Compare commits
12 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 543ae0f643 | |||
| a12574f3c5 | |||
| 110dc87b08 | |||
| 2bb2cf63cc | |||
| ea6a9163ad | |||
| 1cc7881a51 | |||
| 74a332a2dd | |||
| dae49eb4a3 | |||
| 9218cb2741 | |||
| 159f9089a5 | |||
| b718e81ccf | |||
| d46197a81a |
@@ -8,3 +8,5 @@ __pycache__/
|
||||
.DS_Store
|
||||
*.log
|
||||
models/
|
||||
# Ricette pre-trained (generate da utente, non versionare)
|
||||
recipes/*.npz
|
||||
|
||||
+217
@@ -0,0 +1,217 @@
|
||||
"""CLI validation harness per LineShapeMatcher.
|
||||
|
||||
Usage:
|
||||
python -m pm2d.eval dataset.json [opzioni]
|
||||
|
||||
Formato dataset (JSON):
|
||||
{
|
||||
"template": "path/to/template.png",
|
||||
"mask": "path/to/mask.png", # opzionale
|
||||
"params": { # opzionali, override su matcher init
|
||||
"use_polarity": true,
|
||||
"angle_step_deg": 5,
|
||||
...
|
||||
},
|
||||
"find_params": { # opzionali, passati a find()
|
||||
"min_score": 0.6,
|
||||
"use_soft_score": true,
|
||||
...
|
||||
},
|
||||
"scenes": [
|
||||
{
|
||||
"image": "path/to/scene1.png",
|
||||
"ground_truth": [
|
||||
{"cx": 320.0, "cy": 240.0, "angle_deg": 12.0,
|
||||
"scale": 1.0, "tolerance_px": 5.0,
|
||||
"tolerance_deg": 3.0}
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
Output: report precision/recall/IoU/timing per ogni scena + aggregati.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import math
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from pm2d.line_matcher import LineShapeMatcher, _poly_iou, _oriented_bbox_polygon
|
||||
|
||||
|
||||
def _load_image(path: str | Path) -> np.ndarray:
|
||||
img = cv2.imread(str(path), cv2.IMREAD_UNCHANGED)
|
||||
if img is None:
|
||||
raise FileNotFoundError(f"Immagine non trovata: {path}")
|
||||
if img.ndim == 2:
|
||||
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
|
||||
return img
|
||||
|
||||
|
||||
def _gt_to_poly(gt: dict, tw: int, th: int) -> np.ndarray:
|
||||
"""Costruisce bbox poligonale per un ground truth."""
|
||||
s = float(gt.get("scale", 1.0))
|
||||
return _oriented_bbox_polygon(
|
||||
float(gt["cx"]), float(gt["cy"]),
|
||||
tw * s, th * s, float(gt["angle_deg"]),
|
||||
)
|
||||
|
||||
|
||||
def _match_to_gt(match, gt: dict, tw: int, th: int,
|
||||
iou_thr: float = 0.3) -> bool:
|
||||
"""True se il match corrisponde al ground truth.
|
||||
|
||||
Criterio: distanza centro <= tolerance_px AND |angle_deg - gt| <= tolerance_deg
|
||||
OR IoU bbox >= iou_thr (fallback per pose con tolerance ampie).
|
||||
"""
|
||||
tol_px = float(gt.get("tolerance_px", 5.0))
|
||||
tol_deg = float(gt.get("tolerance_deg", 3.0))
|
||||
dx = match.cx - float(gt["cx"])
|
||||
dy = match.cy - float(gt["cy"])
|
||||
dist = math.hypot(dx, dy)
|
||||
da = abs((match.angle_deg - float(gt["angle_deg"]) + 180) % 360 - 180)
|
||||
if dist <= tol_px and da <= tol_deg:
|
||||
return True
|
||||
# Fallback IoU
|
||||
poly_gt = _gt_to_poly(gt, tw, th)
|
||||
poly_m = match.bbox_poly
|
||||
if _poly_iou(poly_m, poly_gt) >= iou_thr:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def evaluate_scene(matcher: LineShapeMatcher, scene_bgr: np.ndarray,
|
||||
gt_list: list[dict], find_params: dict,
|
||||
tw: int, th: int) -> dict:
|
||||
"""Esegue match e calcola TP/FP/FN per una scena."""
