download bundle from the specified source or url. The bundle should be a zip file and it will be extracted after downloading. This functi

Download and extract Medical Model Archive (MMAR) from Nvidia Clara Train. See Also: - https://docs.nvidia.com/clara/ - Nvid

Convert a numpy dtype to its torch equivalent.

Flip boxes when the corresponding image is flipped Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is

Returns floor and ceil of the input Args: n: input number Returns: A tuple containing: (1) floor(n)

Read the package versions into a dictionary.

Get the default meta. Returns: default metadata.

Returns the down-sampling ratio of the whole slide image at a given level. Args: wsi: a whole slide image object loaded

Get the ensemble

Get the history of the bundleAlgo object with their names/identifiers

get_index_of_first takes a ``predicate`` and returns the index of the first transform that satisfies the predicate (ie. makes the pre

Returns validation scores of the model trained by the current Algo.

Initialize the bundle workflow before running.

Converts an ITK image to a MetaTensor object. Args: image: The ITK image to be converted. channel_dim: the channel dimension

Converts an ITK affine matrix (2x2 for 2D or 3x3 for 3D matrix and translation vector) to a MONAI affine matrix. Args: image: The IT

Load multiple config files into a single config dict. The latter config file in the list will override or add the former config file.

Load a state dict from a ViT model trained with an older version of MONAI where ``CrossAttentionBlock`` was unconditionally instantia

Normalize an array to [0, 1]

Read data from specified h5 file. Note that the returned object is a dictionary. Args: data: file name to read.

Read image data from specified file or files. Note that it returns a data object or a sequence of data objects. Args:

Resample `data` using the affine transformation defined by ``matrix``. Args: data: input data to be resampled. matrix: affin

Resolves to a tuple of available ``ImageWriter`` in ``SUPPORTED_WRITERS`` according to the filename extension key ``ext_name``. Args:

Select cross validation data based on data partitions and specified fold index. if a list of fold indices is provided, concatenate the partit

Set the ensemble method. Args: ensemble: the AlgoEnsemble to build.

Set the number of cross validation folds for all algos. Args: num_fold: a positive integer to define the number of folds

Converts row and column subscripts into linear indices, basically the copy of the MATLAB function of the same name. https://www.mathwo

Given ``affine`` defined for coordinates in the pixel space, compute the corresponding affine for the normalized coordinates. Args:

`np.unravel_index` with equivalent implementation for torch. Args: idx: index to unravel. shape: shape of array/tensor. Retu

Update operations for nested label format. Operation value in report_format will be resolved to a dict with only keys. Args:

Write the given version number to the given _version.py file.

Args: spatial_dims: number of spatial dims in_channels: number of input channels num_channel_initial: num

Args: spatial_dims: number of spatial dimensions. in_channels: number of input channels. Must equal ``out_channels``.

Args: transform: the previously applied transform. nearest_interp: whether to use `nearest` interpolation mode when i

Args: project_name: ClearML project name, default to 'MONAI'. task_name: ClearML task name, default to 'monai_experim

A fast approximation of the cumulative distribution function of the standard normal. Code adapted from https://github.com/openai/impr

Compute the class-conditional mean of a masked tensor. This computes the mean over only the masked (non-zero) elements, i.e.,

Check the LMDB cache and write the cache if needed. py-lmdb doesn't have a good support for concurrent write. This method can be used

Get the array data of the image. If `RescaleSlope` and `RescaleIntercept` are available, the raw array data will be rescaled. The out

Return the cap. If multiprocessing, create a new one. Else return the one from construction time.

Return the max compute capability (major*100+minor) the _C extension was compiled for, or 0 if the extension is not available (no build info).

Get all the metadata of the image and convert to dict type. Args: img: a Pydicom dataset object.

Return True if this is the parent process.

Extract the latest versions from the data dictionary. Args: data: the data dictionary. max_versions: the maximum number of v

Create a reference and test model pair with identical initial weights.

Effective rank score computed separately per class. Detects asymmetric collapse: one class may use 400 dimensions while another collapses to

Resolve an ROI parameter from the data dictionary if it is a string key. Args: val: the ROI parameter value. If a string, it is u

Calculate and round number of filters based on width coefficient multiplier and depth divisor. Args: filters: number of input filter

Compute average precision Args: dataset_statistics (dict): computed statistics over dataset - `counts`:

Compute average recall Args: dataset_statistics (dict): computed statistics over dataset - `counts`: Nu

Write scale value into TensorBoard. Default to call `SummaryWriter.add_scalar()`. Args: _engine: Ignite Engine,

Execute reduction for the confusion matrix values. Args: compute_sample: when reducing, if ``True``, each sample's metri

Import the Algo object from a JSON file (pickle-free serialization). Args: filename: the name of the saved file (algo_object.json or

`np.ascontiguousarray` with equivalent implementation for torch (`contiguous`). Args: x: array/tensor. kwargs: if `x` is PyTorch

Register a set of Ignite Event-Handlers to a specified Ignite engine. Args: engine: Ignite Engine, it can be a trainer,

Attaches current metric to provided engine. On the end of engine's run, `engine.state.metrics` dictionary will contain computed metri

Distance of center points between two sets of boxes Args: boxes1: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode i

Check if the all keys in kwargs exist in the __init__ method of the class. Args: cls: the class to check. kwargs: kwargs to

Utility to check whether the parent directory of the `path` exists. Args: path: input path to check the parent directory. cr

This function clips the ``boxes`` to makes sure the bounding boxes are within the image. Args: boxes: bounding boxes, Nx4 or Nx6 tor

Compute the target spatial size which should be divisible by `k`. Args: spatial_shape: original spatial shape. k: the target

Args: y_pred: [N, C, H, W, D] or [N, C, H, W] or [N, C, H] where N is repeats, C is channels and H, W, D stand for Height, Wi

Get the nested value in a list of dictionary that shares the same structure iteratively on all keys. It returns a dictionary with keys with t

Convert given boxes to standard mode. Standard mode is "xyxy" or "xyzxyz", representing box format of [xmin, ymin, xmax, ymax] or [xmin,