added aid dataset datamodule and download script

README.md

@@ -40,13 +40,14 @@ pip install 'git+https://github.com/isaaccorley/torchrs.git#egg=torch-rs[train]'
 * [RSICD - Remote Sensing Image Captioning Dataset](https://github.com/isaaccorley/torchrs#remote-sensing-image-captioning-dataset-rsicd)
 * [Sydney Captions](https://github.com/isaaccorley/torchrs#sydney-captions)
 * [UC Merced (UCM) Captions](https://github.com/isaaccorley/torchrs#uc-merced-ucm-captions)
-* [RESISC45 - Remote Sensing Image Scene Classification](https://github.com/isaaccorley/torchrs#remote-sensing-image-scene-classification-resisc45)
-* [EuroSAT](https://github.com/isaaccorley/torchrs#eurosat)
-* [SAT-4-&-SAT-6](https://github.com/isaaccorley/torchrs#sat-4--sat-6)
-* [Inria Aerial Image Labeling - Building Segmentation](https://github.com/isaaccorley/torchrs#inria-aerial-image-labeling)
+* [RESISC45 - Scene Classification](https://github.com/isaaccorley/torchrs#remote-sensing-image-scene-classification-resisc45)
+* [EuroSAT - Scene Classification](https://github.com/isaaccorley/torchrs#eurosat)
+* [SAT-4-&-SAT-6 - Scene Classification](https://github.com/isaaccorley/torchrs#sat-4--sat-6)
+* [AID - Scene Classification](https://github.com/isaaccorley/torchrs#aid)
+* [Inria Aerial Image Labeling - Building Semantic Segmentation](https://github.com/isaaccorley/torchrs#inria-aerial-image-labeling)
 * [GID-15 - Semantic Segmentation](https://github.com/isaaccorley/torchrs#gid-15)
 * [ZueriCrop - Time-Series Instance Segmentation](https://github.com/isaaccorley/torchrs#zuericrop)
-* [TiSeLaC - Time-series Land Cover Classification](https://github.com/isaaccorley/torchrs#tiselac)
+* [TiSeLaC - Time-Series Land Cover Classification](https://github.com/isaaccorley/torchrs#tiselac)
 
 ### PROBA-V Super Resolution
 
@@ -473,7 +474,7 @@ x: dict(
 
 <img src="./assets/resisc45.png" width="500px"></img>
 
-The [RESISC45](http://www.escience.cn/people/JunweiHan/NWPU-RESISC45.html) dataset, proposed in ["Remote Sensing Image Scene Classification: Benchmark and State of the Art", Cheng et al.](https://arxiv.org/abs/1703.00121) is an scene classification dataset of 31,500 RGB images extracted using [Google Earth Engine](https://earthengine.google.com/). The dataset contains 45 scenes with 700 images per class from over 100 countries and was selected to optimize for high variability in image conditions (spatial resolution, occlusion, weather, illumination, etc.).
+The [RESISC45](http://www.escience.cn/people/JunweiHan/NWPU-RESISC45.html) dataset, proposed in ["Remote Sensing Image Scene Classification: Benchmark and State of the Art", Cheng et al.](https://arxiv.org/abs/1703.00121) is a scene classification dataset of 31,500 RGB images extracted using [Google Earth](https://earth.google.com/web/). The dataset contains 45 scenes with 700 images per class from over 100 countries and was selected to optimize for high variability in image conditions (spatial resolution, occlusion, weather, illumination, etc.).
 
 The dataset can be downloaded (0.47GB) using `scripts/download_resisc45.sh` and instantiated below:
 
