About
The Model
NHSPID, New Hampshire Spider Identifier, is a machine learning tool that identifies spiders in NH.
The Classifier
- Trained on 32,075 images across 36 species of NH jumping spiders
- Uses Vision Transformer (ViT) Large architecture (307M parameters)
- Achieves 81.4% accuracy on test data
- Hosted via Hugging Face Inference Endpoints (Intel Sapphire Rapids 2 vCPUs, 4 GB)
- Currently has one head with 36 classes
- Fine-tuned with differential learning rates (0.0001 for backbone layers, 0.001 for classifier)
The Dataset
The model was trained on observations made available on iNaturalist.com and will be made available publicly.
Inclusion Criteria
- At least one research-grade observation in New Hampshire
- A minimum of 300 photos (from any location)
- A maximum of 10 photos per observation
Versions
| Version | Date | Model | Species |
|---|---|---|---|
| v1 | 7/15/25 | ViT-L/16 (224) | 36 |
Future Directions
Include spiders from regions that border NH
Introduce other families (e.g., Thomisidae, Lycosidae, etc.)
Add species with low image counts
Continue to improve the model's accuracy
Display default images for both sexes of a species
- Include jumping spiders from bordering regions (e.g., Vermont, Maine, Massachusetts, and southern regions of Canada that border NH)
- Introduce other families (e.g., Thomisidae, Lycosidae, etc.)
- Add species with low image counts
- Continue to improve the model's accuracy
- Display default images for both sexes of a species
Credits
Species images from iNaturalist.com .
Phidippus audax on landing page from wirestock on Freepik .