← Directory
software · Global
resnet18_sentinel2_all_moco
Hugging Face model torchgeo/resnet18_sentinel2_all_moco (image-classification)
Claim this listing
Represent resnet18_sentinel2_all_moco? Send a claim for review so we can discuss listing updates. Claims do not automatically grant ownership or verification.
What's in it
- Data offered docs-verified
- pretrained ResNet-18 weights from SSL4EO-S12, loadable with timm
- Coverage llm-inferred
- Global
- Formats docs-verified
- timm-loadable model weights
- Access docs-verified
- Open access under cc-by-4.0 licence
Useful for
- Use cases llm-inferred
- Transfer-learning backbone for land-cover classification of Sentinel-2 tiles in a UK habitat or BNG baseline study · Feature extraction from Sentinel-2 scenes to classify vegetation or surface change for an environmental impact assessment · Pretrained initialisation for a small labelled dataset of UK catchment land use mapping
- Audience llm-inferred
- GIS analysts · ecologists · environmental consultants · remote sensing specialists · data scientists
Limitations
- Constraints llm-inferred
- Not deployed by any Hugging Face Inference Provider, so it needs local or self-hosted inference · Requires timm and PyTorch with custom loading code to use the weights · Upstream SSL4EO-S12 terms and requirements apply; DOCS give no training, benchmark or accuracy details
- Licence
- cc-by-4.0
- Authentication
- No API key required (repository README, auto-extracted; check upstream requirements)
- GitHub stars
- Unknown
- Last commit
- Unknown
- Last successful page check
- 14/10/2026
- Page health
- healthy
- Package
- Not recorded
- Verification
- Not independently verified
Provenance & evidence
Verified 2026-10-15 via HF API: exists; 914 downloads/30d, 1 likes.
Metadata observed 14/10/2026 · research sweep: manual-2026-10-15 (Hugging Face models)