Base video dataset. Args: video_source: filename of video. transform: transform to be applied to each frame.

Args: metric_name: Name of a binary metric from the MetricsReloaded package. include_background: whether to include

Args: optimizer: wrapped optimizer. end_lr: the final learning rate. num_iter: the number of iterations o

Args: normalize: Whether to divide out spatial sizes in order to make the computation roughly inv

Args: kernel_type: {``"gaussian"``, ``"b-spline"``} ``"gaussian"``: adapted from DeepReg Referenc

Args: iter_: Number of iterations for skeletonization. Must be a non-negative integer. Defaults to 3. smooth_nr: a sm

Args: base_dir: the base directory of the dataset. is_segmentation: whether the datalist is for segmentation task. items:

Apply the model-specific params to the prediction params based on the name of the Algo. Args: algo_spec_param: a dict th

Builds and applies a mask on the spatial dimensions. Args: k: k-space version of the image. Returns: masked v

Perform a transform 'transform' on 'data', according to the other parameters specified. If `data` is a tuple and `unpack_parameters` is True

If TRT engine is not ready, exports model to ONNX, builds TRT engine and saves serialized TRT engine to the disk. Args:

A function to cache the expensive input data transform operations so that huge data sets (larger than computer memory) can be process

In order to enable direct storage to the GPU when loading the hashfile, rewritten this function. Note that in this function, it will

Calculate unit conversion factor with respect to the input unit

Each sequence of coordinates describes a boundary between foreground and background starting and ending at two sides of the bounding

Check data uniformity since DataAnalyzer provides no support to multi-modal images with different affine matrices/spacings due to mon

Check if self.proposal_matcher and self.fg_bg_sampler have been set for training.

Helper method to check consistency of self.loc and input image. Raises assertion error if any index in loc is out of bounds.

Perform sanity checks on the kwargs if the filter contains the required keys. If the filter is ``gauss``, kwargs should contain ``sig

Get the `monai_version` from the metadata.json and compare if it is smaller than the installed `monai` package version

If an optional property has reference in the config, check whether the property is existing. If `ValidationHandler` is defined for a

Should be at least 1 random transform, and all random transforms should be invertible.

This method appends to the _state_dict_user_keys AdversarialTrainer's elements that are required for checkpoint saving. Foll

Args: flat_target: the target tensor.

Compute AP metrics Args: dataset_statistics (list[dict[int, dict[str, np.ndarray]]]): list with result s per image (in l

Compute AR metrics Args: dataset_statistics (list[dict[int, dict[str, np.ndarray]]]): list with result s per image (in l

Args: alpha: generalised number of true positives of target class. flat_target: the target tensor. wasser

Compute the final affine transformation matrix to apply to the point data. Args: data: Input coordinates assumed to be i

Execute the metric computation for `y_pred` and `y` in a list of "channel-first" tensors. The return value is a "batch-first" tensor

This function is used to compute the Hausdorff distance.

Compute expected items for the replacement of next epoch, execute deterministic transforms. It can support multi-threads to accelerat

Compute statistics needed for COCO metrics (mAP, AP of individual classes, mAP@IoU_Thresholds, AR) Adapted from https://github.com/co

Compute recall value, precision curve and scores thresholds Adapted from https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocot

Args: y_pred: input data to compute, typical segmentation model output. It must be one-hot format and first dim i

All header fields of a NRRD are specified in `F` (Fortran) order, even if the image was read as C-ordered array. 1D arrays of header[

convert the label name to index

get the most similar mode of `pad` from ``padding_mode`` of the spatial resampling.

Copies the algorithm templates folder to at_path. Returns a dictionary of algorithm templates.

rearrange slices for buffering