SODA
Other names: torchgeo.datasets.SODAA
Overview
The SODA-A dataset is a high resolution aerial imagery dataset for small object detection.
Description (from the source)
The SODA-A dataset is a high resolution aerial imagery dataset for small object detection.
- Domain
- Geospatial Data
- Data type
- Images
- Tasks
- Object Detection
- Subfields
- Remote sensing, Object detection
- Languages
- Not available
- Tags
- Aerial, RGB
Statistics and structure
- Number of samples
- 2,513
- Number of classes
- 9
- Number of features
- Not available
- Number of subjects / cases
- Not available
- Number of images
- Not available
- Number of files
- Not available
- Size
- Not available
- Formats
- Not available
- Missing values
- Not available
Licence and access
- Licence
- Creative Commons Attribution-NonCommercial 4.0 (CC-BY-NC-4.0)
- Licence documentation
- Listed in a catalogue (needs confirmation from the source)
- Commercial use
- No
- Redistribution
- Yes
- Attribution required
- Yes
- Access method
- Visit the source
- Access restrictions
- Not available
- Terms of use
- Not available
Allows non-commercial use only, with attribution. Licence text
Always review the original publisher's terms before use; the explorer grants no licence.
Source and download
- Platform
- Publisher website
- Publisher / source
- TorchGeo dataset catalog
- Identifier at the source
- torchgeo:SODAA
- DOI
- Not available
- Metadata source
- torchgeo
- Metadata last updated
- 2026-11-14
- Original page
shaunyuan22.github.io - Documentation
torchgeo.readthedocs.io - Metadata source
pypi.org
The explorer does not host data files; all links point to the original publisher.
Related papers
No verified papers are linked to this dataset at the moment.
Cite the dataset
Built from recorded fields only; missing fields are omitted, not guessed. It is also good practice to cite the paper that introduced the dataset, if there is one.
SODA [Data set]. (n.d.). TorchGeo dataset catalog. https://shaunyuan22.github.io/SODA/
[1] "SODA," TorchGeo dataset catalog, [Online]. Available: https://shaunyuan22.github.io/SODA/
@misc{soda,
title = {{SODA}},
publisher = {TorchGeo dataset catalog},
url = {https://shaunyuan22.github.io/SODA/},
howpublished = {\url{https://shaunyuan22.github.io/SODA/}},
note = {Dataset. Accessed: 2026-11-21}
}Verification
- Verification status
- Partially verified
- Last link check
- Not checked yet
- Source verification date
- Not available
- Verification method
- Metadata parsed from the TorchGeo 0.10.1 package docstrings and the TorchGeo documentation dataset tables (raw GitHub).
- Notes
- Counts and licence are as listed in the TorchGeo documentation table; publication titles are not stored in the catalog, only the citation links (titles need to be filled in through OpenAlex/Crossref enrichment). Original URL not yet checked for availability.
Source and check date of each field
| Field | Source | Date |
|---|---|---|
| number_of_samples | TorchGeo 0.10 documentation table (benchmark.csv, "# Samples") | 2026-11-14 |
| number_of_classes | TorchGeo 0.10 documentation table (benchmark.csv, "# Classes") | 2026-11-14 |
| original_url | TorchGeo 0.10.1 soda.py docstring of SODAA | 2026-11-14 |
| description | TorchGeo 0.10.1 soda.py docstring of SODAA | 2026-11-14 |
| license | TorchGeo 0.10 documentation table (benchmark.csv, "License") | 2026-11-14 |
Similar datasets
Forest Damage
The ForestDamage dataset contains drone imagery that can be used for tree identification, as well as tree damage classification for larch trees.
NASA Marine Debris
The NASA Marine Debris dataset is a dataset for detection of floating marine debris in satellite imagery.
DIOR
DIOR dataset contains horizontal bounding box annotations of Google Earth Aerial RGB imagery. The test split does not contain bounding box annotations and labels.
IDTReeS
The IDTReeS dataset is a dataset for tree crown detection.
EverWatch
The EverWatch Bird Detection dataset contains high-resolution aerial images of birds in the Everglades National Park. Seven bird species haven been annotated and classified.
FAIR1M
The FAIR1M dataset is a dataset for remote sensing fine-grained oriented object detection.
