vp_suite.datasets.synpick

class SynpickMovingDataset(split, **dataset_kwargs)

Bases: vp_suite.base.base_dataset.VPDataset

Dataset class for the Videos of the dataset “Synpick - Moving”, as encountered in “SynPick: A Dataset for Dynamic Bin Picking Scene Understanding” by Periyasamy et al. (https://arxiv.org/pdf/2107.04852.pdf).

Each sequence depicts a robotic suction cap gripper that moves around in a red bin filled with objects. Over the course of the sequence, the robot approaches 4 waypoints that are randomly chosen from the 4 corners. On its way, the robot is pushing around the objects in the bin.

ACTION_SIZE: int = 3

The size of the action vector per frame (If the dataset provides no actions, this value is 0).

DATASET_FRAME_SHAPE: (<class 'int'>, <class 'int'>, <class 'int'>) = (135, 240, 3)

Shape of a single frame in the dataset (height, width, channels).

DEFAULT_DATA_DIR: pathlib.Path = PosixPath('/home/runner/work/vp-suite/vp-suite/vp-suite-data/data/synpick')

The default save location of the dataset files.

IS_DOWNLOADABLE: str = 'Not Yet'

A string identifying whether the dataset can be (freely) downloaded.

MIN_SEQ_LEN: int = 90

The minimum sequence length provided by the dataset.

NAME: str = 'SynPick - Moving'

The dataset’s name.

REFERENCE: str = 'https://arxiv.org/abs/2107.04852'

The reference (publication) where the original dataset is introduced.

SKIP_FIRST_N = 72

Skip the first few frames as the robotic gripper is still in descent to the bin.

VALID_SPLITS = ['train', 'val', 'test']

The valid arguments for specifying splits.

__init__(split, **dataset_kwargs)

Initializes the dataset loader by determining its split and extracting and processing all dataset attributes from the parameters given in dataset_kwargs.

Parameters

• split (str) – The dataset’s split identifier (i.e. whether it’s a training/validation/test dataset)

• **dataset_kwargs (Any) – Optional dataset arguments for image transformation, value_range, splitting etc.

download_and_prepare_dataset()

Downloads the specific dataset, prepares it for the video prediction task (if needed) and stores it in a default location in the ‘data/’ folder. Implemented by the derived dataset classes.

train_to_val_ratio: float = 0.9

The ratio of files that will be training data (rest will be validation data). For bigger datasets, this ratio can be set closer to 1.

download_synpick(d_path_raw)

Downloads the SynPick - Moving dataset. Currently, this method is not implemented and will raise an Error.

Parameters

d_path_raw (Path) – The output path for the raw data.