def _update_args(args: Optional[Union[str, Dict]] = None,
ignore_none: bool = True,
**kwargs) -> Dict:
"""
Update the `args` with the input `kwargs`.
For dict data, recursively update the content based on the keys.
Args:
args: source args to update.
ignore_none: whether to ignore input args with None value, default to `True`.
kwargs: destination args to update.
"""
args_: Dict = args if isinstance(args, dict) else {} # type: ignore
if isinstance(args, str):
# args are defined in a structured file
args_ = ConfigParser.load_config_file(args)
# recursively update the default args with new args
for k, v in kwargs.items():
if ignore_none and v is None:
continue
if isinstance(v, dict) and isinstance(args_.get(k), dict):
args_[k] = _update_args(args_[k], ignore_none, **v)
else:
args_[k] = v
return args_
def verify_metadata(
meta_file: Optional[Union[str, Sequence[str]]] = None,
filepath: Optional[PathLike] = None,
create_dir: Optional[bool] = None,
hash_val: Optional[str] = None,
hash_type: Optional[str] = None,
args_file: Optional[str] = None,
**kwargs,
):
"""
Verify the provided `metadata` file based on the predefined `schema`.
`metadata` content must contain the `schema` field for the URL of schema file to download.
The schema standard follows: http://json-schema.org/.
Args:
meta_file: filepath of the metadata file to verify, if `None`, must be provided in `args_file`.
if it is a list of file paths, the content of them will be merged.
filepath: file path to store the downloaded schema.
create_dir: whether to create directories if not existing, default to `True`.
hash_val: if not None, define the hash value to verify the downloaded schema file.
hash_type: if not None, define the hash type to verify the downloaded schema file. Defaults to "md5".
args_file: a JSON or YAML file to provide default values for all the args in this function.
so that the command line inputs can be simplified.
kwargs: other arguments for `jsonschema.validate()`. for more details:
https://python-jsonschema.readthedocs.io/en/stable/validate/#jsonschema.validate.
"""
_args = _update_args(
args=args_file,
meta_file=meta_file,
filepath=filepath,
create_dir=create_dir,
hash_val=hash_val,
hash_type=hash_type,
**kwargs,
)
_log_input_summary(tag="verify_metadata", args=_args)
filepath_, meta_file_, create_dir_, hash_val_, hash_type_ = _pop_args(
_args, "filepath", "meta_file", create_dir=True, hash_val=None, hash_type="md5"
)
check_parent_dir(path=filepath_, create_dir=create_dir_)
metadata = ConfigParser.load_config_files(files=meta_file_)
url = metadata.get("schema")
if url is None:
raise ValueError("must provide the `schema` field in the metadata for the URL of schema file.")
download_url(url=url, filepath=filepath_, hash_val=hash_val_, hash_type=hash_type_, progress=True)
schema = ConfigParser.load_config_file(filepath=filepath_)
try:
# the rest key-values in the _args are for `validate` API
validate(instance=metadata, schema=schema, **_args)
except ValidationError as e: # pylint: disable=E0712
# as the error message is very long, only extract the key information
raise ValueError(
re.compile(r".*Failed validating", re.S).findall(str(e))[0] + f" against schema `{url}`."
) from e
logger.info("metadata is verified with no error.")
def ckpt_export(
net_id: Optional[str] = None,
filepath: Optional[PathLike] = None,
ckpt_file: Optional[str] = None,
meta_file: Optional[Union[str, Sequence[str]]] = None,
config_file: Optional[Union[str, Sequence[str]]] = None,
key_in_ckpt: Optional[str] = None,
args_file: Optional[str] = None,
**override,
):
"""
Export the model checkpoint to the given filepath with metadata and config included as JSON files.
Typical usage examples:
.. code-block:: bash
python -m monai.bundle ckpt_export network --filepath <export path> --ckpt_file <checkpoint path> ...
Args:
net_id: ID name of the network component in the config, it must be `torch.nn.Module`.
filepath: filepath to export, if filename has no extension it becomes `.ts`.
ckpt_file: filepath of the model checkpoint to load.
meta_file: filepath of the metadata file, if it is a list of file paths, the content of them will be merged.
config_file: filepath of the config file to save in TorchScript model and extract network information,
the saved key in the TorchScript model is the config filename without extension, and the saved config
value is always serialized in JSON format no matter the original file format is JSON or YAML.
it can be a single file or a list of files. if `None`, must be provided in `args_file`.
key_in_ckpt: for nested checkpoint like `{"model": XXX, "optimizer": XXX, ...}`, specify the key of model
weights. if not nested checkpoint, no need to set.
args_file: a JSON or YAML file to provide default values for `meta_file`, `config_file`,
`net_id` and override pairs. so that the command line inputs can be simplified.
override: id-value pairs to override or add the corresponding config content.
e.g. ``--_meta#network_data_format#inputs#image#num_channels 3``.
"""
_args = _update_args(
args=args_file,
net_id=net_id,
filepath=filepath,
meta_file=meta_file,
config_file=config_file,
ckpt_file=ckpt_file,
key_in_ckpt=key_in_ckpt,
**override,
)
_log_input_summary(tag="ckpt_export", args=_args)
filepath_, ckpt_file_, config_file_, net_id_, meta_file_, key_in_ckpt_ = _pop_args(
_args,
"filepath",
"ckpt_file",
"config_file",
net_id="",
meta_file=None,
key_in_ckpt="")
parser = ConfigParser()
parser.read_config(f=config_file_)
if meta_file_ is not None:
parser.read_meta(f=meta_file_)
# the rest key-values in the _args are to override config content
for k, v in _args.items():
parser[k] = v
net = parser.get_parsed_content(net_id_)
if has_ignite:
# here we use ignite Checkpoint to support nested weights and be compatible with MONAI CheckpointSaver
Checkpoint.load_objects(to_load={key_in_ckpt_: net},
checkpoint=ckpt_file_)
else:
copy_model_state(
dst=net,
src=ckpt_file_ if key_in_ckpt_ == "" else ckpt_file_[key_in_ckpt_])
# convert to TorchScript model and save with meta data, config content
net = convert_to_torchscript(model=net)
extra_files: Dict = {}
for i in ensure_tuple(config_file_):
# split the filename and directory
filename = os.path.basename(i)
# remove extension
filename, _ = os.path.splitext(filename)
if filename in extra_files:
raise ValueError(
f"filename '{filename}' is given multiple times in config file list."
)
extra_files[filename] = json.dumps(
ConfigParser.load_config_file(i)).encode()
save_net_with_metadata(
jit_obj=net,
filename_prefix_or_stream=filepath_,
include_config_vals=False,
append_timestamp=False,
meta_values=parser.get().pop("_meta_", None),
more_extra_files=extra_files,
)
logger.info(f"exported to TorchScript file: {filepath_}.")