Create the command to execute training.

compute a `spatial_size` mesh with the numpy API.

compute a `spatial_size` mesh with the torch API.

Perform Stain Deconvolution and return stain matrix for the image. Args: image: uint8 RGB image to perform stain deconvolution on

Execute dataset log operation based on the input dataset_dict. The dataset_dict should have a format like: {

Execute epoch level log operation. Default to track the values from Ignite `engine.state.metrics` dict and track the values o

Execute epoch level log operation. Default to print the values from Ignite `engine.state.metrics` dict and print the values o

Execute epoch level event write operation. Default to write the values from Ignite `engine.state.metrics` dict and write the

Execute iteration log operation based on Ignite `engine.state.output` data. Log the values from `self.output_transform(engine.state.o

Execute iteration log operation based on Ignite `engine.state.output` data. Print the values from `self.output_transform(engine.state

Execute iteration level event write operation based on Ignite `engine.state.output` data. Extract the values from `self.output_transf

Delete parameters in given dict, if they are already logged by current mlflow run. Args: param_dict: parameter dict to b

Recursively parse the nested data in config source, add every item as `ConfigItem` to the resolver. Args: config: config

Recursively resolve `self.config` to replace the relative ids with absolute ids, for example, `@##A` means `A` in the upper level. an

Downloads the algorithm templates release archive, and extracts it into a parent directory of the at_path folder. Returns a dictionary of the

First of all, download a series from TCIA according to `series_uid`. Then find all referenced series and download.

Calculate the location for each patch in a sliding-window manner

Calculate the location for each patch based on the mask at different resolution level

Compute and fill the cache content from data source. Args: indices: target indices in the `self.data` source to compute

Find all the classes and functions in the modules with specified `modnames`. Args: modnames: names of the target modules

Find all the modules start with MOD_START and don't contain any of `excludes`.

Computes 2D or 3D gaussian kernel. Args: spatial_dims: number of spatial dimensions of the input images. num_channels: number of

Raises: ValueError: When ``section`` is not one of ["training", "validation", "test"].

products of polynomials as bias field estimations

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

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

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

Get all case stats from a partitioned datalist. The function can only be called internally by get_all_case_stats. Args: r

Get the raw array data of the image, converted to Numpy array. Following PyTorch conventions, the returned array data has contiguous

Get the raw array data of the image, converted to Numpy array. Args: img: a Nibabel image object loaded from an image fi

Get the raw array data of the image. This function is used when `to_gpu` is set to True. Args: img: a Pydicom dataset ob

Bottom layer (bottleneck) in voxelmorph consists of a typical down layer followed by an upsample layer. Args: in_channel

Returns the bottom or bottleneck layer at the bottom of the network linking encode to decode halves. Args: in_channels:

Returns the block object defining a layer of the UNet structure including the implementation of the skip between encoding (down) and

Returns a single layer of the decoder part of the network.

Returns the decode part of the network by building up a sequence of layers returned by `_get_decode_layer`.

Returns a single layer of the encoder part of the network.

Returns the encode part of the network by building up a sequence of layers returned by `_get_encode_layer`.

yield frames and description from the segmentation image. This function is adapted from Highdicom: https://github.com/herrman

Returns the intermediate block of the network which accepts input from the encoder and whose output goes to the decoder.

Returns a layer accepting inputs with `in_channels` number of channels and producing outputs of `out_channels` number of channels. Th

Returns a layer accepting inputs with `in_channels` number of channels and producing outputs of `out_channels` number of channels. Th

Define the shape of merged tensors (non-padded and padded)

Get all the metadata of the loaded dict and return the meta dict. Args: dat: a dictionary object loaded from an h5 file.

Get all the metadata of the image and convert to dict type. Args: img: an ITK image object loaded from an image file.

Get the all the metadata of the image and convert to dict type. Args: img: a Nibabel image object loaded from an image f

Get the all the metadata of the image and convert to dict type. Args: img: a PIL Image object loaded from an image file.

Returns metadata of the extracted patch from the whole slide image. Args: wsi: the whole slide image object, from which

get the label name to index mapping

returns a lookup table. For every binary neighbour code (2x2x2 neighbourhood = 8 neighbours = 8 bits = 256 codes) it contains the surface nor

Try to connect to NGC.

Calculate the size and step required for splitting the image Args: The size of the input image

Extracts and returns a patch image form the whole slide image. Args: wsi: a whole slide image object loaded from a file