Set the options for the underlying writer by updating the `self.*_kwargs` dictionaries. The arguments correspond to the following us

Set the prediction params for all algos. Args: params: a dict that defines the overriding key-value pairs during predict

Report the acc to NNI server.

Set the accuracy score

Set the `spatial_size` and `spatial_zoom` attributes used for interpolating the field to the given dimension, or not interpolate at a

Get hashable transforms, and then hash them. Hashable transforms are deterministic transforms that inherit from `Transform`. We stop a

Set the Optuna trial

Set validator if not setting in the __init__().

FL(pt) = -alpha * (1 - pt)**gamma * log(pt) where p = sigmoid(x), pt = p if label is 1 or 1 - p if label is 0

Applies data consistency to input x. Suppose x is an intermediate estimate of the kspace and ref_kspace is the reference under-sample

Perform soft dilation on the input image Args: img: the shape should be BCH(WD) Adapted from: https://github.com/jocpae

FL(pt) = -alpha * (1 - pt)**gamma * log(pt) where p_i = exp(s_i) / sum_j exp(s_j), t is the target (ground truth) class, and s_j is the

Sort the best_metrics

Functional implementation of resampling the input image to the specified ``dst_affine`` matrix and ``spatial_size``. This function operates e

Split `src` string into two parts: a config file path and component id. The file path should end with `(json|yaml|yml)`. The componen

Check MLFlow status and start if not active.

`torch.std` with equivalent implementation for numpy Args: x: array/tensor. Returns: the standard deviation of x.

Step function propagating the sample with the linear multi-step method. This has one forward pass with multiple times to approximate

Step function propagating the sample with the Runge-Kutta method. RK takes 4 forward passes to approximate the solution to the differ

Args: operator (function): The operator function that takes in an input tensor x and returns an output tensor y. We will use this

Run the training for all the models specified by the configurations. Note: to set the number of GPUs to use, use ``gpu_id_for_all`` i

Create the line command for subprocess call for parallel training. Note: to set the number of GPUs to use, use ``gpu_id_for_all`` ins

Create the line command for subprocess call for parallel training. Args: configs: configurations that should be trained.

Transform coordinates using an affine transformation matrix. Args: data: The input coordinates are assumed to be in the

Unwrap a function value and generates the same set keys in a dict when the function is actually called in runtime Args:

Args: output: sequence with contents [y_pred, y]. Raises: ValueError: When ``output`` length is not 2. metri

With all the references in ``refs``, update the input config content with references and return the new config. Args:

Find the documentation for a given transform and if it's missing, add a pointer to the transform's example image.

Translate the parameter from monai bundle to meet NNI requirements. Args: params: a dict of parameters.

Translate the parameter from monai bundle. Args: params: a dict of parameters.

Update point_coords with respect to patch coords. If point is outside of the patch, remove the coordinates and set label to -1.

Match regular expression for the input string to update content with the references. The reference part starts with ``"@"``, like: ``

Image has been padded by sliding window inferer. The related padding need to be performed outside of slidingwindow inferer.

Perform validation on single model. Args: config: configuration that should be trained. fold: fold of the 5-

Verify the provided `metadata` file based on the predefined `schema`. `metadata` content must contain the `schema` field for the URL of schem

Verify the input and output data shape and data type of network defined in the metadata. Will test with fake Tensor data according to the req

Verify whether the specified file or files format is supported by ITK reader. Args: filename: file name or a list of fil

Try to determine the version from _version.py if present.

Try to determine the version from the parent directory name. Source tarballs conventionally unpack into a directory that includes both the pr

Try to determine the version from the parent directory name. Source tarballs conventionally unpack into a directory that includes both the pr

Warm up the Kvikio library to initialize the internal buffers, cuFile, GDS, etc. This can accelerate the data loading process when `t

Warm up the Kvikio library to initialize the internal buffers, cuFile, GDS, etc. This can accelerate the data loading process when `t

Compute the voxel-wise Wasserstein distance between the flattened prediction and the flattened labels (ground_truth) with respect

Computes `n_samples` of random patch sampling locations, given the sampling weight map `w` and patch `spatial_size`. Args: spatial_s

window reverse operation based on: "Liu et al., Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/abs

Map `op`, using `mapfunc`, to each tuple derived from zipping the iterables in `vals`.

Functional implementation of zoom. This function operates eagerly or lazily according to ``lazy`` (default ``False``). Args:

for numpy Interoperability, so that we can compute ``np.sum(MetaTensor([1.0]))``.

For numpy interoperability, so that we can compute ``MetaTensor([1.0]) >= np.asarray([1.0])``. This is for pytorch > 1.8.

Raises: OptionalImportError: When you call this method.

Run the filtering. Arguments: data: ExchangeObject containing some data. Returns: ExchangeObject: f

Example filter that doesn't filter anything but only prints data summary. Arguments: data: ExchangeObject containing som

Execute basic computation for model prediction `y_pred` and ground truth `y` (optional). It supports inputs of a list of "channel-fir

Execute basic computation for model prediction and ground truth. It can support both `list of channel-first Tensor` and `batch-first

Args: y_pred: Predicted segmentation, typically segmentation model output. It must be N-repeats, repeat-first ten

Args: y_pred: Predicted segmentation, typically segmentation model output. It must be N-repeats, repeat-first ten

Compute the metric for the given prediction and ground truth. Args: y_pred: input predictions with shape (batch_size, nu

Compute collapse scores. Args: embeddings: float tensor of shape ``[N, D]``. Required. labels: integer class labels o

Args: data: is a dictionary containing (key,value) pairs from the loaded dataset Returns: th

Args: data: is a dictionary containing (key,value) pairs from the loaded dataset Returns: th

This transform can support to crop ND spatial (channel-first) data. It also supports pseudo ND spatial data (e.g., (C,H,W) is a pseud