Check if the intermediate result is cached after each step in the current working directory Returns: a dict of cache res

Remove extra metadata from the dictionary. Operates in-place so nothing is returned. Args: meta: dictionary containing metadata to b

Remove keys from a dictionary. Operates in-place so nothing is returned. Args: data: dictionary to be modified. keys: keys t

Use `skimage.morphology.remove_small_objects` to remove small objects from images. See: https://scikit-image.org/docs/dev/api/skimage.morphol

Render the given version pieces into the requested style.

Render the given version pieces into the requested style.

TAG[-DISTANCE-gHEX][-dirty]. Like 'git describe --tags --dirty --always'. Exceptions: 1: no tags. HEX[-dirty] (note: no 'g' prefix)

TAG[-DISTANCE-gHEX][-dirty]. Like 'git describe --tags --dirty --always'. Exceptions: 1: no tags. HEX[-dirty] (note: no 'g' prefix)

TAG-DISTANCE-gHEX[-dirty]. Like 'git describe --tags --dirty --always -long'. The distance/hash is unconditional. Exceptions: 1: no

TAG-DISTANCE-gHEX[-dirty]. Like 'git describe --tags --dirty --always -long'. The distance/hash is unconditional. Exceptions: 1: no

Build up version string, with post-release "local version identifier". Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you get a tagged

Build up version string, with post-release "local version identifier". Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you get a tagged

TAG[[.dev0]+DISTANCE.gHEX[.dirty]] . The ".dev0" means not master branch. Note that .dev0 sorts backwards (a feature branch will appear "olde

TAG[[.dev0]+DISTANCE.gHEX[.dirty]] . The ".dev0" means not master branch. Note that .dev0 sorts backwards (a feature branch will appear "olde

TAG[.postDISTANCE[.dev0]] . The ".dev0" means dirty. Exceptions: 1: no tags. 0.postDISTANCE[.dev0]

TAG[.postDISTANCE[.dev0]] . The ".dev0" means dirty. Exceptions: 1: no tags. 0.postDISTANCE[.dev0]

TAG[.postDISTANCE[.dev0]+gHEX] . The ".dev0" means dirty. Note that .dev0 sorts backwards (a dirty tree will appear "older" than the correspo

TAG[.postDISTANCE[.dev0]+gHEX] . The ".dev0" means dirty. Note that .dev0 sorts backwards (a dirty tree will appear "older" than the correspo

TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] . The ".dev0" means not master branch. Exceptions: 1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty]

TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] . The ".dev0" means not master branch. Exceptions: 1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty]

TAG[.postN.devDISTANCE] -- No -dirty. Exceptions: 1: no tags. 0.post0.devDISTANCE

TAG[.postN.devDISTANCE] -- No -dirty. Exceptions: 1: no tags. 0.post0.devDISTANCE

Top-level function to replace modules in model, specified by class name with a desired replacement. NOTE: This occurs in place, if you want t

Check whether the transformation matrix suggests voxel-wise interpolation. Returns None if the affine matrix suggests interpolation. Oth

Resample ``data_array`` to ``output_spatial_shape`` if needed. Args: data_array: input data array. This method assumes th

Utility function to resample the loaded datalist for training, for example: If factor < 1.0, randomly pick part of the datalist and set to Da

Reset all stats

Clear the cache dictionary content

Resize boxes when the corresponding image is resized Args: boxes: source bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box

Utility function used in `instantiate()` to resolve the arguments from current config content.

Resolve the input events to create a pair of Ignite events

Resolve the format of the pre-defined report. Args: report: the dictionary to resolve. Values will be replaced in-place.

Resolve the target module name from current config content. The config content must have ``"_target_"`` key.

