Source code for torchgeo.datamodules.loveda
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
"""LoveDA datamodule."""
from typing import Any, Dict, List, Optional
import pytorch_lightning as pl
from torch.utils.data import DataLoader
from ..datasets import LoveDA
# https://github.com/pytorch/pytorch/issues/60979
# https://github.com/pytorch/pytorch/pull/61045
DataLoader.__module__ = "torch.utils.data"
class LoveDADataModule(pl.LightningDataModule):
"""LightningDataModule implementation for the LoveDA dataset.
Uses the train/val/test splits from the dataset.
.. versionadded:: 0.2
"""
[docs] def __init__(
self,
root_dir: str,
scene: List[str],
batch_size: int = 32,
num_workers: int = 0,
**kwargs: Any,
) -> None:
"""Initialize a LightningDataModule for LoveDA based DataLoaders.
Args:
root_dir: The ``root`` argument to pass to LoveDA Dataset classes
scene: specify whether to load only 'urban', only 'rural' or both
batch_size: The batch size to use in all created DataLoaders
num_workers: The number of workers to use in all created DataLoaders
"""
super().__init__()
self.root_dir = root_dir
self.scene = scene
self.batch_size = batch_size
self.num_workers = num_workers
[docs] def preprocess(self, sample: Dict[str, Any]) -> Dict[str, Any]:
"""Transform a single sample from the Dataset.
Args:
sample: dictionary containing image and mask
Returns:
preprocessed sample
"""
sample["image"] = sample["image"].float()
sample["image"] /= 255.0
return sample
[docs] def prepare_data(self) -> None:
"""Make sure that the dataset is downloaded.
This method is only called once per run.
"""
_ = LoveDA(self.root_dir, scene=self.scene, download=False, checksum=False)
[docs] def setup(self, stage: Optional[str] = None) -> None:
"""Initialize the main ``Dataset`` objects.
This method is called once per GPU per run.
Args:
stage: stage to set up
"""
train_transforms = self.preprocess
val_test_transforms = self.preprocess
self.train_dataset = LoveDA(
self.root_dir, split="train", scene=self.scene, transforms=train_transforms
)
self.val_dataset = LoveDA(
self.root_dir, split="val", scene=self.scene, transforms=val_test_transforms
)
self.test_dataset = LoveDA(
self.root_dir,
split="test",
scene=self.scene,
transforms=val_test_transforms,
)
[docs] def train_dataloader(self) -> DataLoader[Any]:
"""Return a DataLoader for training.
Returns:
training data loader
"""
return DataLoader(
self.train_dataset,
batch_size=self.batch_size,
num_workers=self.num_workers,
shuffle=True,
)
[docs] def val_dataloader(self) -> DataLoader[Any]:
"""Return a DataLoader for validation.
Returns:
validation data loader
"""
return DataLoader(
self.val_dataset,
batch_size=self.batch_size,
num_workers=self.num_workers,
shuffle=False,
)
[docs] def test_dataloader(self) -> DataLoader[Any]:
"""Return a DataLoader for testing.
Returns:
testing data loader
"""
return DataLoader(
self.test_dataset,
batch_size=self.batch_size,
num_workers=self.num_workers,
shuffle=False,
)