PTv3 semantic-segmentation checkpoint trained on synthetic Isaac Sim industrial RGB-D/point-cloud data.

The checkpoint metadata records best_metric_value=0.9111804725342209 at epoch 120. This value comes from the training experiment's configured validation metric; reproduce evaluation on the intended dataset before using it as a benchmark.

Optimizer, scheduler, and training history were removed from the published checkpoint. The original full checkpoint is therefore not resumable from this file.

The fixed model order is:

The Dockerized FastAPI server, RTX 4070/4080 settings, request contract, operations guide, and checksum verification are documented at:

The deployment pins Pointcept commit d7272257058337969292865e0892b91d2f362b6a.

This model is intended for research and evaluation on scenes compatible with the synthetic industrial training domain and the published 23-class taxonomy. It may not generalize to unseen sensors, materials, lighting, geometry, or class definitions. Review predictions before any safety-relevant use.