Adriano 27a0ef1a45 feat: coarse_stride per sub-sampling top-level ...

Nuovo kernel JIT _jit_score_bitmap_rescored_strided: valuta solo
pixel su griglia stride x stride al top della piramide. NMS + fase
full-res recuperano precisione. Speed-up ~stride^2 sulla fase coarse,
specie su scene grandi (1920x1080).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-05-04 15:24:44 +02:00

..

web

feat: upload file nella cartella IMAGES_DIR

2026-04-24 14:45:16 +02:00

__init__.py

perf: Numba JIT kernel per score_by_shift (2.1x speedup)

2026-04-24 01:30:31 +02:00

_jit_kernels.py

feat: coarse_stride per sub-sampling top-level

2026-05-04 15:24:44 +02:00

auto_tune.py

perf: Fase 2 speed (3x baseline) - fuse JIT + LRU + sub-pixel lazy

2026-04-24 21:21:59 +00:00

gui.py

ui: layout fisso 1600x900 con pannelli SX/DX, scena scalata

2026-04-24 08:59:06 +02:00

line_matcher.py

feat: coarse_stride per sub-sampling top-level

2026-05-04 15:24:44 +02:00

matcher.py

perf: piramide al training, refinement sub-step, multithreading

2026-04-24 01:22:56 +02:00