Prithvi-EO-2.0-tiny β€” ONNX Encoder

Encoder-only ONNX export of Prithvi-EO-2.0-tiny-TL for browser inference via ONNX Runtime WebAssembly.

Usage

  • Input: (batch, 6, 1, 224, 224) β€” 6-band HLS patch, single timestep
  • Output: (batch, 192) β€” CLS token embedding
  • Normalization: mean-std per channel (see below)
Band Mean Std
B02 1087 2248
B03 1342 2179
B04 1433 2178
B05 2734 1850
B06 1958 1242
B07 1363 1049

Export

Generated with scripts/export_onnx.py from the folia project. Wraps the ViT-MAE encoder, strips the decoder, returns CLS token only.

License

Apache-2.0 (same as base model).

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for nthh/prithvi-eo-tiny-onnx

Quantized
(1)
this model