DOTA2GamesDataModule¶
- class torch_uncertainty.datamodules.DOTA2GamesDataModule(root, batch_size, val_split=0.0, test_split=0.2, num_workers=1, pin_memory=True, persistent_workers=True, binary=True)[source]¶
The Dota2 Games UCI classification datamodule.
- Parameters:
root (string) – Root directory of the datasets.
batch_size (int) – The batch size for training and testing.
val_split (float, optional) – Share of validation samples among the non-test samples. Defaults to
0
.test_split (float, optional) – Share of test samples. Defaults to
0.2
.num_workers (int, optional) – How many subprocesses to use for data loading. Defaults to
1
.pin_memory (bool, optional) – Whether to pin memory in the GPU. Defaults to
True
.persistent_workers (bool, optional) – Whether to use persistent workers. Defaults to
True
.binary (bool, optional) – Whether to use binary classification. Defaults to
True
.