def convert_to_herb_json(dataset_name, output_file, allow_cached=True):
"""
Converts dataset into COCO format and saves it to a json file.
dataset_name must be registered in DatasetCatalog and in herbarium's standard format.
Args:
dataset_name:
reference from the config file to the catalogs
must be registered in DatasetCatalog and in herbarium's standard format
output_file: path of json file that will be saved to
allow_cached: if json file is already present then skip conversion
"""
# TODO: The dataset or the conversion script *may* change,
# a checksum would be useful for validating the cached data
PathManager.mkdirs(os.path.dirname(output_file))
with file_lock(output_file):
if PathManager.exists(output_file) and allow_cached:
logger.warning(
f"Using previously cached COCO format annotations at '{output_file}'. "
"You need to clear the cache file if your dataset has been modified."
)
else:
logger.info(f"Converting annotations of dataset '{dataset_name}' to HERB format ...)")
coco_dict = convert_to_herb_dict(dataset_name)
logger.info(f"Caching COCO format annotations at '{output_file}' ...")
tmp_file = output_file + ".tmp"
with PathManager.open(tmp_file, "w") as f:
json.dump(coco_dict, f)
shutil.move(tmp_file, output_file)
def evaluate(self, img_ids=None):
"""
Args:
img_ids: a list of image IDs to evaluate on. Default to None for the whole dataset
"""
if self._distributed:
comm.synchronize()
predictions = comm.gather(self._predictions, dst=0)
predictions = list(itertools.chain(*predictions))
if not comm.is_main_process():
return {}
else:
predictions = self._predictions
if len(predictions) == 0:
self._logger.warning(
"[HERBEvaluator] Did not receive valid predictions.")
return {}
if self._output_dir:
PathManager.mkdirs(self._output_dir)
file_path = os.path.join(self._output_dir,
"instances_predictions.pth")
with PathManager.open(file_path, "wb") as f:
torch.save(predictions, f)
self._results = OrderedDict()
self._eval_predictions(predictions, img_ids=img_ids)
# Copy so the caller can do whatever with results
#return copy.deepcopy(self._results)
return None
def default_setup(cfg, args):
"""
Perform some basic common setups at the beginning of a job, including:
1. Set up the herbarium logger
2. Log basic information about environment, cmdline arguments, and config
3. Backup the config to the output directory
Args:
cfg (CfgNode or omegaconf.DictConfig): the full config to be used
args (argparse.NameSpace): the command line arguments to be logged
"""
output_dir = _try_get_key(cfg, "OUTPUT_DIR", "output_dir",
"train.output_dir")
if comm.is_main_process() and output_dir:
PathManager.mkdirs(output_dir)
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,
_highlight(
PathManager.open(args.config_file, "r").read(),
args.config_file),
))
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")
if isinstance(cfg, CfgNode):
logger.info("Running with full config:\n{}".format(
_highlight(cfg.dump(), ".yaml")))
with PathManager.open(path, "w") as f:
f.write(cfg.dump())
else:
LazyConfig.save(cfg, path)
logger.info("Full config saved to {}".format(path))
# make sure each worker has a different, yet deterministic seed if specified
seed = _try_get_key(cfg, "SEED", "train.seed", default=-1)
seed_all_rng(None if seed < 0 else 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 = _try_get_key(cfg,
"CUDNN_BENCHMARK",
"train.cudnn_benchmark",
default=False)
def after_step(self):
if self._profiler is None:
return
self._profiler.__exit__(None, None, None)
PathManager.mkdirs(self._output_dir)
out_file = os.path.join(
self._output_dir,
"profiler-trace-iter{}.json".format(self.trainer.iter))
if "://" not in out_file:
self._profiler.export_chrome_trace(out_file)
else:
# Support non-posix filesystems
with tempfile.TemporaryDirectory(
prefix="detectron2_profiler") as d:
tmp_file = os.path.join(d, "tmp.json")
self._profiler.export_chrome_trace(tmp_file)
with open(tmp_file) as f:
content = f.read()
with PathManager.open(out_file, "w") as f:
f.write(content)
def setup_logger(output=None,
distributed_rank=0,
*,
color=True,
name="herbarium",
abbrev_name=None):
"""
Initialize the herbarium logger and set its verbosity level to "DEBUG".
Args:
output (str): a file name or a directory to save log. If None, will not save log file.
If ends with ".txt" or ".log", assumed to be a file name.
Otherwise, logs will be saved to `output/log.txt`.
name (str): the root module name of this logger
abbrev_name (str): an abbreviation of the module, to avoid long names in logs.
Set to "" to not log the root module in logs.
By default, will abbreviate "herbarium" to "hb" and leave other
modules unchanged.
Returns:
logging.Logger: a logger
"""
logger = logging.getLogger(name)
logger.setLevel(logging.DEBUG)
logger.propagate = False
if abbrev_name is None:
abbrev_name = "hb" if name == "herbarium" else name
plain_formatter = logging.Formatter(
"[%(asctime)s] %(name)s %(levelname)s: %(message)s",
datefmt="%m/%d %H:%M:%S")
# stdout logging: master only
if distributed_rank == 0:
ch = logging.StreamHandler(stream=sys.stdout)
ch.setLevel(logging.DEBUG)
if color:
formatter = _ColorfulFormatter(
colored("[%(asctime)s %(name)s]: ", "green") + "%(message)s",
datefmt="%m/%d %H:%M:%S",
root_name=name,
abbrev_name=str(abbrev_name),
)
else:
formatter = plain_formatter
ch.setFormatter(formatter)
logger.addHandler(ch)
# file logging: all workers
if output is not None:
if output.endswith(".txt") or output.endswith(".log"):
filename = output
else:
filename = os.path.join(output, "log.txt")
if distributed_rank > 0:
filename = filename + ".rank{}".format(distributed_rank)
PathManager.mkdirs(os.path.dirname(filename))
fh = logging.StreamHandler(_cached_log_stream(filename))
fh.setLevel(logging.DEBUG)
fh.setFormatter(plain_formatter)
logger.addHandler(fh)
return logger