Args: spatial_dims: number of spatial dimensions, could be 1, 2 or 3. in_channels: number of input channels.

Mobile Inverted Residual Bottleneck Block. Args: spatial_dims: number of spatial dimensions. in_channels: nu

Args: inplanes: number of input channels. planes: number of output channels. ks: kernel size for one dime

Args: in_channel: number of input channels. out_channel: number of output channels. kernel_size: kernel s

Args: reduction: define the mode to reduce metrics, will only execute reduction on `not-nan` values, available r

Generate batch of patches and locations Args: patches: a tensor or list of tensors Yields: A batch of patche

Calculate perceptual loss in one of the axis used in the 2.5D approach. After the slices of one spatial axis is transformed into diff

Calculates the output image size when using _make_same_padder with a stride. Required for static padding. Args: input_image_size

Update the replacement data position in the total data.

Computes the target dimensions for resizing a whole slide image to match a user-specified resolution in microns per pixel (MPP).

Determines if user-provided MPP values are within a specified tolerance of the closest level's MPP and checks if the closest level ha

Computation logic for `y_pred` and `y` of an iteration, the data should be "batch-first" Tensors. A subclass should implement its own

Export a model defined in the parser to a new one specified by the converter. Args: converter: a callable object that takes a torch.

yield patches optionally post-processed by transform. Args: src: a iterable of image patches. apply_args: ot

Get the affine matrix of the image, it can be used to correct spacing, orientation or execute spatial transforms. Args:

Get a fake input shape e.g. [N, C, H, W] or [N, C, H, W, D], whose batch size is 1, from the given parser. Args: parser: a ConfigPar

Get the window index.

Compute the global mean of a masked tensor. This computes the mean over all elements, where values outside the mask are zero

Unbiased linear HSIC estimator.

Create a `_tracing` instance member to store the thread-local tracing state value.

Invert a single transform, delegating directly to nested ``Compose`` objects. When ``t`` is a ``Compose`` instance its own ``inverse()`` is calle

This function is used to load pretrained models. Adapted from PyTorch Hub 2D version: https://pytorch.org/vision/stable/models.html#id16.

Convert new-style state dict keys to legacy naming conventions. Args: new_sd: State dict with current key naming. inc

Process the data from original state up to the first random element. Args: item_transformed: The data to be transformed

Add a ProfileResult object to the queue.

Helper function for :py:class:`monai.networks.utils.replace_modules`.

Resizes the whole slide image to the specified resolution in microns per pixel (mpp). Args: wsi: whole slide image objec

Resizes the whole slide image to the specified resolution in microns per pixel (mpp). Args: wsi: whole slide image objec

Resizes the whole slide image to the specified resolution in microns per pixel (mpp). Args: wsi: whole slide image objec

Same code as https://github.com/pytorch/vision/blob/release/0.12/torchvision/models/detection/backbone_utils.py Except that ``in_channels_sta

Evaluate the expression or expression list given by `id`. The resolved values from the evaluations are not stored, allowing this to b

Execute reduction logic for the output of `compute_generalized_dice`. Returns: torch.Tensor: Aggregated metric value.

Typically `y_pred` and `y` are stored in the cumulative buffers at each iteration, This function reads the buffers and computes the a

A helper function to compute kernel_size, padding and stride for the given scale Args: scale: scale from a current scale level

`np.any` with equivalent implementation for torch. For pytorch, convert to boolean for compatibility with older versions. Args: x: i

Append with a new value, and an optional count. Any data type is supported that is convertable with torch.as_tensor() e.g. number

Get the object as a dictionary for backwards compatibility. This method does not make a deep copy of the objects. Args:

Compute center points of boxes Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be ``Stan

Compute the generalized intersection over union (GIoU) of a pair of boxes. The two inputs should have the same shape and the func return an (

Compute CrossEntropy loss for the input logits and target. Will remove the channel dim according to PyTorch CrossEntropyLoss:

Checks whether some files in the Decathlon datalist are missing. It would be helpful to check missing files before a heavy training run. Args

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

Compute complex-valued multiplication. Supports Ndim inputs with last dim equal to 2 (real/imaginary channels) Args: x: Input tensor

This function is used to compute confusion matrix related metric. Args: metric_name: [``"sensitivity"``, ``"specificity"``, ``"preci

Computes Intersection over Union (IoU) score metric from a batch of predictions. Args: y_pred: input data to compute, typical segmentatio

Compute mean IoU from confusion matrix values. Args: confusion_matrix: tensor with shape (..., 4) where the last dimension contains

Compute the crop slices based on specified `center & size` or `start & end` or `slices`. Args: roi_center: voxel coordin

Function to compute the Structural Similarity Index Measure (SSIM) and Contrast Sensitivity (CS) for a batch of images. Args: y_

Args: input: the shape should be BNH[WD], where N is the number of classes. target: the shape should be BNH[WD] or B1H[WD], where

Occlude with a constant occlusion. Multiplicative is zero, additive is constant value.

Recursively change the interpolation mode in the applied operation stacks, default to "nearest". See also: :py:class:`monai.transform.invers

Utility to convert padding mode between numpy array and PyTorch Tensor. Args: dst: target data to convert padding mode for, should b

Convert a 3D point coordinates into image mask. The returned mask has the same spatial size as `image_size` while the batch dimension is the

Rearrange the data array axes to make the `channel_dim`-th dim the last dimension and ensure there are ``spatial_ndim`` number of spa

Convert complex-valued data to a 2-channel PyTorch tensor. The real and imaginary parts are stacked along the last dimension. This functi

Utility to convert a model into TorchScript model and save to file, with optional input / output data verification. Args: model:

Check nifti object header's format, update the header if needed. In the updated image pixdim matches the affine. Args: img_nii:

control grid with two additional point in each direction

Utility to pre-process and create dataset list for Deepgrow training over on existing one. The input data list is normally a list of images a

To create semantic and image mock inputs for the network. Args: shape: input shape semantic_regions: number of semantic regio

Based on a latent space sample, forwards it through the Decoder. Args: z: Bx[Z_CHANNELS]x[LATENT SPACE SHAPE] R

Default function to prepare the data for current iteration. The input `batchdata` is either a single tensor, a pair of tensors, or a diction