|
||||
t0 = time.time()
|
||||
matches = matcher.find(scene_bgr, **find_params)
|
||||
elapsed = time.time() - t0
|
||||
|
||||
gt_matched = [False] * len(gt_list)
|
||||
match_is_tp = [False] * len(matches)
|
||||
iou_per_match = [0.0] * len(matches)
|
||||
for i, m in enumerate(matches):
|
||||
for j, gt in enumerate(gt_list):
|
||||
if gt_matched[j]:
|
||||
continue
|
||||
if _match_to_gt(m, gt, tw, th):
|
||||
gt_matched[j] = True
|
||||
match_is_tp[i] = True
|
||||
# Calcolo IoU per metrica
|
||||
poly_gt = _gt_to_poly(gt, tw, th)
|
||||
iou_per_match[i] = _poly_iou(m.bbox_poly, poly_gt)
|
||||
break
|
||||
tp = sum(match_is_tp)
|
||||
fp = len(matches) - tp
|
||||
fn = len(gt_list) - sum(gt_matched)
|
||||
return {
|
||||
"n_matches": len(matches),
|
||||
"n_gt": len(gt_list),
|
||||
"tp": tp, "fp": fp, "fn": fn,
|
||||
"find_time_s": elapsed,
|
||||
"iou_mean": float(np.mean([i for i, t in zip(iou_per_match, match_is_tp) if t])
|
||||
if tp > 0 else 0.0),
|
||||
"diag": (matcher.get_last_diag()
|
||||
if hasattr(matcher, "get_last_diag") else None),
|
||||
}
|
||||
|
||||
|
||||
def run(dataset_path: str, scene_filter: str | None = None,
|
||||
verbose: bool = False) -> dict:
|
||||
"""Esegue eval su dataset, ritorna report aggregato."""
|
||||
dataset_path = Path(dataset_path)
|
||||
base = dataset_path.parent
|
||||
with open(dataset_path) as f:
|
||||
ds = json.load(f)
|
||||
|
||||
template = _load_image(base / ds["template"])
|
||||
mask = None
|
||||
if ds.get("mask"):
|
||||
mask_img = cv2.imread(str(base / ds["mask"]), cv2.IMREAD_GRAYSCALE)
|
||||
if mask_img is not None:
|
||||
mask = (mask_img > 128).astype(np.uint8) * 255
|
||||
init_params = ds.get("params", {})
|
||||
find_params = ds.get("find_params", {})
|
||||
|
||||
matcher = LineShapeMatcher(**init_params)
|
||||
n_var = matcher.train(template, mask=mask)
|
||||
tw, th = matcher.template_size
|
||||
print(f"Template: {ds['template']} ({tw}x{th}), {n_var} varianti")
|
||||
print(f"Param matcher: {init_params}")
|
||||
print(f"Param find: {find_params}")
|
||||
print()
|
||||
|
||||
scenes = ds["scenes"]
|
||||
if scene_filter:
|
||||
scenes = [s for s in scenes if scene_filter in s["image"]]
|
||||
|
||||
rows = []
|
||||
tot_tp = tot_fp = tot_fn = 0
|
||||
tot_time = 0.0
|
||||
for sc in scenes:
|
||||
scene = _load_image(base / sc["image"])
|
||||
gt = sc.get("ground_truth", [])
|
||||
result = evaluate_scene(matcher, scene, gt, find_params, tw, th)
|
||||
rows.append({"scene": sc["image"], **result})
|
||||
tot_tp += result["tp"]; tot_fp += result["fp"]; tot_fn += result["fn"]
|
||||
tot_time += result["find_time_s"]
|
||||
prec = result["tp"] / max(1, result["tp"] + result["fp"])
|
||||
rec = result["tp"] / max(1, result["tp"] + result["fn"])
|
||||
line = (f" {sc['image']:30s} "
|
||||
f"TP={result['tp']} FP={result['fp']} FN={result['fn']} "
|
||||
f"P={prec:.2f} R={rec:.2f} "
|
||||
f"IoU={result['iou_mean']:.2f} "
