Forward pass of Restormer. Processes input through encoder-decoder architecture with skip connections. Args: inp_img: Inpu

Args: i: Input tensor Returns: list of outputs and another list of lists with the intermediate features

Args: x: input tensor Returns: list of intermediate features, with the last element being the output.

Args: x: Tensor in shape (batch, channel, spatial_1[, spatial_2, ...).

Args: x: in shape (batch, inplanes, spatial_1, spatial_2).

Args: pred: the shape should be B[NDHW]. target: the shape should be same as the pred shape. Raises:

Args: input: the shape should be B1HW[D], where the channel dimension is 1 for binary classification. target: the sha

Positionally encode points that are not normalized to [0,1].

Since the output of HoVerNet is a dictionary, this function is to extend `monai.handlers.from_engine` to work with HoVerNet. If data is

Combine point results with auto results using gaussian. Args: logits: automatic branch results, [B, 1, H, W, D].

For Gaussian occlusion, Multiplicative is 1-Gaussian, additive is zero. Default sigma of 0.25 empirically shown to give reasonable ke

Generate the record for each Algo. If it is a BundleAlgo, it will generate the config files. Args: output_folder: the di

Generate the record for each Algo. If it is a BundleAlgo, it will generate the config files. Args: output_folder: the di

Compute cell anchor shapes at multiple sizes and aspect ratios for the current feature map. Args: scales: a sequence whi

Generate anchors and store it in self.anchors: List[Tensor]. We generate anchors only when there is no stored anchors, or the

Compute cell anchor shapes at multiple sizes and aspect ratios for the current feature map. Args: anchor_shapes: [w, h]

Fill a `buffer` list up to `self.size`, then generate randomly popped items.

Get all bundles names (and the latest versions) that are stored in the release of specified repository with the provided tag. If tag is "dev"

Download a platform-appropriate clang-format binary if one doesn't already exist at the expected location and verify that it is the right bin

Get samples from one image for box regression losses computation. Args: box_regression_per_image: box regression result

Get samples from one image for classification losses computation. Args: cls_logits_per_image: classification logits for

returns a table mapping neighbourhood code to the surface area or contour length. Args: spacing: a sequence of 2 or 3 numbers, indic

Create, populate and return the VersioneerConfig() object.

Converts the mask to one hot representation and is smoothened with the selected spatial filter. Args: mask: the shape sh

Get the constructor for the given factory name and arguments. Raises: TypeError: When ``factory_name`` is not a ``str``.

Get the aggregator tensor for number of samples. Returns: torch.Tensor: number of accumulated samples at each location.

Get the aggregator tensor for number of samples. Returns: zarr.Array: Number of accumulated samples at each location.

Get the example data to be used. Use MarsAtlas as it only contains 1 image for quick download and that image is parcellated.

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

Get the data source filename

Returns summary statistics about the local data. Args: extra: Dict with additional information that can be provided by t

Get the filename of the data stats

Get the expected target device in the native PyTorch distributed data parallel. For NCCL backend, return GPU device of current process. F

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

Get a string representation of the dtype.

This method calculates dynamic_axes to use in onnx.export(). Args: profiles: [[min,opt,max],...] list of profile dimensions

Get names of resnet backbones.

Get the initialization parameter for resnet backbones.

Get a list of unnecessary keys for metadata that can be removed. Returns: List of keys to be removed.

Computes the FID score metric on a batch of feature vectors. Args: y_pred: feature vectors extracted from a pretrained network run on gen

Return the file path for the WSI object

Get number of foreground classes based on class and point prompt.

Get a foreground image by removing all-zero rectangles on the edges of the image Note for the developer: update select_fn if the foreground i

Get the FPS of the capture device.

Extracts the size of the fully-sampled part of the kspace. Note that when a kspace is under-sampled, a part of its center is fully sa

Get parameter for next round of training from NNI server.

Get parameter for next round of training from optuna trial object. This function requires user rewrite during usage for different sea

Load the InferClass from the infer.py. The InferClass should be defined in the template under the path of `"scripts/infer.py"`. It is

Return the input spatial shape. Args: inputs: either a tensor of shape BCHW[D], representing a batch of images,

Return the input spatial shape. Args: inputs: either a tensor of shape BCHW[D], representing a batch of images,

Get the keywords needed to look up the version information.

Find all connected components and their bounding shape. Backend can be cuPy/cuCIM or Numpy depending on the hardware. Args: mask

Args: layer_id: a layer name string or a callable. If it is a callable such as `lambda m: m.fc`, this method wil

Returns the number of levels in the whole slide image. Args: wsi: a whole slide image object loaded from a file.

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

Calculates a loss output accounting for differences in shapes, and downsizing targets if necessary (using nearest neighbor interpolat

Compute edges from binary segmentation masks. This function is helpful to further calculate metrics such as Average Surface Distance and

Get the experiment name for MLflow server

Get the tracking URI for MLflow server

Returns the micro-per-pixel resolution of the whole slide image at a given level. Args: wsi: a whole slide image object

Returns the micro-per-pixel resolution of the whole slide image at a given level. Args: wsi: a whole slide image object

Returns the micro-per-pixel resolution of the whole slide image at a given level. Args: wsi: a whole slide image object

Returns the micro-per-pixel resolution of the whole slide image at a given level. Args: wsi: a whole slide image object

Returns the micro-per-pixel resolution of the whole slide image at a given level. Args: wsi: a whole slide image object

Get the mode name for the given spatial dimension using class variable ``name``. Args: spatial_dims: number of spatial d

Get the name of Algo from the identifier of the Algo. Args: id: identifier which follows a convention of "name_fold_other". Ret

Initializes and returns a `nnUNetMONAIModelWrapper` containing the corresponding `nnUNetPredictor`. The model folder should contain the follo

Get the nnUNet trainer instance based on the provided configuration. The returned nnUNet trainer can be used to initialize the SupervisedTrai