Compute the absolute value of a complex tensor. Args: x: Input tensor with 2 channels in the last dimension representing real and im

Compute complex conjugate of a tensor. Supports Ndim inputs with last dim equal to 2 (real/imaginary channels) Args: x: Input tensor

Performs layer mean-std normalization for complex data. Normalization is done for each batch member along each part (part refers to real and

Computes Average Precision (AP). AP is a useful metric to evaluate a classifier when the classes are imbalanced. It summarizes a Precision-Recall

Compute the start points and end points of bounding box to crop. And adjust bounding box coords to be divisible by `k`.

Compute whether the current system GPU CUDA compute capability is after or equal to the specified version. The current system GPU CUDA comput

Computes Dice score metric for a batch of predictions. This performs the same computation as :py:class:`monai.metrics.DiceMetric`, which is p

This function is modified from the official evaluation code of `CAMELYON 16 Challenge <https://camelyon16.grand-challenge.org/>`_, and used t

This function is modified from the official evaluation code of `CAMELYON 16 Challenge <https://camelyon16.grand-challenge.org/>`_, and used t

This function is modified from the official evaluation code of `CAMELYON 16 Challenge <https://camelyon16.grand-challenge.org/>`_, and used t

This function is modified from the official evaluation code of `CAMELYON 16 Challenge <https://camelyon16.grand-challenge.org/>`_, and used t

Get importance map for different weight modes. Args: patch_size: Size of the required importance map. This should be either H, W [,D].

Computing region masks based on: "Liu et al., Swin Transformer: Hierarchical Vision Transformer using Shifted Windows <https://arxiv.org/abs/2

dynamically compute the pad width according to the spatial shape. the output is the amount of padding for all dimensions including th

Computes Panoptic Quality (PQ). If specifying `metric_name` to "SQ" or "RQ", Segmentation Quality (SQ) or Recognition Quality (RQ) will be returne

Computes Area Under the Receiver Operating Characteristic Curve (ROC AUC). Referring to: `sklearn.metrics.roc_auc_score <https://scikit-learn.org/

Combine auto results with point click response. The auto results have shape [B, 1, H, W, D] which means B foreground masks from a sin

Convert box to int16 mask image, which has the same size with the input image. Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor

Helper function to convert global weights to local weights format

Convert int16 mask image to box, which has the same size with the input image Args: boxes_mask: int16 array, sized (num_box, H, W).

Utility to join pandas tables, select rows, columns and generate groups. Will return a list of dictionaries, every dictionary maps to a row o

returns a copy of the data. list and dict are shallow copied for efficiency purposes.

Copy object or tuple/list/dictionary of objects to ``device``. Args: obj: object or tuple/list/dictionary of objects to move to ``de

Return a 3D image with a sphere inside. Voxel values will be 1 inside the sphere, and 0 elsewhere. Args: radius: radius of spher

Return a 3D image with a sphere inside. Voxel values will be 1 inside the sphere, and 0 elsewhere. Args: radius: radius of spher

Crop and pad based on the bounding box.

Detect if there is anything that may enable TF32 mode by default. If any, show a warning message.

Generate distance transform. Args: img (np.ndarray): input mask as NCHWD or NCHW. Returns: np.ndarray: Dista

Pad input to feed into the network (torch script compatible) Args: x: input of shape (B,C,H,W) for 2D data or (B,C,H,W,D) for 3D dat

Download a dicom series from a public The Cancer Imaging Archive (TCIA) dataset. The downloaded compressed file will be stored in `download_d

Convert a torch dtype to its numpy equivalent.

assert equal state_dict (for the shared keys between st_1 and st_2).

Applies the callables to the data, and convert the numerics to list or Python numeric types (int/float). Args: d

Save all the BundleAlgo in the history to algo_object.json in each individual folder. Args: history: a List of Bundle. Typically, th

Please refer to :py:class:`monai.transforms.AddExtremePointsChannel` for the usage. Applies a gaussian filter to the extreme points image. T

Computes the actual feature map size given `nn_module` and the target_layer name. Args: input_size: shape of the input te

Pytorch-based fft for spatial_dims-dim signals. "centered" means this function automatically takes care of the required ifft and fft shifts.

Create a filename based on the input ``subject`` and ``idx``. The output filename is formed as: ``output_dir/[subject/]

Sort the patches based on the sum of their intensity, and just keep `self.num_patches` of them. Args: image_np: a numpy.

Finalize step after the running of bundle workflow.

Perform final operations for merging patches and return the final merged output. Returns: The results of merged patches,

Find the best model configurations. Args: plans: list of plan identifiers. Default: nnUNetPlans. configs: li

Flatten the nested dictionary to a flat dictionary.

Recursively flatten input and yield all instances of `MetaObj`. This means that for both `torch.add(a, b)`, `torch.stack([a, b])` (an

`np.floor_divide` with equivalent implementation for torch. As of pt1.8, use `torch.div(..., rounding_mode="floor")`, and before that, use `t

Args: x: input tensor (N, C, H, W, [D]). timesteps: timestep tensor (N,). controlnet_cond: controlnet con

Forward pass of the MedNeXtBlock. Args: x (torch.Tensor): Input tensor. Returns: torch.Tensor: Outp

Args: input: the shape should be BNH[WD]. target: the shape should be BNH[WD]. Raises: ValueErro

Args: pred: the shape should be BNH[WD]. target: the shape should be BNH[WD]. Raises: ValueError:

Compute the logarithm of the Hausdorff Distance Transform Loss. Args: input (torch.Tensor): The shape should be BNHW[D],

Args: input: the shape should be BNH[WD], where N is the number of classes. target: the shape should be BNH[WD] or B1

A utility function to help freeze specific layers. Args: model: a source PyTorch model to freeze layer. freeze_vars: a regul

Get a BlockArgs object from a string notation of arguments. Args: block_string (str): A string notation of arguments.

Generate elements needed in decoding and topology. - `transfer_mtx`: feasible path activation matrix (denoted as T) given a node

Utility function to generate parameter groups with different LR values for optimizer. The output parameter groups have the same order as `lay

If image is 3d, get the central slice. If is already 2d, return as-is. If image is label, set 0 to np.nan.

Try different codecs, see which are available. Returns a dictionary with of available codecs with codecs as keys and file extensions as values

Create a binary kernel to extract the patches. The window size HxWxD will create a (H*W*D)xHxWxD kernel.

Get the full module name of the class or function with specified ``name``. If target component name exists in multiple packages or mo

Extract data array and metadata from the loaded data and return them. This function returns two objects, first is numpy array of imag

Extract data array and metadata from loaded image and return them. This function returns two objects, first is numpy array of image d

Extract data array and metadata from loaded image and return them. This function must return two objects, the first is a numpy array

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

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

Get dtype bound value Args: dtype: dtype to get bound value Returns: (bound_min_value, bound_max_value)

Get the input image size for a given efficientnet model. Args: model_name: name of model to initialize, can be from [efficientnet-b0

Get the filename from the URL link.

Get foreground image pixel values and mask out the non-labeled area. Args image: ndarray image to segment. label: ndarray th

Get the ID name of current config item, useful to identify config items during parsing.

Return a cached or new identity grid depends on the availability. Args: spatial_size: non-dynamic spatial size

Return IoU thresholds needed for this metric in an numpy array Returns: Sequence[float]: IoU thresholds [M], M is the nu

Get the ``ConfigItem`` by id. If ``resolve=True``, the returned item will be resolved, that is, all the reference strings ar