|
||||
f"t={result['find_time_s']*1000:.0f}ms")
|
||||
print(line)
|
||||
if verbose and result["diag"] and hasattr(matcher, "_format_diag"):
|
||||
print(f" diag: {matcher._format_diag(result['diag'])}")
|
||||
|
||||
# Aggregati
|
||||
precision = tot_tp / max(1, tot_tp + tot_fp)
|
||||
recall = tot_tp / max(1, tot_tp + tot_fn)
|
||||
f1 = 2 * precision * recall / max(1e-9, precision + recall)
|
||||
print()
|
||||
print(f"AGGREGATO: precision={precision:.3f} recall={recall:.3f} "
|
||||
f"F1={f1:.3f} TP={tot_tp} FP={tot_fp} FN={tot_fn}")
|
||||
print(f"TIME: total={tot_time:.2f}s avg={tot_time / max(1, len(scenes)) * 1000:.0f}ms/scene")
|
||||
|
||||
return {
|
||||
"precision": precision, "recall": recall, "f1": f1,
|
||||
"tp": tot_tp, "fp": tot_fp, "fn": tot_fn,
|
||||
"total_time_s": tot_time, "n_scenes": len(scenes),
|
||||
"per_scene": rows,
|
||||
}
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
p = argparse.ArgumentParser(
|
||||
description="pm2d-eval: validation harness per LineShapeMatcher"
|
||||
)
|
||||
p.add_argument("dataset", help="JSON dataset (template + scenes + GT)")
|
||||
p.add_argument("--scene-filter", default=None,
|
||||
help="Filtro substring sui nomi scena (debug)")
|
||||
p.add_argument("--verbose", "-v", action="store_true",
|
||||
help="Stampa diag dict per ogni scena")
|
||||
p.add_argument("--out", default=None,
|
||||
help="Salva report JSON su file")
|
||||
args = p.parse_args(argv)
|
||||
report = run(args.dataset, scene_filter=args.scene_filter,
|
||||
verbose=args.verbose)
|
||||
if args.out:
|
||||
with open(args.out, "w") as f:
|
||||
json.dump(report, f, indent=2)
|
||||
print(f"Report salvato: {args.out}")
|
||||
return 0 if report["f1"] > 0.5 else 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
+143
-6
@@ -512,8 +512,10 @@ class LineShapeMatcher:
|
||||
self.variants.clear()
|
||||
# Reset view list: template principale = view 0
|
||||
self._view_templates = [(gray.copy(), mask_full.copy())]
|
||||
# Invalida cache feature di refine: il template e cambiato.
|
||||
# Invalida cache: template/param cambiati → spread/feature obsoleti.
|
||||
self._refine_feat_cache = {}
|
||||
if hasattr(self, "_scene_cache"):
|
||||
self._scene_cache.clear()
|
||||
self._build_variants_for_view(gray, mask_full, view_idx=0)
|
||||
self._dedup_variants()
|
||||
return len(self.variants)
|
||||
@@ -669,6 +671,51 @@ class LineShapeMatcher:
|
||||
raw[b] = d.astype(np.float32)
|
||||
return raw
|
||||
|
||||
# --- Scene precompute cache (II Halcon-style) -----------------------
|
||||
_SCENE_CACHE_SIZE = 4
|
||||
|
||||
def _scene_cache_key(self, gray: np.ndarray) -> str | None:
|
||||
"""Hash compatto della scena + param che influenzano spread/density.
|
||||
|
||||
Hash su prime 64KB della scena (sufficiente discriminante per
|
||||
scene fotografiche) + parametri matcher rilevanti. None se cache
|
||||
disabilitata (es. scene troppo piccole).
|
||||
"""
|
||||
if gray.size < 100:
|
||||
return None
|
||||
try:
|
||||
import hashlib
|
||||
h = hashlib.md5()
|
||||
sample = gray.tobytes()[:65536]
|
||||
h.update(sample)
|
||||
h.update(f"|{gray.shape}|{gray.dtype}".encode())
|
||||
h.update(
|
||||
f"|{self.weak_grad}|{self.strong_grad}"
|
||||
f"|{self.spread_radius}|{self._n_bins}"
|
||||
f"|{self.pyramid_levels}".encode()
|
||||
)
|
||||
return h.hexdigest()
|
||||
except Exception:
|
||||
return None
|
||||
|
||||
def _scene_cache_get(self, key: str) -> tuple | None:
|
||||
cache = getattr(self, "_scene_cache", None)
|
||||
if cache is None:
|
||||
return None
|
||||
v = cache.get(key)
|
||||
if v is not None:
|
||||
cache.move_to_end(key)
|
||||
return v
|
||||
|
||||
def _scene_cache_put(self, key: str, value: tuple) -> None:
|
||||
from collections import OrderedDict
|
||||
if not hasattr(self, "_scene_cache"):
|
||||
self._scene_cache = OrderedDict()
|
||||
self._scene_cache[key] = value
|
||||
self._scene_cache.move_to_end(key)
|
||||
while len(self._scene_cache) > self._SCENE_CACHE_SIZE:
|
||||
self._scene_cache.popitem(last=False)
|
||||
|
||||
def _spread_bitmap(self, gray: np.ndarray) -> np.ndarray:
|
||||
"""Spread bitmap: bit b acceso dove bin b è presente nel raggio.
|
||||
|
||||
@@ -1309,6 +1356,7 @@ class LineShapeMatcher:
|
||||
min_recall: float = 0.0,
|
||||
use_soft_score: bool = False,
|
||||
subpixel_lm: bool = False,
|
||||
debug: bool = False,
|
||||
) -> list[Match]:
|
||||
"""
|
||||
scale_penalty: se > 0, riduce lo score per match a scala diversa da 1.0:
|
||||
@@ -1326,6 +1374,32 @@ class LineShapeMatcher:
|
||||
if not self.variants:
|
||||
raise RuntimeError("Matcher non addestrato: chiamare train() prima.")
|
||||
|
||||
# Diagnostic counter: traccia perche' candidati sono droppati lungo
|
||||
# la pipeline. Esposto via get_last_diag() o ritornato implicitamente
|
||||
# se debug=True (vedi sotto).
|
||||
diag = {
|
||||
"n_variants_total": len(self.variants),
|
||||
"n_variants_top_evaluated": 0,
|
||||
"n_variants_top_passed": 0,
|
||||
"n_variants_full_evaluated": 0,
|
||||
"n_raw_candidates": 0,
|
||||
"n_after_pre_nms": 0,
|
||||
"drop_ncc_low": 0,
|
||||
"drop_min_score_post_avg": 0,
|
||||
"drop_recall_low": 0,
|
||||
"drop_bbox_out_of_scene": 0,
|
||||
"drop_nms_iou": 0,
|
||||
"n_final": 0,
|
||||
"top_thresh_used": 0.0,
|
||||
"verify_threshold_used": float(verify_threshold),
|
||||
"min_score_used": float(min_score),
|
||||
"min_recall_used": float(min_recall),
|
||||
"use_polarity": bool(self.use_polarity),
|
||||
"use_soft_score": bool(use_soft_score),
|
||||
"subpixel_lm": bool(subpixel_lm),
|
||||
}
|
||||
self._last_diag = diag
|
||||
|
||||
gray_full = self._to_gray(scene_bgr)
|
||||
# Applica ROI di ricerca: restringe scena a crop, ricorda offset per
|
||||
# ri-traslare le coordinate dei match a fine pipeline.
|
||||
@@ -1340,18 +1414,31 @@ class LineShapeMatcher:
|
||||
else:
|
||||
gray0 = gray_full
|
||||
roi_offset = (0, 0)
|
||||
|
||||
# Cache pre-compute scena (II Halcon-style): hash bytes scene + param
|
||||
# gradient/spread → riusa spread piramide + density tra find()
|
||||
# consecutive con stessa scena (typical UI tuning: slider produce
|
||||
# 10+ find() su scena identica). Risparmia ~80% del costo non-kernel.
|
||||
cache_key = self._scene_cache_key(gray0)
|
||||
cached = self._scene_cache_get(cache_key) if cache_key else None
|
||||
if cached is not None:
|
||||
grays, spread_top, bit_active_top, density_top, spread0, \
|
||||
bit_active_full, density_full, top = cached
|
||||
else:
|
||||
grays = [gray0]
|
||||
for _ in range(self.pyramid_levels - 1):
|
||||
grays.append(cv2.pyrDown(grays[-1]))
|
||||
top = len(grays) - 1
|
||||
|
||||
# Spread bitmap (uint8) al top level: 32× meno memoria della response
|
||||
# map float32 → MOLTO più cache-friendly per _score_by_shift.
|
||||
spread_top = self._spread_bitmap(grays[top])
|
||||
bit_active_top = int(
|
||||
sum(1 << b for b in range(self._n_bins)
|
||||
if (spread_top & (spread_top.dtype.type(1) << b)).any())
|
||||
)
|
||||
density_top = _jit_popcount(spread_top)
|
||||
# spread0 + density_full computati piu sotto, quindi salvo dopo.
|
||||
spread0 = None
|
||||
bit_active_full = None
|
||||
density_full = None
|
||||
if nms_radius is None:
|
||||
nms_radius = max(8, min(self.template_size) // 2)
|
||||
# Pruning adattivo allo step angolare: con step piccolo (<= 3 deg)
|
||||
@@ -1368,9 +1455,10 @@ class LineShapeMatcher:
|
||||
top_factor = max(top_factor, 0.7)
|
||||
cf_eff = 1
|
||||
top_thresh = min_score * top_factor
|
||||
diag["top_thresh_used"] = float(top_thresh)
|
||||
|
||||
tw, th = self.template_size
|
||||
density_top = _jit_popcount(spread_top)
|
||||
# density_top gia' computato sopra (cache o miss)
|
||||
sf_top = 2 ** top
|
||||
bg_cache_top: dict[float, np.ndarray] = {}
|
||||
bg_cache_full: dict[float, np.ndarray] = {}
|
||||
@@ -1453,6 +1541,7 @@ class LineShapeMatcher:
|
||||
|
||||
kept_coarse: list[tuple[int, float]] = []
|
||||
all_top_scores: list[tuple[int, float]] = []
|
||||
diag["n_variants_top_evaluated"] = len(coarse_idx_list)
|
||||
# batch_top: usa kernel batch single-call con prange-esterno su
|
||||
# varianti. Vince su threadpool quando n_vars >> n_threads e quando
|
||||
# H*W top e' piccolo (overhead chiamate JIT > costo kernel).
|
||||
@@ -1516,14 +1605,24 @@ class LineShapeMatcher:
|
||||
kept_variants.sort(key=lambda t: -t[1])
|
||||
max_vars_full = max(max_matches * 8, len(self.variants) // 2)
|
||||
kept_variants = kept_variants[:max_vars_full]
|
||||
diag["n_variants_top_passed"] = len(kept_coarse)
|
||||
diag["n_variants_full_evaluated"] = len(kept_variants)
|
||||
|
||||
# Full-res (parallelizzato) con bitmap
|
||||
# Full-res (parallelizzato) con bitmap.
|
||||
# Riusa cache se disponibile, altrimenti computa e salva.
|
||||
if spread0 is None:
|
||||
spread0 = self._spread_bitmap(gray0)
|
||||
bit_active_full = int(
|
||||
sum(1 << b for b in range(self._n_bins)
|
||||
if (spread0 & (spread0.dtype.type(1) << b)).any())
|
||||
)
|
||||
density_full = _jit_popcount(spread0)
|
||||
# Salva cache scena complete
|
||||
if cache_key is not None:
|
||||
self._scene_cache_put(cache_key, (
|
||||
grays, spread_top, bit_active_top, density_top,
|
||||
spread0, bit_active_full, density_full, top,
|
||||
))
|
||||
for sc in unique_scales:
|
||||
bg_cache_full[sc] = _bg_for_scale(density_full, sc, 1)
|
||||
|
||||
@@ -1601,6 +1700,7 @@ class LineShapeMatcher:
|
||||
raw.append((float(vals[i]), int(xs[i]), int(ys[i]), vi))
|
||||
|
||||
raw.sort(key=lambda c: -c[0])
|
||||
diag["n_raw_candidates"] = len(raw)
|
||||
|
||||
# Mappa vi → score_map per subpixel/refinement
|
||||
score_maps = dict(candidates_per_var)
|
||||
@@ -1632,6 +1732,7 @@ class LineShapeMatcher:
|
||||
preliminary_int.append((score, xi, yi, vi))
|
||||
if len(preliminary_int) >= pre_cap:
|
||||
break
|
||||
diag["n_after_pre_nms"] = len(preliminary_int)
|
||||
|
||||
# Subpixel + refine + verify solo sui candidati pre-NMS (max pre_cap)
|
||||
kept: list[Match] = []
|
||||
@@ -1678,6 +1779,7 @@ class LineShapeMatcher:
|
||||
view_idx=getattr(var, "view_idx", 0),
|
||||
)
|
||||
if ncc < verify_threshold:
|
||||
diag["drop_ncc_low"] += 1
|
||||
continue
|
||||
score_f = (float(score_f) + max(0.0, ncc)) * 0.5
|
||||
# Soft-margin gradient similarity: sostituisce o integra lo
|
||||
@@ -1692,6 +1794,7 @@ class LineShapeMatcher:
|
||||
# abbattere lo shape-score sotto la soglia user. Senza questo
|
||||
# check apparivano match con score < min_score (UI confusing).
|
||||
if float(score_f) < min_score:
|
||||
diag["drop_min_score_post_avg"] += 1
|
||||
continue
|
||||
|
||||
# Feature recall (Halcon MinScore-style): conta quante feature
|
||||
@@ -1703,6 +1806,7 @@ class LineShapeMatcher:
|
||||
spread0, var, cx_f, cy_f, ang_f,
|
||||
)
|
||||
if recall < min_recall:
|
||||
diag["drop_recall_low"] += 1
|
||||
continue
|
||||
|
||||
# Ri-traslo coord da spazio crop ROI a spazio scena originale.
|
||||
@@ -1726,6 +1830,7 @@ class LineShapeMatcher:
|
||||
)
|
||||
inside_ratio = float(inter) / poly_area
|
||||
if inside_ratio < 0.75:
|
||||
diag["drop_bbox_out_of_scene"] += 1
|
||||
continue
|
||||
# Penalità scala opzionale: score degrada con distanza da 1.0
|
||||
if scale_penalty > 0.0 and var.scale != 1.0:
|
||||
@@ -1750,6 +1855,7 @@ class LineShapeMatcher:
|
||||
dup = True
|
||||
break
|
||||
if dup:
|
||||
diag["drop_nms_iou"] += 1
|
||||
continue
|
||||
kept.append(Match(
|
||||
cx=cx_out, cy=cy_out,
|
||||
@@ -1760,4 +1866,35 @@ class LineShapeMatcher:
|
||||
))
|
||||
if len(kept) >= max_matches:
|
||||
break
|
||||
diag["n_final"] = len(kept)
|
||||
if debug:
|
||||
# Debug mode: stampa diagnostica su stderr per visibilita' immediata.
|
||||
import sys as _sys
|
||||
_sys.stderr.write(f"[pm2d.find debug] {self._format_diag(diag)}\n")
|
||||
return kept
|
||||
|
||||
def _format_diag(self, diag: dict) -> str:
|
||||
"""Formatta dict diagnostica in una linea leggibile."""
|
||||
return (
|
||||
f"vars: {diag['n_variants_total']} -> "
|
||||
f"top_eval={diag['n_variants_top_evaluated']} "
|
||||
f"top_pass={diag['n_variants_top_passed']} "
|
||||
f"full_eval={diag['n_variants_full_evaluated']} | "
|
||||
f"raw={diag['n_raw_candidates']} "
|
||||
f"pre_nms={diag['n_after_pre_nms']} -> "
|
||||
f"drop[ncc={diag['drop_ncc_low']}, "
|
||||
f"score={diag['drop_min_score_post_avg']}, "
|
||||
f"recall={diag['drop_recall_low']}, "
|
||||
f"bbox={diag['drop_bbox_out_of_scene']}, "
|
||||
f"nms={diag['drop_nms_iou']}] = "
|
||||
f"final={diag['n_final']} (top_thresh={diag['top_thresh_used']:.2f})"
|
||||
)
|
||||
|
||||
def get_last_diag(self) -> dict | None:
|
||||
"""Ritorna dict diagnostica dell'ultima chiamata find().
|
||||
|
||||
Halcon-equivalent: oggi inspect_shape_model espone parziali contatori.
|
||||
Util per debug 'perche' 0 match', tuning interattivo, validation.
|
||||
Vedi diag keys per significato (n_variants_top_evaluated, drop_*, ...).
|
||||
"""
|
||||
return getattr(self, "_last_diag", None)
|
||||
|
||||
@@ -217,6 +217,7 @@ class MatchResp(BaseModel):
|
||||
find_time: float
|
||||
num_variants: int
|
||||
annotated_id: str
|
||||
diag: dict | None = None # CC: diagnostica pipeline (drop reasons)
|
||||
|
||||
|
||||
class TuneParams(BaseModel):
|
||||
@@ -521,6 +522,7 @@ def match(p: MatchParams):
|
||||
) for m_ in matches],
|
||||
train_time=t_train, find_time=t_find,
|
||||
num_variants=n, annotated_id=ann_id,
|
||||
diag=m.get_last_diag() if hasattr(m, "get_last_diag") else None,
|
||||
)
|
||||
|
||||
|
||||
@@ -596,6 +598,7 @@ def match_simple(p: SimpleMatchParams):
|
||||
) for mt in matches],
|
||||
train_time=t_train, find_time=t_find,
|
||||
num_variants=n, annotated_id=ann_id,
|
||||
diag=m.get_last_diag() if hasattr(m, "get_last_diag") else None,
|
||||
)
|
||||
|
||||
|
||||
@@ -676,6 +679,103 @@ def list_recipes():
|
||||
return {"files": files, "dir": str(RECIPES_DIR)}
|
||||
|
||||
|
||||
# Cache di matcher caricati da .npz (V feature). Key: nome ricetta.
|
||||
_RECIPE_MATCHERS: OrderedDict = OrderedDict()
|
||||
_RECIPE_MATCHERS_SIZE = 4
|
||||
|
||||
|
||||
@app.post("/recipes/{name}/load")
|
||||
def load_recipe(name: str):
|
||||
"""Carica ricetta .npz e popola cache matcher in memoria.
|
||||
|
||||
Una volta caricata, /match_recipe la usa direttamente senza
|
||||
re-train. Halcon-equivalent read_shape_model + handle.
|
||||
"""
|
||||
safe_name = "".join(c for c in name if c.isalnum() or c in "._-")
|
||||
if not safe_name.endswith(".npz"):
|
||||
safe_name += ".npz"
|
||||
path = RECIPES_DIR / safe_name
|
||||
if not path.is_file():
|
||||
raise HTTPException(404, f"Ricetta non trovata: {safe_name}")
|
||||
m = LineShapeMatcher.load_model(str(path))
|
||||
_RECIPE_MATCHERS[safe_name] = m
|
||||
_RECIPE_MATCHERS.move_to_end(safe_name)
|
||||
while len(_RECIPE_MATCHERS) > _RECIPE_MATCHERS_SIZE:
|
||||
_RECIPE_MATCHERS.popitem(last=False)
|
||||
return {
|
||||
"name": safe_name,
|
||||
"n_variants": len(m.variants),
|
||||
"template_size": list(m.template_size),
|
||||
"use_polarity": m.use_polarity,
|
||||
}
|
||||
|
||||
|
||||
class RecipeMatchParams(BaseModel):
|
||||
recipe: str
|
||||
scene_id: str
|
||||
# Solo find-time params (training gia' fatto offline)
|
||||
min_score: float = 0.65
|
||||
max_matches: int = 25
|
||||
min_recall: float = 0.0
|
||||
use_soft_score: bool = False
|
||||
subpixel_lm: bool = False
|
||||
nms_iou_threshold: float = 0.3
|
||||
coarse_stride: int = 1
|
||||
pyramid_propagate: bool = False
|
||||
greediness: float = 0.0
|
||||
refine_pose_joint: bool = False
|
||||
search_roi: list[int] | None = None
|
||||
verify_threshold: float = 0.5
|
||||
scale_penalty: float = 0.0
|
||||
|
||||
|
||||
@app.post("/match_recipe", response_model=MatchResp)
|
||||
def match_recipe(p: RecipeMatchParams):
|
||||
"""Match con ricetta pre-trained: zero training, solo find."""
