-
Andrey Filippov authored
When curt_dnn_model is set, run the ONNX DNN per-pixel inference over curt_save_select across all available scenes (not just the first few), saving -DNN-RECT / -DNN-HYPER-RECT. Slice labels carry timestamp + absolute frame index for matching to real targets. New curt_dnn_thresh (6 sites in IntersceneMatchParameters) zeroes the (Vx,Vy,s) field below confidence s - display/FP-suppression only. inferROI tiles the ROI batch (CHUNK) to bound ONNX Runtime activation memory. Co-authored-by:Claude Opus 4.8 (1M context) <noreply@anthropic.com>
c899aa2b
| Name |
Last commit
|
Last update |
|---|---|---|
| .. | ||
| calibration | ||
| cameras | ||
| common | ||
| correction | ||
| cuas | ||
| dct | ||
| gpu | ||
| ims | ||
| jp4 | ||
| lwir | ||
| mcp | ||
| orthomosaic | ||
| readers | ||
| tensorflow | ||
| tileprocessor | ||
| vegetation | ||
| x3d/export |