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 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 build_hooks(self):
"""
Build a list of default hooks, including timing, evaluation,
checkpointing, lr scheduling, precise BN, writing events.
Returns:
list[HookBase]:
"""
cfg = self.cfg.clone()
cfg.defrost()
cfg.DATALOADER.NUM_WORKERS = 0 # save some memory and time for PreciseBN
ret = [
hooks.IterationTimer(),
hooks.LRScheduler(),
hooks.PreciseBN(
# Run at the same freq as (but before) evaluation.
cfg.TEST.EVAL_PERIOD,
self.model,
# Build a new data loader to not affect training
self.build_train_loader(cfg),
cfg.TEST.PRECISE_BN.NUM_ITER,
) if cfg.TEST.PRECISE_BN.ENABLED and get_bn_modules(self.model)
else None,
]
# Do PreciseBN before checkpointer, because it updates the model and need to
# be saved by checkpointer.
# This is not always the best: if checkpointing has a different frequency,
# some checkpoints may have more precise statistics than others.
if comm.is_main_process():
ret.append(
hooks.PeriodicCheckpointer(self.checkpointer,
cfg.SOLVER.CHECKPOINT_PERIOD))
def test_and_save_results():
self._last_eval_results = self.test(self.cfg, self.model)
return self._last_eval_results
# Do evaluation after checkpointer, because then if it fails,
# we can use the saved checkpoint to debug.
ret.append(hooks.EvalHook(cfg.TEST.EVAL_PERIOD, test_and_save_results))
if comm.is_main_process():
# Here the default print/log frequency of each writer is used.
# run writers in the end, so that evaluation metrics are written
ret.append(hooks.PeriodicWriter(self.build_writers(), period=20))
return ret
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("[COCOEvaluator] 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()
if "proposals" in predictions[0]:
self._eval_box_proposals(predictions)
if "instances" in predictions[0]:
self._eval_predictions(predictions, img_ids=img_ids)
# Copy so the caller can do whatever with results
return copy.deepcopy(self._results)
def evaluate(self):
results = OrderedDict()
for evaluator in self._evaluators:
result = evaluator.evaluate()
if is_main_process() and result is not None:
for k, v in result.items():
assert (
k not in results
), "Different evaluators produce results with the same key {}".format(k)
results[k] = v
return results
def test(cls, cfg, model, evaluators=None):
"""
Evaluate the given model. The given model is expected to already contain
weights to evaluate.
Args:
cfg (CfgNode):
model (nn.Module):
evaluators (list[DatasetEvaluator] or None): if None, will call
:meth:`build_evaluator`. Otherwise, must have the same length as
``cfg.DATASETS.TEST``.
Returns:
dict: a dict of result metrics
"""
logger = logging.getLogger(__name__)
if isinstance(evaluators, DatasetEvaluator):
evaluators = [evaluators]
if evaluators is not None:
assert len(
cfg.DATASETS.TEST) == len(evaluators), "{} != {}".format(
len(cfg.DATASETS.TEST), len(evaluators))
results = OrderedDict()
for idx, dataset_name in enumerate(cfg.DATASETS.TEST):
data_loader = cls.build_test_loader(cfg, dataset_name)
# When evaluators are passed in as arguments,
# implicitly assume that evaluators can be created before data_loader.
if evaluators is not None:
evaluator = evaluators[idx]
else:
try:
evaluator = cls.build_evaluator(cfg, dataset_name)
except NotImplementedError:
logger.warn(
"No evaluator found. Use `DefaultTrainer.test(evaluators=)`, "
"or implement its `build_evaluator` method.")
results[dataset_name] = {}
continue
results_i = inference_on_dataset(model, data_loader, evaluator)
results[dataset_name] = results_i
if comm.is_main_process():
assert isinstance(
results_i, dict
), "Evaluator must return a dict on the main process. Got {} instead.".format(
results_i)
logger.info("Evaluation results for {} in csv format:".format(
dataset_name))
print_csv_format(results_i)
if len(results) == 1:
results = list(results.values())[0]
return results
def train(self):
"""
Run training.
Returns:
OrderedDict of results, if evaluation is enabled. Otherwise None.
"""
super().train(self.start_iter, self.max_iter)
if len(self.cfg.TEST.EXPECTED_RESULTS) and comm.is_main_process():
assert hasattr(self, "_last_eval_results"
), "No evaluation results obtained during training!"
verify_results(self.cfg, self._last_eval_results)
return self._last_eval_results
def __init__(self,
model,
save_dir="",
*,
save_to_disk=None,
**checkpointables):
is_main_process = comm.is_main_process()
super().__init__(
model,
save_dir,
save_to_disk=is_main_process
if save_to_disk is None else save_to_disk,
**checkpointables,
)
self.path_manager = PathManager
def write_metrics(
loss_dict: Mapping[str, torch.Tensor],
data_time: float,
prefix: str = "",
) -> None:
"""
Args:
loss_dict (dict): dict of scalar losses
data_time (float): time taken by the dataloader iteration
prefix (str): prefix for logging keys
"""
metrics_dict = {
k: v.detach().cpu().item()
for k, v in loss_dict.items()
}
metrics_dict["data_time"] = data_time
# Gather metrics among all workers for logging
# This assumes we do DDP-style training, which is currently the only
# supported method in detectron2.
all_metrics_dict = comm.gather(metrics_dict)
if comm.is_main_process():
storage = get_event_storage()
# data_time among workers can have high variance. The actual latency
# caused by data_time is the maximum among workers.
data_time = np.max([x.pop("data_time") for x in all_metrics_dict])
storage.put_scalar("data_time", data_time)
# average the rest metrics
metrics_dict = {
k: np.mean([x[k] for x in all_metrics_dict])
for k in all_metrics_dict[0].keys()
}
total_losses_reduced = sum(metrics_dict.values())
if not np.isfinite(total_losses_reduced):
raise FloatingPointError(
f"Loss became infinite or NaN at iteration={storage.iter}!\n"
f"loss_dict = {metrics_dict}")
storage.put_scalar("{}total_loss".format(prefix),
total_losses_reduced)
if len(metrics_dict) > 1:
storage.put_scalars(**metrics_dict)