datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
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.GeoChat-NWPU-RESISC45resisc45
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/mteb/resisc45.resisc45_1knwpu-resisc45-v1
NWPU-RESISC45
Train/val split manifests extracted from GeoChat_Instruct
for fine-tuning vision-language models on satellite scene classification.
This Hub dataset includes a real image column so the dataset viewer shows the image,
question, and answer aligned row-by-row.
Classes
45 scene categories (e.g. airplane, baseball diamond, beach, bridge, …)
Splits
Split
Samples
train
~25 200
val
~4 725
Format
Columns:
image (previewable… See the full description on the dataset page: https://huggingface.co/datasets/tarek199147/nwpu-resisc45-v1.resisc45_sortedresisc45_sorted_with_labelresisc45_2kresisc45_5kresisc45resisc45_scoreresisc45