To simplify the reference or macro tokens ID in the nested config content, it's available to use relative ID name which starts with t

Similar to roll but for only one dim. Args: x: input data (k-space or image) that can be 1) real-valued: the shape is (C

Rotate boxes by 90 degrees in the plane specified by axes. Rotation direction is from the first towards the second axis. Args: b

Functional implementation of rotate90. This function operates eagerly or lazily according to ``lazy`` (default ``False``). Args:

Calls the `run` method of the wrapped engine.

Load the run function in the training script of each model. Training parameter is predefined by the algo_config.yaml file, which is p

Run the nnU-Net pipeline. Args: run_convert_dataset: whether to convert datasets, defaults to True. run_plan

The python interface for NNI to run. Args: obj_filename: the serialized Algo object. output_folder: the root

Run the Auto3DSeg modules before the BundleGen step. Args: test_path: a path to contain `sim_dataroot` which is for the simulated dat

Call the given command(s).

multi workers stress tests

Load test cases by excluding those need external dependencies. The loaded cases should work with "requirements-min.txt":: # in the m

Sample training pairs for VISTA3D training. Args: labels: [1, 1, H, W, D], ground truth labels. label_set: the label list fo

sample several slices of input numpy array or Tensor on specified `dim`. Args: data: input data to sample slices, can be numpy array or P

Randomly samples training timesteps using the chosen sampling method. Args: x_start (torch.Tensor): The input tensor for

Save image to file, ensuring there's no whitespace around the edge.

Save an object to file with specified path. Support to serialize to a temporary file first, then move to final destination, so that files

This method save the probability map for an image, when its inference is finished, and delete that probability map from memory.

Save numpy array into a TIFF RGB/RGBA file Args: array: numpy ndarray with the shape of CxHxW and C==3 representing a RGB image

A helper function to compute a schedule of scale at different downsampling levels, given the input resolution. .. code-block:: python

Validate the contents of setup.py against Versioneer's expectations.

`np.searchsorted` with equivalent implementation for torch. Args: a: numpy array or tensor, containing monotonically increasing sequ

Select hard negative samples. Args: negative: indices of all the negative samples, sized (P,), where P i

Select positive samples Args: positive: indices of positive samples, sized (P,), where P is the number o

Select positives and hard negatives from list samples per image. Hard negative sampler will be applied to each image independently.

Select positives and hard negatives from samples. Args: labels_per_img: labels, sized (A,). Positive sam

Select indices with highest scores. The indices selection is performed with the following steps: #. If self.apply_sigmoid,

Register model in the ensemble

Set the data analysis extra params. Args: params: a dict that defines the overriding key-value pairs during training. Th

Copies the elements from src into self tensor and returns self. The src tensor must be broadcastable with the self tensor. It

Using for training. Set loss for box regression. Args: box_loss: loss module for box regression encode_gt: i

Convert each element in self.cell_anchors to ``dtype`` and send to ``device``.

Using for training. Set loss for classification that takes logits as inputs, make sure sigmoid/softmax is built in. Args:

Set the input data and delete all the out-dated cache content.

Set the input data and run deterministic transforms to generate cache content. Note: should call `shutdown()` before calling this fu

Set the data source configuration file Args: data_src_cfg: path to a configuration file (yaml) that contains datalist, d

Set the data stats filename Args: data_stats_filename: filename of datastats

Set the device related info Args: cuda_visible_devices: define GPU ids for data analyzer, training, and ensembling.

Set options for GPU-based parameter customization/optimization. Args: gpu_customization: the switch to determine automat

Set the files to perform model inference. Args: dataroot: the path of the files data_list_or_path: the data

Sets input bindings for TRT engine according to feed_dict Args: feed_dict: a dictionary [str->Tensor] stream: C

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

Set the experiment name for MLflow server Args: mlflow_experiment_name: a string to specify the experiment name for MLfl

Set the tracking URI for MLflow server Args: mlflow_tracking_uri: a tracking URI for MLflow server which could be local

Set the search space for NNI parameter search. Args: search_space: hyper parameter search space in the form of dict. For