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

`np.concatenate` with equivalent implementation for torch (`torch.cat`).

compute a `spatial_size` mesh. - when ``homogeneous=True``, the output shape is (N+1, dim_size_1, dim_size_2, ..., dim_size_N) -

Get the first available key of `self.keys` in the input `data` dictionary. If no available key, return an empty tuple `()`.

Enhancement for PyTorch DataLoader default collate. If dataset already returns a list of batch data that generated in transforms, need to mer

Adds a factory function which returns the supplied class under the given name, with optional description.

Apply 1-D convolutions along each spatial dimension of `x`. Args: x: the input image. must have shape (batch, channels, H[, W, ...])

The key to store the stack of applied transforms.

Convert a value to a JSON-serializable type. Handles numpy arrays, Path objects, torch tensors, and other common types.

Computing the current spacing from the affine matrix. Args: affine: a d x d affine matrix. r: indexing based on the spatial

Applies the current model to a set of feature vectors. Args: features (torch.Tensor): feature vectors for each element.

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

This function is to do the metric reduction for calculated `not-nan` metrics of each sample's each class. The function also returns `not_nans

Split arguments in a way to be suitable for using with the factory types. If `args` is a string it's interpreted as the type name. Args:

Temporarily set the tracing status of a transform with a context manager.

Compares the report and the report_format that has only keys. Args: report: dict that has real values. report_format: dict t

Args: keys: the key of expected data in the dict, the inverse of ``transforms`` will be applied on it in-place. I

Aggregate values for merging. This method is being called in a loop and should add values to their corresponding location in the merg

``download_url`` and skip the tests if any downloading error occurs.

Returns a copy of `tup` with `dim` values by either shortened or padded with `pad_val` as necessary.

Get most recent matching transform for the current class from the sequence of applied operations. Args: data: dictionary

Load a single config file with specified file path (currently support JSON and YAML files). Args: filepath: path of targ

Create a temporary nifti image on the disk and return the image name. User is responsible for deleting the temporary file when done with it.

Recursively resolve `self.config` to replace the macro tokens with target content. Then recursively parse the config source, add ever

Args: input_noise: random noise, of the same shape as the desired sample. diffusion_model: model to sample from.

Register a statistical operation to the Analyzer and update the report_format. Args: key: value key in the report.

create a metatensor with fresh metadata if track_meta is True otherwise convert img into a torch tensor

Utility function to create the path to the output file based on the input filename (file name extension is not added by this function). W

create a 2D or 3D rotation matrix Args: spatial_dims: {``2``, ``3``} spatial rank radians: rotation radians when

create a translation matrix Args: spatial_dims: spatial rank shift: translate pixel/voxel for every spatial dim, defaults to

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

one dimensional Gaussian kernel. Args: sigma: std of the kernel truncated: tail length approx: discrete Gaussian ker

Return a dictionary with the relevant information pertaining to an applied transform.

Returns True if version `lhs` is earlier or equal to `rhs`. Args: lhs: version name to compare with `rhs`, return True if earlier or

Return True if ``monai._C`` (the compiled C extension providing ``grid_pull``) is not compiled with support for the given CUDA device's compu

Transform `data` with `transform`. If `data` is a list or tuple and `map_data` is True, each item of `data` will be transformed and this

Compute a module state_dict, of which the keys are the same as `dst`. The values of `dst` are overwritten by the ones from `src` whenever the

Create simulated data using create_test_image_3d. Args: dataroot: data directory path that hosts the "nii.gz" image files. s

For key-value pairs in the self.data, if the value is a callable, then this function will apply the callable to the input data.

Extract file to the output directory. Expected file types are: `zip`, `tar.gz` and `tar`. Args: filepath: the file path of compr

Forward pass through the UNet model. Args: x: Input tensor of shape (N, C, SpatialDims). timesteps: Timestep

Get the config content of current config item.

`moveaxis` for pytorch and numpy

Rescale the values of numpy array `arr` to be from `minv` to `maxv`. If either `minv` or `maxv` is None, it returns `(a - min_a) / (max_a - m

Resample ``self.data_obj`` if needed. This method assumes ``self.data_obj`` is a 'channel-last' ndarray. Args: meta_dic

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

Read a list of data dictionary `datalist` Args: datalist: the name of a JSON file listing the data, or a dictionary. basedir

Download file from URL and extract it to the output directory. Args: url: source URL link to download file. filepath: the fi

Args: x: input tensor (N, C, SpatialDims). timesteps: timestep tensor (N,). seg: Bx[LABEL_NC]x[SPATIAL DI

When we may be using TF32 mode, check the precision of matrix operation. If the checking result is greater than the threshold 0.001, set

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

Convert ``data_array`` into 'channel-last' numpy ndarray. Args: data_array: input data array with the channel dimension

Update a stack of applied/pending transforms metadata of ``data``. Args: data: dictionary of data or `MetaTensor`.

Create a Nibabel object from ``self.create_backend_obj(self.obj, ...)`` and call ``nib.save``. Args: filename: filename

Execute reduction logic for the output of `_compute_tensor`. Args: reduction: define mode of reduction to the metrics, w

Filtering `x` with `kernel` independently for each batch and channel respectively. Args: x: the input image, must have shape (batch,

Args: x: input tensor (N, C, SpatialDims). timesteps: timestep tensor (N,). context: context tensor (N, 1

Get the state dict of input object if has `state_dict`, otherwise, return object directly. For data parallel model, automatically convert it

Args: input_noise: random noise, of the same shape as the desired latent representation. autoencoder_model: first sta

Args: data: input data to load and transform to generate dataset for model. transform: a callable, sequence of callab

Args: boundaries: list defining lower and upper boundaries for the signal drop, lower and upper values need to be pos

Evaluate on client's local data. Args: data: `ExchangeObject` containing the current global model weights. e

Split the dataset into N partitions. It can support shuffle based on specified random seed. Will return a set of datasets, every dataset cont

Convert a file path to URI. if not absolute path, will convert to absolute path first. Args: path: input file path to convert, can b

perform one iteration of the CG method. It takes the current solution x, the current search direction p, the current residual r, and