
"Using {} processes per machine. Rank of current process: {}".format(
num_processes, comm.get_rank()
)
)
logger.info("Environment info:\n" + collect_env_info())
logger.info("Running with full config:\n{}".format(cfg))
logger.info("Running with runner: {}".format(runner))
def setup(args):
cfg = get_cfg()
get_meshrcnn_cfg_defaults(cfg)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
default_setup(cfg, args)
# Setup logger for "meshrcnn" module
setup_logger(output=cfg.OUTPUT_DIR, distributed_rank=comm.get_rank(), name="meshrcnn")
return cfg
def setup(args):
"""
Create configs and perform basic setups.
"""
cfg = get_cfg()
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
set_global_cfg(cfg)
default_setup(cfg, args)
# Setup loggers
setup_logger(output=cfg.OUTPUT_DIR,
distributed_rank=comm.get_rank(),
name="doublefewshot")
setup_logger(output=cfg.OUTPUT_DIR,
distributed_rank=comm.get_rank(),
name='OurPaper')
return cfg
def setup(args):
cfg = get_cfg()
add_gambler_config(cfg)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
default_setup(cfg, args)
setup_logger(output=cfg.OUTPUT_DIR, distributed_rank=comm.get_rank(), name="imbalance detection")
set_global_cfg(cfg)
return cfg
def setup(args):
if args.config_file.endswith(".yaml"):
cfg = get_cfg()
cfg.merge_from_file(args.config_file)
cfg.SOLVER.BASE_LR = 0.001 # Avoid NaNs. Not useful in this script anyway.
cfg.merge_from_list(args.opts)
cfg.freeze()
else:
cfg = LazyConfig.load(args.config_file)
cfg = LazyConfig.apply_overrides(cfg, args.opts)
setup_logger(distributed_rank=comm.get_rank())
return cfg
def _file_storage_gather(
storage: SingleProcessFileTensorStorage,
dst_rank: int = 0,
mode: str = "rb",
) -> Optional[MultiProcessFileTensorStorage]:
storage.storage_impl.close()
fpath_list = gather(storage.fpath, dst=dst_rank)
if get_rank() != dst_rank:
return None
rank_to_fpath = {i: fpath_list[i] for i in range(len(fpath_list))}
return MultiProcessFileTensorStorage(storage.data_schema, rank_to_fpath,
mode)
def default_setup(cfg, args):
"""
Perform some basic common setups at the beginning of a job, including:
1. Set up the detectron2 logger
2. Log basic information about environment, cmdline arguments, and config
3. Backup the config to the output directory
Args:
cfg (CfgNode): the full config to be used
args (argparse.NameSpace): the command line arguments to be logged
"""
output_dir = cfg.OUTPUT_DIR
if comm.is_main_process() and output_dir:
PathManager.mkdirs(output_dir)
if cfg.OWOD.COMPUTE_ENERGY:
PathManager.mkdirs(os.path.join(output_dir, cfg.OWOD.ENERGY_SAVE_PATH))
if cfg.OWOD.ENABLE_CLUSTERING:
PathManager.mkdirs(os.path.join(output_dir, cfg.OWOD.FEATURE_STORE_SAVE_PATH))
rank = comm.get_rank()
setup_logger(output_dir, distributed_rank=rank, name="fvcore")
logger = setup_logger(output_dir, distributed_rank=rank)
logger.info("Rank of current process: {}. World size: {}".format(rank, comm.get_world_size()))
logger.info("Environment info:\n" + collect_env_info())
logger.info("Command line arguments: " + str(args))
if hasattr(args, "config_file") and args.config_file != "":
logger.info(
"Contents of args.config_file={}:\n{}".format(
args.config_file, PathManager.open(args.config_file, "r").read()
)
)
logger.info("Running with full config:\n{}".format(cfg))
if comm.is_main_process() and output_dir:
# Note: some of our scripts may expect the existence of
# config.yaml in output directory
path = os.path.join(output_dir, "config.yaml")
with PathManager.open(path, "w") as f:
f.write(cfg.dump())
logger.info("Full config saved to {}".format(path))
# make sure each worker has a different, yet deterministic seed if specified
seed_all_rng(None if cfg.SEED < 0 else cfg.SEED + rank)
# cudnn benchmark has large overhead. It shouldn't be used considering the small size of
# typical validation set.
if not (hasattr(args, "eval_only") and args.eval_only):
torch.backends.cudnn.benchmark = cfg.CUDNN_BENCHMARK
def __init__(self, size: int):
"""
Args:
size (int): the total number of data of the underlying dataset to sample from
"""
self._size = size
assert size > 0
self._rank = comm.get_rank()
self._world_size = comm.get_world_size()
shard_size = (self._size - 1) // self._world_size + 1
self.begin = shard_size * self._rank
self.end = min(shard_size * (self._rank + 1), self._size)
def setup(args):
"""
Create configs and perform basic setups.
"""
cfg = get_cfg()
add_pointrend_config(cfg)
add_point_sup_config(cfg)
cfg.merge_from_file(args.config_file)
cfg.merge_from_list(args.opts)
cfg.freeze()
default_setup(cfg, args)
# Setup logger for "point_sup" module
setup_logger(output=cfg.OUTPUT_DIR, distributed_rank=comm.get_rank(), name="point_sup")
return cfg
def _ram_storage_gather(storage: SingleProcessRamTensorStorage,
dst_rank: int = 0) -> MultiProcessRamTensorStorage:
storage.storage_impl.seek(0, os.SEEK_SET)
# TODO: overhead, pickling a bytes object, can just pass bytes in a tensor directly
# see detectron2/utils.comm.py
data_list = gather(storage.storage_impl.read(), dst=dst_rank)
if get_rank() != dst_rank:
return None
rank_to_buffer = {
i: io.BytesIO(data_list[i])
for i in range(len(data_list))
}
storage = MultiProcessRamTensorStorage(storage.data_schema, rank_to_buffer)
return storage
