Add samples to the local cumulative buffers. A buffer will be allocated for each `data` item. Compared with `self.extend`, th

Returns a numpy array of ``self``. The array and ``self`` shares the same underlying storage if self is on cpu. Changes to ``self`` (

Assert that types and all values of two data objects are close. Args: actual: Pytorch Tensor or numpy array for comparison.

Imports an optional module specified by `module` string. Any importing related exceptions will be stored, and exceptions raise lazily whe

Get the config by id. Args: id: id to specify the expected position. See also :py:meth:`__getitem__`. defaul

Cast to ``dtype``, sharing data whenever possible. Args: dtype: dtypes such as np.float32, torch.float, "np.float32", fl

Utility to convert the input data to a PyTorch Tensor, if `track_meta` is True, the output will be a `MetaTensor`, otherwise, the output will

Return the `MetaTensor` as a `torch.Tensor`. It is OS dependent as to whether this will be a deep copy or not.

Returns a tuple of `vals`. Args: vals: input data to convert to a tuple. wrap_array: if `True`, treat the input numerical ar

Returns a copy of `tup` with `dim` values by either shortened or duplicated input. Raises: ValueError: When ``tup`` is a sequence an

Iterate across keys and optionally extra iterables. If key is missing, exception is raised if `allow_missing_keys==False` (default).

Set network(s) to eval mode and then return to original state at the end. Args: nets: Input network(s) Examples .. code-bl

Returns: dataset info dictionary.

Set random seed for modules to enable or disable deterministic training. Args: seed: the random seed to use, default is np.iinfo(np.

Set the ``id`` and the corresponding config content in pairs, see also :py:meth:`__setitem__`. For example, ``parser.update({"train::

Return the boolean as to whether metadata is tracked. If `True`, metadata will be associated its data by using subclasses of `MetaObj`. If `F

Save data into the cache dictionary. The metadata should have the following key: - ``'filename_or_obj'`` -- save the data corresponding to

`torch.max` with equivalent implementation for numpy Args: x: array/tensor. Returns: the maximum of x.

Convert source data to the same data type and device as the destination data. If `dst` is an instance of `torch.Tensor` or its subclass, conv

Convert to `MetaTensor`, `torch.Tensor` or `np.ndarray` from `MetaTensor`, `torch.Tensor`, `np.ndarray`, `float`, `int`, etc. Args:

Create an image with the before and after of the transform. Also update the transform's documentation to point to this image.

`torch.min` with equivalent implementation for numpy Args: x: array/tensor. Returns: the minimum of x.

Look up the option in the supported collection and return the matched item. Raise a value error possibly with a guess of the closest match.

Returns a copy of the MetaTensor instance. Args: kwargs: additional keyword arguments to `torch.clone`. See als

Extend the local buffers with new ("batch-first") data. A buffer will be allocated for each `data` item. Compared with `self.

Return state for serialization. Subclasses should override this method to return a dictionary of attributes that need to be

Get the currently expected spatial shape as if all the pending operations are executed. For tensors that have more than 3 spatial dim

Skips a test if downloading something raises an exception recognised to indicate a download has failed.

Test the ability to save `net` as a Torchscript object, reload it, and apply inference. The value `inputs` is forward-passed through the orig

Create an ITK object from ``self.create_backend_obj(self.obj, ...)`` and call ``itk.imwrite``. Args: filename: filename

De-collate a batch of data (for example, as produced by a `DataLoader`). Returns a list of structures with the original tensor's 0-th dimension s

Get the parsed result of ``ConfigItem`` with the specified ``id``. - If the item is ``ConfigComponent`` and ``instantiate=True``

Boolean to set whether metadata is tracked. If `True`, metadata will be associated its data by using subclasses of `MetaObj`. If `False`, the

get _test_data_config[keys0][keys1]...[keysN]

Return and pop the most recent transform. Args: data: dictionary of data or `MetaTensor` key: if data is a d

This test function is used to test the consistency between non-lazy and lazy transforms. Args: resampler: instance of a resampling tr

Utility to convert the input data to a numpy array. If passing a dictionary, list or tuple, recursively check every item and convert it to nu

Restore state from a dictionary. Subclasses should override this method to restore their state from the dictionary returned

Push to a stack of applied transforms of ``data``. Args: data: dictionary of data or `MetaTensor`. args: add

Create a normalization layer instance. For example, to create normalization layers: .. code-block:: python from monai.networks

Args: keys: keys of the corresponding items to be transformed. See also: :py:class:`monai.transforms.compose.MapT

Export the config content to the specified file path (currently support JSON and YAML files). Args: config: source confi

Close the read environment and set it to None, if it exists.

test that invertible_xform can bring to_invert back to im

Store the object `value` under the name `name` with description `desc`.

Create cartesian product, equivalent to a nested for-loop, combinations of the items dict. Args: items: dict of items to be combined.

Sliding window inference on `inputs` with `predictor`. The outputs of `predictor` could be a tensor, a tuple, or a dictionary of tensors.

Refine `user_provided` according to the `default`, and returns as a validated tuple. The validation is done for each element in `user_provid

Create an activation layer instance. For example, to create activation layers: .. code-block:: python from monai.networks.laye

Copy metadata from a `MetaObj` or an iterable of `MetaObj` instances. Args: input_objs: list of `MetaObj` to copy data f

Utility function to simplify the `batch_transform` or `output_transform` args of ignite components when handling dictionary or list of dictio

This method applies pending transforms to `data` tensors. Currently, only 2d and 3d inputs are supported. This method is designed to be

Convert to the `dtype` that corresponds to `data_type`. The input dtype can also be a string. e.g., `"float32"` becomes `torch.float32` or `n

Performs a single optimization step. Arguments: closure: A closure that reevaluates the model and returns the loss. Defaults to `

Get spatial dimension for the giving setting and check the validity of them. Missing input is allowed. But at least one of the input value sh

Return a noisy 2D image with `num_objs` circles and a 2D mask image. The maximum and minimum radii of the circles are given as `rad_max` and

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

Try to load package and get version. If not found, return `default`.

Using elements from affine, to create a new affine matrix by assigning the rotation/zoom/scaling matrix and the translation vector. When

Read whole slide image objects from given file or list of files. Args: data: file name or a list of file names to read.

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

Functional form of :class:`EmbeddingCollapseMetric`. Computes a suite of representational collapse indicators from embeddings and optional cl

Return a noisy 3D image and segmentation. Args: height: height of the image. The value should be larger than `2 * rad_max`.

Get the synchronized list of buffers. A typical usage is to generate the metrics report based on the raw metric details. Each

Download file from specified URL link, support process bar and hash check. Args: url: source URL link to download file. file

Get the report format by resolving the registered operations recursively. Returns: a dictionary with {keys: None} pairs.

Sets the discrete timesteps used for the diffusion chain. Supporting function to be run before inference. Args: num_infe

Read the config from specified JSON/YAML file or a dictionary and override the config content in the `self.config` dictionary.

Read training/validation data and output a model.

Args: keys: keys of the corresponding items to be transformed. See also: :py:class:`monai.transforms.compose.MapT

``execute_compose`` provides the implementation that the ``Compose`` class uses to execute a sequence of transforms. As well as being used by

Get a `module_name` logger with the specified format and date format. By default, the logger will print to `stdout` at the INFO level. If

`np.percentile` with equivalent implementation for torch. Pytorch uses `quantile`. For more details please refer to: https://pytorch.org/docs

For every value v in `labels`, the value in the output will be either 1 or 0. Each vector along the `dim`-th dimension has the "one-hot" form