RESISC45
Datasets
All datasets matching “RESISC45”resisc45
RESISC45
Overview
Usage
from datasets import load_dataset
# Load the dataset
dataset = load_dataset('tanganke/resisc45')
Dataset Information
The dataset is divided into the following splits:
Training set: Contains 18,900 examples, used for model training.
Test set: Contains 6,300 examples, used for model evaluation and benchmarking.
The dataset also includes the following augmented sets, which can be used for testing the model's robustness to… See the full description on the dataset page: https://huggingface.co/datasets/tanganke/resisc45.resisc45
Description
RESISC45 dataset 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 dataset does not have any default splits. Train, validation, and test splits were based on these definitions here… See the full description on the dataset page: https://huggingface.co/datasets/timm/resisc45.resisc45resisc45Redistributed from https://drive.google.com/file/d/1DnPSU5nVSN7xv95bpZ3XQ0JhKXZOKgIv without modification. Only converted the RAR file to a ZIP file. Please cite https://doi.org/10.1109/jproc.2017.2675998 if you use this dataset. The train-val-test split files come from https://arxiv.org/abs/1911.06721.
RESISC45
Remote Sensing Image Scene Classification (RESISC45) Dataset
Paper Remote Sensing Image Scene Classification: Benchmark and State of the Art
Paper with code: RESISC45
Description
The RESISC45 dataset is a scene classification dataset that focuses on RGB images extracted using Google Earth. This dataset comprises a total of 31,500 images, with each image having a resolution of 256x256 pixels. RESISC45 contains 45 different scene classes, with 700 images per… See the full description on the dataset page: https://huggingface.co/datasets/blanchon/RESISC45.wds_vtab-resisc45