Tri-Net v2 — Initial Open-Source Release (v0.9.0)

Tri-Net v2 — Initial Open-Source Release (v0.9.0)

This is the first public release of Tri-Net v2, the official implementation accompanying the paper:

Tri-Net: Unified Deep Learning for Skin Lesion and Symptom-Based Monkeypox Detection

This release provides a reproducible research framework for Mpox and skin lesion classification, including modern deep learning architectures, feature-fusion methods, explainability, benchmarking, and evaluation tools.

Features

• Reproducible training and evaluation pipeline
• Modern CNN backbones:
  • ConvNeXt-Tiny
  • InceptionResNetV2
  • DenseNet201
• Feature-level fusion models
• Binary Mpox screening evaluation
• Cross-validation and statistical benchmarking
• Grad-CAM explainability
• Python package available via:

pip install mpox-trinet

Command-Line Interface

trinet doctor
trinet predict image.jpg
trinet explain image.jpg
trinet benchmark
trinet reproduce

Repository

https://github.com/Sudharsanselvaraj/Synergistic-Deep-Learning-for-Monkeypox-Diagnosis

Citation

If you use this repository in your research, please cite the accompanying publication and this software release.