def _download_from_github(repo: str, download_path: Path, filename: str, progress: bool = True):
if len(repo.split("/")) != 3:
raise ValueError("if source is `github`, repo should be in the form of `repo_owner/repo_name/release_tag`.")
repo_owner, repo_name, tag_name = repo.split("/")
if ".zip" not in filename:
filename += ".zip"
url = _get_git_release_url(repo_owner, repo_name, tag_name=tag_name, filename=filename)
filepath = download_path / f"{filename}"
download_url(url=url, filepath=filepath, hash_val=None, progress=progress)
extractall(filepath=filepath, output_dir=download_path, has_base=True)
def download(
name: Optional[str] = None,
bundle_dir: Optional[PathLike] = None,
source: str = "github",
repo: Optional[str] = None,
url: Optional[str] = None,
progress: bool = True,
args_file: Optional[str] = None,
):
"""
download bundle from the specified source or url. The bundle should be a zip file and it
will be extracted after downloading.
This function refers to:
https://pytorch.org/docs/stable/_modules/torch/hub.html
Typical usage examples:
.. code-block:: bash
# Execute this module as a CLI entry, and download bundle:
python -m monai.bundle download --name "bundle_name" --source "github" --repo "repo_owner/repo_name/release_tag"
# Execute this module as a CLI entry, and download bundle via URL:
python -m monai.bundle download --name "bundle_name" --url <url>
# Set default args of `run` in a JSON / YAML file, help to record and simplify the command line.
# Other args still can override the default args at runtime.
# The content of the JSON / YAML file is a dictionary. For example:
# {"name": "spleen", "bundle_dir": "download", "source": ""}
# then do the following command for downloading:
python -m monai.bundle download --args_file "args.json" --source "github"
Args:
name: bundle name. If `None` and `url` is `None`, it must be provided in `args_file`.
bundle_dir: target directory to store the downloaded data.
Default is `bundle` subfolder under`torch.hub get_dir()`.
source: place that saved the bundle.
If `source` is `github`, the bundle should be within the releases.
repo: repo name. If `None` and `url` is `None`, it must be provided in `args_file`.
If `source` is `github`, it should be in the form of `repo_owner/repo_name/release_tag`.
For example: `Project-MONAI/MONAI-extra-test-data/0.8.1`.
url: url to download the data. If not `None`, data will be downloaded directly
and `source` will not be checked.
If `name` is `None`, filename is determined by `monai.apps.utils._basename(url)`.
progress: whether to display a progress bar.
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.
"""
_args = _update_args(args=args_file,
name=name,
bundle_dir=bundle_dir,
source=source,
repo=repo,
url=url,
progress=progress)
_log_input_summary(tag="download", args=_args)
name_, bundle_dir_, source_, repo_, url_, progress_ = _pop_args(
_args,
name=None,
bundle_dir=None,
source="github",
repo=None,
url=None,
progress=True)
bundle_dir_ = _process_bundle_dir(bundle_dir_)
if url_ is not None:
if name is not None:
filepath = bundle_dir_ / f"{name}.zip"
else:
filepath = bundle_dir_ / f"{_basename(url_)}"
download_url(url=url_,
filepath=filepath,
hash_val=None,
progress=progress_)
extractall(filepath=filepath, output_dir=bundle_dir_, has_base=True)
elif source_ == "github":
if name_ is None or repo_ is None:
raise ValueError(
f"To download from source: Github, `name` and `repo` must be provided, got {name_} and {repo_}."
)
_download_from_github(repo=repo_,
download_path=bundle_dir_,
filename=name_,
progress=progress_)
else:
raise NotImplementedError(
f"Currently only download from provided URL in `url` or Github is implemented, got source: {source_}."
)