Source code for torchgeo.datasets.ucmerced

# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.

"""UC Merced dataset."""
import os
from typing import Callable, Dict, Optional, cast

import matplotlib.pyplot as plt
import numpy as np
from torch import Tensor

from .geo import NonGeoClassificationDataset
from .utils import check_integrity, download_url, extract_archive

class UCMerced(NonGeoClassificationDataset):
    """UC Merced dataset.

    The `UC Merced <>`__
    dataset is a land use classification dataset of 2.1k 256x256 1ft resolution RGB
    images of urban locations around the U.S. extracted from the USGS National Map Urban
    Area Imagery collection with 21 land use classes (100 images per class).

    Dataset features:

    * land use class labels from around the U.S.
    * three spectral bands - RGB
    * 21 classes

    Dataset classes:

    * agricultural
    * airplane
    * baseballdiamond
    * beach
    * buildings
    * chaparral
    * denseresidential
    * forest
    * freeway
    * golfcourse
    * harbor
    * intersection
    * mediumresidential
    * mobilehomepark
    * overpass
    * parkinglot
    * river
    * runway
    * sparseresidential
    * storagetanks
    * tenniscourt

    This dataset uses the train/val/test splits defined in the "In-domain representation
    learning for remote sensing" paper:


    If you use this dataset in your research, please cite the following paper:


    url = ""  # 318 MB
    filename = ""
    md5 = "5b7ec56793786b6dc8a908e8854ac0e4"

    base_dir = os.path.join("UCMerced_LandUse", "Images")
    classes = [

    splits = ["train", "val", "test"]
    split_urls = {
        "train": "",  # noqa: E501
        "val": "",  # noqa: E501
        "test": "",  # noqa: E501
    split_md5s = {
        "train": "f2fb12eb2210cfb53f93f063a35ff374",
        "val": "11ecabfc52782e5ea6a9c7c0d263aca0",
        "test": "046aff88472d8fc07c4678d03749e28d",

[docs] def __init__( self, root: str = "data", split: str = "train", transforms: Optional[Callable[[Dict[str, Tensor]], Dict[str, Tensor]]] = None, download: bool = False, checksum: bool = False, ) -> None: """Initialize a new UC Merced dataset instance. Args: root: root directory where dataset can be found split: one of "train", "val", or "test" transforms: a function/transform that takes input sample and its target as entry and returns a transformed version download: if True, download dataset and store it in the root directory checksum: if True, check the MD5 of the downloaded files (may be slow) Raises: RuntimeError: if ``download=False`` and data is not found, or checksums don't match """ assert split in self.splits self.root = root self.transforms = transforms = download self.checksum = checksum self._verify() valid_fns = set() with open(os.path.join(self.root, f"uc_merced-{split}.txt")) as f: for fn in f: valid_fns.add(fn.strip()) is_in_split: Callable[[str], bool] = lambda x: os.path.basename(x) in valid_fns super().__init__( root=os.path.join(root, self.base_dir), transforms=transforms, is_valid_file=is_in_split, )
def _check_integrity(self) -> bool: """Check integrity of dataset. Returns: True if dataset files are found and/or MD5s match, else False """ integrity: bool = check_integrity( os.path.join(self.root, self.filename), self.md5 if self.checksum else None ) return integrity def _verify(self) -> None: """Verify the integrity of the dataset. Raises: RuntimeError: if ``download=False`` but dataset is missing or checksum fails """ # Check if the files already exist filepath = os.path.join(self.root, self.base_dir) if os.path.exists(filepath): return # Check if zip file already exists (if so then extract) if self._check_integrity(): self._extract() return # Check if the user requested to download the dataset if not raise RuntimeError( "Dataset not found in `root` directory and `download=False`, " "either specify a different `root` directory or use `download=True` " "to automatically download the dataset." ) # Download and extract the dataset self._download() self._extract() def _download(self) -> None: """Download the dataset.""" download_url( self.url, self.root, filename=self.filename, md5=self.md5 if self.checksum else None, ) for split in self.splits: download_url( self.split_urls[split], self.root, filename=f"uc_merced-{split}.txt", md5=self.split_md5s[split] if self.checksum else None, ) def _extract(self) -> None: """Extract the dataset.""" filepath = os.path.join(self.root, self.filename) extract_archive(filepath)
[docs] def plot( self, sample: Dict[str, Tensor], show_titles: bool = True, suptitle: Optional[str] = None, ) -> plt.Figure: """Plot a sample from the dataset. Args: sample: a sample returned by :meth:`NonGeoClassificationDataset.__getitem__` show_titles: flag indicating whether to show titles above each panel suptitle: optional string to use as a suptitle Returns: a matplotlib Figure with the rendered sample .. versionadded:: 0.2 """ image = np.rollaxis(sample["image"].numpy(), 0, 3) label = cast(int, sample["label"].item()) label_class = self.classes[label] showing_predictions = "prediction" in sample if showing_predictions: prediction = cast(int, sample["prediction"].item()) prediction_class = self.classes[prediction] fig, ax = plt.subplots(figsize=(4, 4)) ax.imshow(image) ax.axis("off") if show_titles: title = f"Label: {label_class}" if showing_predictions: title += f"\nPrediction: {prediction_class}" ax.set_title(title) if suptitle is not None: plt.suptitle(suptitle) return fig

© Copyright 2021, Microsoft Corporation. Revision 34680c94.

Built with Sphinx using a theme provided by Read the Docs.
Read the Docs v: latest
On Read the Docs
Project Home

Free document hosting provided by Read the Docs.


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources