Module `preprocessor.roi_input`

Images used to train Region of Interest require more than simple named "target" information for training. Specifically, coordinates for the bounding box that defines a region associated with a target must also be defined.

Classes

class ROIPreprocessor (target_path_column: str, dtype: Optional[str])

Static methods

def builder() -> ROIPreprocessorBuilder

Instance variables

var target_path_column

Methods

def read_file(self, asset: Union[str, pathlib.Path, Package]) -> torch.utils.data.dataset.Dataset

class ROIPreprocessorBuilder

Abstract base for a preprocessor that can output data as a torch.dataset

Ancestors

Class variables

var SCHEMA

Methods

def dtype(self, dtype: Optional[str]) -> ROIPreprocessorBuilder

Cast an output numpy array to a given dtype. If unset, the Protocol will choose. Ignored for non numpy outputs.

Args

dtype: The dtype that a numpy output will be cast into.

Returns

ROIPreprocessorBuilder: This class instance, useful for chaining.

def target_path_column(self, column_name: str) -> ROIPreprocessorBuilder

Sets which column from the asset's record data to use as a target.

Args

column_name: The name of the column to take as target information.

Returns

ROIPreprocessorBuilder: This class instance, useful for chaining.

Inherited members

OutputTorchDataset:
- output_torch_dataset
IsDict:
- from_dict
- to_dict

class ROITorchDataset (parent: ROIPreprocessor, asset: Package)

An abstract class representing a :class:Dataset.

All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite :meth:__getitem__, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite :meth:__len__, which is expected to return the size of the dataset by many :class:~torch.utils.data.Sampler implementations and the default options of :class:~torch.utils.data.DataLoader. Subclasses could also optionally implement :meth:__getitems__, for speedup batched samples loading. This method accepts list of indices of samples of batch and returns list of samples.

Note

:class:~torch.utils.data.DataLoader by default constructs an index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.

Ancestors

torch.utils.data.dataset.Dataset
typing.Generic