@@ -600,6 +601,40 @@ dataset.classes
 """
 ```
 
+### Aerial Image Dataset (AID)
+
+<img src="./assets/aid.png" width="500px"></img>
+
+The [AID](https://captain-whu.github.io/AID/) dataset, proposed in ["AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification", Xia et al.](https://arxiv.org/abs/1608.05167) is a scene classification dataset of 10k 600x600 RGB images extracted using [Google Earth](https://earth.google.com/web/). The dataset contains 30 scenes with several hundred images per class from regions and countries around the world. This dataset is fairly easy with ~90% accuracy achievable with a VGG-16.
+
+The dataset can be downloaded (2.6GB) using `scripts/download_aid.sh` and instantiated below:
+
+```python
+import torchvision.transforms as T
+from torchrs.datasets import AID
+
+transform = T.Compose([T.ToTensor()])
+
+dataset = AID(
+    root="path/to/dataset/",
+    transform=transform
+)
+
+x, y = dataset[0]
+"""
+x: (3, 600, 600)
+y: int
+"""
+
+dataset.classes
+"""
+['Airport', 'BareLand', 'BaseballField', 'Beach', 'Bridge', 'Center', 'Church', 'Commercial',
+'DenseResidential', 'Desert', 'Farmland', 'Forest', 'Industrial', 'Meadow', 'MediumResidential',
+'Mountain', 'Park', 'Parking', 'Playground', 'Pond', 'Port', 'RailwayStation', 'Resort',
+'River', 'School', 'SparseResidential', 'Square', 'Stadium', 'StorageTanks', 'Viaduct']
+"""
+```
+
 ### Inria Aerial Image Labeling
 
 <img src="./assets/inria_ail.png" width="950px"></img>

scripts/download_aid.sh

@@ -0,0 +1,5 @@
+pip instal gdown
+mkdir -p .data
+gdown --id 1cvjfe_MZJI9HXwkRgoQbSCH55qQd6Esm
+unzip AID.zip -d .data/
+rm AID.zip

torchrs/datasets/__init__.py

@@ -19,11 +19,12 @@
 from .tiselac import Tiselac
 from .gid15 import GID15
 from .zuericrop import ZueriCrop
+from .aid import AID
 
 
 __all__ = [
     "PROBAV", "ETCI2021", "RSVQALR", "RSVQAxBEN", "EuroSATRGB", "EuroSATMS",
     "RESISC45", "RSICD", "OSCD", "S2Looking", "LEVIRCDPlus", "FAIR1M",
     "SydneyCaptions", "UCMCaptions", "S2MTCP", "ADVANCE", "SAT4", "SAT6",
-    "HRSCD", "InriaAIL", "Tiselac", "GID15", "ZueriCrop"
+    "HRSCD", "InriaAIL", "Tiselac", "GID15", "ZueriCrop", "AID"
 ]

torchrs/datasets/aid.py

@@ -0,0 +1,26 @@
+import torchvision.transforms as T
+from torchvision.datasets import ImageFolder
+
+
+class AID(ImageFolder):
+    """ Image Scene Classification dataset from 'Remote Sensing Image
+    Scene Classification: Benchmark and State of the Art', Cheng at al. (2017)
+    https://arxiv.org/abs/1703.00121
+
+    'We propose a large-scale dataset, termed "NWPU-RESISC45", which is a publicly
+    available benchmark for REmote Sensing Image Scene Classification (RESISC), created
+    by Northwestern Polytechnical University (NWPU). This dataset contains 31,500 images,
+    covering 45 scene classes with 700 images in each class. The proposed NWPU-RESISC45 (i)
+    is large-scale on the scene classes and the total image number, (ii) holds big variations
+    in translation, spatial resolution, viewpoint, object pose, illumination, background, and
+    occlusion, and (iii) has high within-class diversity and between-class similarity.'
+    """
+    def __init__(
+        self,
+        root: str = ".data/AID",
+        transform: T.Compose = T.Compose([T.ToTensor()])
+    ):
+        super().__init__(
+            root=root,
+            transform=transform
+        )

torchrs/train/datamodules/__init__.py

@@ -19,6 +19,7 @@
 from .tiselac import TiselacDataModule
 from .gid15 import GID15DataModule
 from .zuericrop import ZueriCropDataModule
+from .aid import AIDDataModule
 
 
 __all__ = [
@@ -27,5 +28,5 @@
     "RSICDDataModule", "OSCDDataModule", "S2LookingDataModule", "LEVIRCDPlusDataModule",
     "FAIR1MDataModule", "SydneyCaptionsDataModule", "UCMCaptionsDataModule", "S2MTCPDataModule",
     "ADVANCEDataModule", "SAT4DataModule", "SAT6DataModule", "HRSCDDataModule", "InriaAILDataModule",
-    "TiselacDataModule", "GID15DataModule", "ZueriCropDataModule"
+    "TiselacDataModule", "GID15DataModule", "ZueriCropDataModule", "AIDDataModule"
 ]

torchrs/train/datamodules/aid.py

@@ -0,0 +1,26 @@
+from typing import Optional
+
+import torchvision.transforms as T
+
+from torchrs.datasets.utils import dataset_split
+from torchrs.train.datamodules import BaseDataModule
+from torchrs.datasets import AID
+
+
+class AIDDataModule(BaseDataModule):
+
+    def __init__(
+        self,
+        root: str = ".data/NWPU-RESISC45",
+        transform: T.Compose = T.Compose([T.ToTensor()]),
+        *args, **kwargs
+    ):
+        super().__init__(*args, **kwargs)
+        self.root = root
+        self.transform = transform
+
+    def setup(self, stage: Optional[str] = None):
+        dataset = AID(root=self.root, transform=self.transform)
+        self.train_dataset, self.val_dataset, self.test_dataset = dataset_split(
+            dataset, val_pct=self.val_split, test_pct=self.test_split
+        )