| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| 0.12.8 source code.tar.gz | 2026-09-30 | 14.0 MB | |
| 0.12.8 source code.zip | 2026-09-30 | 14.2 MB | |
| README.md | 2026-09-30 | 2.8 kB | |
| Totals: 3 Items | 28.2 MB | 0 | |
A patch release that adds LibreYOLO as a detection backend, fixes seven bugs in COCO category remapping, slicing, mask conversion and box merging, and builds boolean masks faster.
✨ Features
- LibreYOLO detection backend (#1425). Install it with
pip install libreyoloand load MIT-licensed LibreYOLO models withmodel_type="libreyolo". It reuses the Ultralytics wrapper, and the models guide covers it in every language (#1467).
🐛 Fixes
- Sliced annotations that touch the slice border are kept (#1462). When a polygon edge lay exactly on a slice border, the intersection came back as a mix of polygons and lines and the annotation was dropped with area 0. The polygon parts are now kept.
- NMM merges boxes whose overlap equals the match threshold (#1464). These boxes were claimed by the keeper but never merged, so they disappeared from the output and the keeper box did not grow.
get_bool_mask_from_coco_segmentationreturns a boolean array (#1463). It returned the float64 canvas, soMask.bool_maskcould not be used to index an image.- Category remapping maps each id once (#1465). With
remapping_dict={0: 1, 1: 2}both categories ended up with id 2 and loading failed withKeyError. - Subsampled, upsampled, area filtered and bbox clipped Coco objects keep their categories (#1466). They applied
remapping_dicta second time to ids that were already remapped, which also affectedclip_bboxes_to_img_dims=True. - Class-aware NMM and greedy NMM accept an image with no detections (#1470) instead of raising
AttributeError. fix_shift_amount_listandfix_full_shape_listaccept empty lists (#1459) instead of raisingIndexError.
⚡ Performance
- Boolean masks from COCO polygons build about 8x faster (#1463). The mask is drawn on a uint8 canvas instead of float64, which takes a 1080p mask from 1.03 ms to 0.13 ms on an Intel Core i7-13850HX and uses 8x less memory.