datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
eurosat-rgb
EuroSat (RGB)
Description
A dataset based on Sentinel-2 satellite images covering 13 spectral bands and consisting of 10 classes with 27000 labeled and geo-referenced samples. This is the RGB version of the dataset with visible bands encoded as JPEG images.
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/eurosat-rgb.EuroSAT_RGB
EuroSAT RGB
EUROSAT RGB is the RGB version of the EUROSAT dataset based on Sentinel-2 satellite images covering 13 spectral bands and consisting of 10 classes with 27000 labeled and geo-referenced samples.
Paper: https://arxiv.org/abs/1709.00029
Homepage: https://github.com/phelber/EuroSAT
Description
The EuroSAT dataset is a comprehensive land cover classification dataset that focuses on images taken by the ESA Sentinel-2 satellite. It contains a total of 27… See the full description on the dataset page: https://huggingface.co/datasets/blanchon/EuroSAT_RGB.bigearthnet-v2-rgb
BigEarthNet v2.0 (reBEN) - Sentinel-2 RGB
Description
BigEarthNet v2.0 (reBEN, "refined BigEarthNet"), a multi-label land-cover classification dataset of Sentinel-2 image patches from 10 European countries. Each 1200 m x 1200 m patch (120x120 pixels at 10 m) is labelled with one or more of 19 land-cover classes. The labels come from the CORINE Land Cover 2018 map, using the 19-class BigEarthNet nomenclature.
This variant is RGB-only, stored as JPEG (quality 98… See the full description on the dataset page: https://huggingface.co/datasets/timm/bigearthnet-v2-rgb.eurosat-rgb
EuroSat (RGB)
Description
A dataset based on Sentinel-2 satellite images covering 13 spectral bands and consisting of 10 classes with 27000 labeled and geo-referenced samples. This is the RGB version of the dataset with visible bands encoded as JPEG images.
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/eurosat-rgb.bigearthnet-v2-rgb-nir-swir
BigEarthNet v2.0 (reBEN) - Sentinel-2 RGB + NIR + SWIR
Description
BigEarthNet v2.0 (reBEN, "refined BigEarthNet"), a multi-label land-cover classification dataset of Sentinel-2 image patches from 10 European countries. Each 1200 m x 1200 m patch (120x120 pixels at 10 m) is labelled with one or more of 19 land-cover classes. The labels come from the CORINE Land Cover 2018 map, using the 19-class BigEarthNet nomenclature.
This variant stores the tone-mapped RGB as… See the full description on the dataset page: https://huggingface.co/datasets/timm/bigearthnet-v2-rgb-nir-swir.EuroSAT_RGB
EuroSAT RGB
Dataset Description
EuroSAT is a dataset for land use and land cover (LULC) classification using Sentinel-2 satellite imagery. This version contains the RGB (visible spectrum) bands encoded as JPEG images at 64x64 pixel resolution.
The dataset covers 10 land use/land cover classes across 27,000 geo-referenced images from 34 European countries.
Source: https://zenodo.org/records/7711810
DOI: 10.5281/zenodo.7711810
License: MIT
Paper: EuroSAT: A Novel Dataset… See the full description on the dataset page: https://huggingface.co/datasets/giswqs/EuroSAT_RGB.CattleFace-RGBT
CattleFace-RGBT: Cattle Facial Landmark Dataset with RGB-Thermal Imagery
Dataset Description
CattleFace-RGBT is the first publicly available multimodal dataset featuring paired frontal-view RGB and thermal facial images of cattle, annotated with 13 facial keypoints and associated ground-truth rectal temperature measurements. The dataset was developed to support research in automated cattle fever estimation and precision livestock farming.
Paper: CattleFever: An… See the full description on the dataset page: https://huggingface.co/datasets/phamtrongthang/CattleFace-RGBT.ImageNet_RGBD_DepthAnything
ImageNet with Depth generated by DepthAnything ViT-L
flame2-rgb-ir-new
FLAME2 RGB-IR Smoke Dataset
This Hugging Face dataset was prepared from a Kaggle mirror of FLAME2 RGB/thermal frame pairs.
Columns:
rgb: RGB image
ir: thermal/IR image
label: int64, where 0 = without smoke and 1 = with smoke
Labels are derived from the original FLAME2 Frame Pair Labels.txt smoke ranges when available.
Please verify redistribution terms against the original dataset source before making the dataset public.
EuroSAT_RGB
EuroSAT RGB
EUROSAT RGB is the RGB version of the EUROSAT dataset based on Sentinel-2 satellite images covering 13 spectral bands and consisting of 10 classes with 27000 labeled and geo-referenced samples.
Paper: https://arxiv.org/abs/1709.00029
Homepage: https://github.com/phelber/EuroSAT
Description
The EuroSAT dataset is a comprehensive land cover classification dataset that focuses on images taken by the ESA Sentinel-2 satellite. It contains a total of 27… See the full description on the dataset page: https://huggingface.co/datasets/ebader/EuroSAT_RGB.