Recursively run collate logic and provide detailed loggings for debugging purposes. It reports results at the 'critical' level, is therefore

Euclidean distance transform, either GPU based with CuPy / cuCIM or CPU based with scipy. To use the GPU implementation, make sure cuCIM is a

Drop connect layer that drops individual connections. Differs from dropout as dropconnect drops connections instead of whole neurons as in dr

Given encoding indices of shape [B,D,H,W,1] embeds them in the quantized space [B, D, H, W, self.embedding_dim] and reshapes them to

Forwards an image through the spatial encoder, obtaining the latent mean and sigma representations. Args: x: BxCx[SPATIA

Forwards an image through the spatial encoder, obtaining the latent mean and sigma representations. Args: x: BxCx[SPATIA

Encode proposals with respect to ground truth (gt) boxes. Args: gt_boxes: gt boxes, Nx4 or Nx6 torch tensor. The box mod

ensemble the results using either "mean" or "vote" method Args: preds: a list of probability prediction in Tensor-Like f

Convert the image to MetaTensor (when meta is not None). If `affine` is in the `meta` dictionary, convert that to `torch.Tensor`, too

Erode 2D/3D binary mask. Args: mask: input 2D/3D binary mask, [N,C,M,N] or [N,C,M,N,P] torch tensor or ndarray. filter_size:

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

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

Writes the cached dict to a csv

Finalize step after the running of bundle workflow.

Finalize merging by dividing values by counts and return the merged tensor. Notes: To avoid creating a new tensor for th

Args: input: the shape should be BNH[WD]. target: the shape should be BNH[WD] or B1H[WD]. Raises:

Args: input: the shape should be BNH[WD]. The input should be the original logits due to the restriction of ``mon

Args: input (torch.Tensor): the shape should be BNH[WD]. The input should be the original logits due to the restr

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

Computes 1D gaussian kernel. Args: kernel_size: size of the gaussian kernel sigma: Standard deviation of the gaussian

"Generate patch filtering function for testing

Generate valid sample locations based on the specified ratios of label classes. Valid: samples sitting entirely within image, expected input

Generate valid sample locations based on the label with option for specifying foreground ratio Valid: samples sitting entirely within image,

Get the algo ensemble after ranking or a empty list if ranking was not started. Returns: A list of Algo

Returns a new array in `output_type`, the array shares the same underlying storage when the output is a numpy array. Changes to self

This function that return a :class:`~monai.data.box_utils.BoxMode` object giving a representation of box mode Args: mode: a represen

Get the latest version, as well as all existing versions of a bundle that is stored in the release of specified repository with the provided

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

This function is used to compute the surface distance from `y_pred` to `y` using the edges of the masks. Args: y_pred: the predicted

Generate extreme points from an image. These are used to generate initial segmentation for annotation models. An optional perturbation can be

Get tensor for the tests. The tensor is around (-1) or (+1), depending on is_positive.

Calculates the center of the ITK image based on its origin, size, and spacing. This center is equivalent to the implicit image center that MO

Computes the log-likelihoods for an input. Args: inputs: input images, NxCxHxW[xD] diffusion_model: model to

Computes the log-likelihoods of the latent representations of the input. Args: inputs: input images, NxCxHxW[xD]

get model specification by `idx`. `idx` could be index of the constant tuple of dict or the actual model ID.

Apply a morphological filter to a 2D/3D binary mask tensor. Args: mask_t: input 2D/3D binary mask, [N,C,M,N] or [N,C,M,N,P] torch te

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

Download resnet pretrained weights from https://huggingface.co/TencentMedicalNet Args: resnet_depth: depth of the pretrained model.

Get relative positional embeddings according to the relative positions of query and key sizes. Args: q_size (int): size of query

Get the resolved ``ConfigItem`` by id. Args: id: id name of the expected item. kwargs: keyword arguments to

Get the statistics information of the training process. Default to return the `rank`, `current_epoch`, `current_iteration`, `total_ep

This function is used to compute the surface distances from `seg_pred` to `seg_gt`. Args: seg_pred: the edge of the predictions.

Achieve metadata of a public The Cancer Imaging Archive (TCIA) dataset. This function makes use of The National Biomedical Imaging Archive (

Get list of non-background labels in an image. Args: img: Image to be processed. Shape should be [C, W, H, [D]] with C=1 if not onehot el

Returns the current weights of the model. Args: extra: Dict with additional information that can be provided by the FL s

Get the workflow type, it can be `None`, "train", or "infer".

Every combination of (a, (g, s), i) in (self.cell_anchors, zip(grid_sizes, strides), 0:spatial_dims) corresponds to a feature map.

Sample an image with respect to a deformation field. `interpolation` can be an int, a string or an InterpolationType. Possible values ar

Applies inverse shift and fourier transform. Only the spatial dimensions are transformed. Args: k: K-space data.

Check whether the config is an import statement (a special case of expression). Args: config: input config content to ch

Check whether the replacement thread is already started.

This function checks whether the box size is non-negative. Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box

Yield successive patches from `arr` of size `patch_size`. The iteration can start from position `start_pos` in `arr` but drawing from a padde

Args: item: data item to be hashed Returns: the corresponding hash key

The assumption is that the DL model makes better predictions than the provided label quality, hence the difference can be treated as a label

Fit a linear classifier on embeddings and return test accuracy. Used to validate that collapse scores predict downstream task performance. R

Load the metadata and nominated configuration files from a MONAI bundle without loading the network itself. This function will load the info

Handles the loading of c++ extension modules. Args: module_name: Name of the module to load. Must match the name of the

Traverse the source of the module structure starting with module `basemod`, loading all packages plus all files if `load_all` is True, exclud

Creates an animated gif out of an image tensor in 'CHWD' format and returns Summary. Args: tag: Data identifier image: The image,

Get the meta. Defaults to ``{}``.

`torch.mode` with equivalent implementation for numpy. Args: x: array/tensor. dim: dimension along which to perform `mode` (refer

Non-maximum suppression (NMS). Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be ``Stan

given a location (loc) and an original array (orig), paste a block array into it

Plots the learning rate range test. Args: skip_start: number of batches to trim from the start. skip_end: number of b

Predict network dict output with an inferer. Compared with directly output network(images), it enables a sliding window inferer that can be u

This function is used to prepare the `spacing` parameter to include batch dimension for the computation of surface distance, hausdorff distan

Preprocess the input images, including - validate of the inputs - pad the inputs so that the output spatial sizes are divisible by `size

Compute whether the current pytorch version is after or equal to the specified version. The current system pytorch version is determined by `

Look at the sform and qform of the nifti object and correct it if any incompatibilities with pixel dimensions Adapted from https://githu

Reset the buffers for cumulative tensors and the synced results.

Retrieve the object stored under a given key name.

Compute the root sum of squares (rss) of the data (typically done for multi-coil MRI samples) Args: x: Input array/tensor sp