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 --ckpt_file ... Args: net_id: ID
(
net_id: str | None = None,
filepath: PathLike | None = None,
ckpt_file: str | None = None,
meta_file: str | Sequence[str] | None = None,
config_file: str | Sequence[str] | None = None,
key_in_ckpt: str | None = None,
use_trace: bool | None = None,
input_shape: Sequence[int] | None = None,
args_file: str | None = None,
converter_kwargs: Mapping | None = None,
**override: Any,
)
| 1435 | |
| 1436 | |
| 1437 | def ckpt_export( |
| 1438 | net_id: str | None = None, |
| 1439 | filepath: PathLike | None = None, |
| 1440 | ckpt_file: str | None = None, |
| 1441 | meta_file: str | Sequence[str] | None = None, |
| 1442 | config_file: str | Sequence[str] | None = None, |
| 1443 | key_in_ckpt: str | None = None, |
| 1444 | use_trace: bool | None = None, |
| 1445 | input_shape: Sequence[int] | None = None, |
| 1446 | args_file: str | None = None, |
| 1447 | converter_kwargs: Mapping | None = None, |
| 1448 | **override: Any, |
| 1449 | ) -> None: |
| 1450 | """ |
| 1451 | Export the model checkpoint to the given filepath with metadata and config included as JSON files. |
| 1452 | |
| 1453 | Typical usage examples: |
| 1454 | |
| 1455 | .. code-block:: bash |
| 1456 | |
| 1457 | python -m monai.bundle ckpt_export network --filepath <export path> --ckpt_file <checkpoint path> ... |
| 1458 | |
| 1459 | Args: |
| 1460 | net_id: ID name of the network component in the config, it must be `torch.nn.Module`. |
| 1461 | Default to "network_def". |
| 1462 | filepath: filepath to export, if filename has no extension it becomes `.ts`. |
| 1463 | Default to "models/model.ts" under "os.getcwd()" if `bundle_root` is not specified. |
| 1464 | ckpt_file: filepath of the model checkpoint to load. |
| 1465 | Default to "models/model.pt" under "os.getcwd()" if `bundle_root` is not specified. |
| 1466 | meta_file: filepath of the metadata file, if it is a list of file paths, the content of them will be merged. |
| 1467 | Default to "configs/metadata.json" under "os.getcwd()" if `bundle_root` is not specified. |
| 1468 | config_file: filepath of the config file to save in TorchScript model and extract network information, |
| 1469 | the saved key in the TorchScript model is the config filename without extension, and the saved config |
| 1470 | value is always serialized in JSON format no matter the original file format is JSON or YAML. |
| 1471 | it can be a single file or a list of files. if `None`, must be provided in `args_file`. |
| 1472 | key_in_ckpt: for nested checkpoint like `{"model": XXX, "optimizer": XXX, ...}`, specify the key of model |
| 1473 | weights. if not nested checkpoint, no need to set. |
| 1474 | use_trace: whether using `torch.jit.trace` to convert the PyTorch model to TorchScript model. |
| 1475 | input_shape: a shape used to generate the random input of the network, when converting the model to a |
| 1476 | TorchScript model. Should be a list like [N, C, H, W] or [N, C, H, W, D]. If not given, will try to |
| 1477 | parse from the `metadata` config. |
| 1478 | args_file: a JSON or YAML file to provide default values for all the parameters of this function, so that |
| 1479 | the command line inputs can be simplified. |
| 1480 | converter_kwargs: extra arguments that are needed by `convert_to_torchscript`, except ones that already exist |
| 1481 | in the input parameters. |
| 1482 | override: id-value pairs to override or add the corresponding config content. |
| 1483 | e.g. ``--_meta#network_data_format#inputs#image#num_channels 3``. |
| 1484 | |
| 1485 | """ |
| 1486 | _args = update_kwargs( |
| 1487 | args=args_file, |
| 1488 | net_id=net_id, |
| 1489 | filepath=filepath, |
| 1490 | meta_file=meta_file, |
| 1491 | config_file=config_file, |
| 1492 | ckpt_file=ckpt_file, |
| 1493 | key_in_ckpt=key_in_ckpt, |
| 1494 | use_trace=use_trace, |
nothing calls this directly
no test coverage detected
searching dependent graphs…