dgs.models.dataset.dataset.ImageHistoryDataset¶

class dgs.models.dataset.dataset.ImageHistoryDataset(*args: Any, **kwargs: Any)[source]¶

A dataset with one index per image ID, the main difference is that in addition to the current frame, the last L frames are given as well.

See BaseDataset for more information.

Params¶

__init__(config: dict[str, any], path: list[str]) → None[source]¶

Methods

`arbitrary_to_ds`(a, idx)	Given a single image ID or filepath, obtain the image, bbox, and possibly more information, then convert everything to a `State` object.
`configure_torch_module`(module[, train])	Set compute mode and send model to the device or multiple parallel devices if applicable.
`get_image_crops`(ds)	Add the image crops and local key-points to a given state.
`get_path_in_dataset`(path)	Given an arbitrary file- or directory-path, return its absolute path.
`terminate`()	Terminate this module and all of its submodules.
`transform_crop_resize`()	Given one single image, with its corresponding bounding boxes and key-points, obtain a cropped image for every bounding box with localized key-points.
`transform_resize_image`()	Given an image, bboxes, and key-points, resize them with custom modes.
`validate_params`(validations[, attrib_name])	Given per key validations, validate this module's parameters.

Attributes

`device`	Get the device of this module.
`is_training`	Get whether this module is set to training-mode.
`module_name`	Get the name of the module.
`module_type`
`name`	Get the name of the module.
`name_safe`	Get the escaped name of the module usable in filepaths by replacing spaces and underscores.
`precision`	Get the (floating point) precision used in multiple parts of this module.
`L`
`data`	Arbitrary data, which will be converted using `self.arbitrary_to_ds()`
`dataset_path`	The base path to the dataset.