Panda — semantic segmentation

5-class LArTPC semantic segmentation: PTv3 encoder–decoder + linear per-point head.

Loading

import pimm
model = pimm.from_pretrained("hf://deeplearnphysics/panda-semantic")

Architecture + hyper-parameters travel in config.json, so no config file is needed. Weights are bitwise-identical to the original checkpoint.

Repackaged from the original panda checkpoints into the pimm export format. Inherits the source repo's license.

Safetensors

Model size

0.1B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support