cortenforge-inference
| Crates.io | cortenforge-inference |
| lib.rs | cortenforge-inference |
| version | 0.6.0 |
| created_at | 2026-01-03 18:02:55.246623+00 |
| updated_at | 2026-01-14 00:59:21.125185+00 |
| description | Detector factory and inference helpers (Burn-backed or heuristic) for the CortenForge stack. |
| homepage | https://github.com/via-balaena/CortenForge |
| repository | https://github.com/via-balaena/CortenForge |
| max_upload_size | |
| id | 2020546 |
| size | 200,212 |
(bigmark222)
documentation
https://docs.rs/cortenforge-inference
README
inference crate
Burn-backed (or heuristic) detector factory and inference plugin for Bevy apps.
Details
- Backend: defaults to
backend-ndarray; enable--features backend-wgpufor WGPU. Needsburnfeatures enabled in the root build if you want GPU. - Model: loads
TinyDet(default) orBigDetfrom the sharedmodelscrate viaBinFileRecorder(full precision). Pass a weights path to the factory to load a checkpoint; otherwise it falls back to a heuristic detector. - Use: app orchestrators insert the detector built by
inference::InferenceFactorywhen mode==Inference. Ensure the checkpoint exists and matches the model config. - Smoke: unit test ensures fallback when no weights are provided. Add an integration test pointing at a real checkpoint once available.
License
Apache-2.0 (see LICENSE in the repo root).