loki200519/urop

By loki200519 · ↓ 0 · ♥ 0 · Updated 2025-12-14

What's in this repo

This page lists the files in loki200519/urop, including model_logits_dynamic.onnx.

1 ONNX models (.onnx files)
11 files, including 3 .json, 3 .png, 1 .md, 1 .onnx, 1 .pt, 1 .py
Last updated 2025-12-14

ONNX files

File	Size	Download
export/model_logits_dynamic.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

UROP — Physics-Informed UNet++ for Multi-Hazard Detection

Overview

Physics-informed deep learning model for large-scale multi-hazard segmentation using satellite imagery (SAR + optical).

Architecture

UNet++ backbone (ResNet34 encoder)
Physics-informed regularization
Optuna-tuned hyperparameters

Key Metrics

Validation IoU: 1.00
Inference: FP16 GPU streaming (Kaggle)

Files

model_logits_traced.pt — TorchScript
model_logits_dynamic.onnx — ONNX
metrics.json — evaluation
optuna_best.json — hyperparameters

License

Apache-2.0

Model info

onnx region:us

↓ 0 ♥ 0

Created: 2025-12-14

Updated: 2025-12-14

View on Hugging Face

Files (11)

.gitattributes

README.md

config.json

export/model_logits_dynamic.onnx ONNX

export/model_logits_traced.pt

figures/training_loss_curve.png

figures/validation_iou_curve.png

inference_example.py

metrics.json

optuna/optuna_best.json

preview_overlay.png

Related models

More from loki200519

No other models by this author.

More models

No task type declared.