Tri-Net v2: Open-source implementation of our Scientific Reports paper on unified skin lesion and symptom-based monkeypox detection [R]

Hi everyone, We've open-sourced Tri-Net v2, the official implementation accompanying our recently published Scientific Reports (Nature Portfolio) paper: "Tri-Net: Unified Deep Learning for Skin Lesion and Symptom-Based Monkeypox Detection" Rather than releasing only training scripts, we rebuilt the project as a reproducible research framework. Highlights: • Leakage-free data preparation pipeline • Multiple CNN backbones (ConvNeXt-Tiny, DenseNet201, Inception-ResNetV2) • Ensemble and feature-fusion strategies • Grad-CAM explainability • Cross-validation and statistical evaluation • Docker support • GitHub Actions CI • PyPI package (pip install mpox-trinet) • CLI for training, inference, and benchmarking The paper has already received over 1,100 article accesses in its first week, and we hope making the implementation fully open-source will help others reproduce, validate, and extend the work. GitHub: github.com/Sudharsanselvaraj/Synergistic-Deep-Learning-for-Monkeypox-Diagnosis PyPI: pypi.org/project/Mpox-Trinet Paper: nature.com/articles/s41598-026-61490-x I'd really appreciate feedback on the implementation, reproducibility, code quality, or ideas for future improvements. Contributions and issues are very welcome!