|
||||
safe_name = p.recipe if p.recipe.endswith(".npz") else f"{p.recipe}.npz"
|
||||
m = _RECIPE_MATCHERS.get(safe_name)
|
||||
if m is None:
|
||||
# Auto-load on demand
|
||||
path = RECIPES_DIR / safe_name
|
||||
if not path.is_file():
|
||||
raise HTTPException(404, f"Ricetta non trovata: {safe_name}")
|
||||
m = LineShapeMatcher.load_model(str(path))
|
||||
_RECIPE_MATCHERS[safe_name] = m
|
||||
scene = _load_image(p.scene_id)
|
||||
if scene is None:
|
||||
raise HTTPException(404, "Scena non trovata")
|
||||
search_roi_t = tuple(p.search_roi) if p.search_roi else None
|
||||
t0 = time.time()
|
||||
matches = m.find(
|
||||
scene,
|
||||
min_score=p.min_score, max_matches=p.max_matches,
|
||||
verify_threshold=p.verify_threshold,
|
||||
scale_penalty=p.scale_penalty,
|
||||
min_recall=p.min_recall,
|
||||
use_soft_score=p.use_soft_score,
|
||||
subpixel_lm=p.subpixel_lm,
|
||||
nms_iou_threshold=p.nms_iou_threshold,
|
||||
coarse_stride=p.coarse_stride,
|
||||
pyramid_propagate=p.pyramid_propagate,
|
||||
greediness=p.greediness,
|
||||
refine_pose_joint=p.refine_pose_joint,
|
||||
search_roi=search_roi_t,
|
||||
)
|
||||
t_find = time.time() - t0
|
||||
tg = m.template_gray if m.template_gray is not None else np.zeros((1, 1), np.uint8)
|
||||
annotated = _draw_matches(scene, matches, tg)
|
||||
ann_id = _store_image(annotated)
|
||||
return MatchResp(
|
||||
matches=[MatchResult(
|
||||
cx=mt.cx, cy=mt.cy, angle_deg=mt.angle_deg, scale=mt.scale,
|
||||
score=mt.score, bbox_poly=mt.bbox_poly.tolist(),
|
||||
) for mt in matches],
|
||||
train_time=0.0, find_time=t_find,
|
||||
num_variants=len(m.variants), annotated_id=ann_id,
|
||||
diag=m.get_last_diag() if hasattr(m, "get_last_diag") else None,
|
||||
)
|
||||
|
||||
|
||||
# Mount static
|
||||
app.mount("/static", StaticFiles(directory=STATIC_DIR), name="static")
|
||||
|
||||
|
||||
@@ -19,6 +19,7 @@ const PALETTE = [
|
||||
const state = {
|
||||
model: null, scene: null, roi: null, drag: null,
|
||||
matches: [], annotatedImg: null,
|
||||
active_recipe: null, // V: ricetta caricata (string nome) o null
|
||||
};
|
||||
|
||||
// ---------- Forms ----------
|
||||
@@ -307,7 +308,43 @@ function setupROI() {
|
||||
}
|
||||
|
||||
// ---------- Match action ----------
|
||||
async function doMatchRecipe() {
|
||||
if (!state.scene) { setStatus("Carica scena"); return; }
|
||||
setStatus(`Match ricetta ${state.active_recipe}...`);
|
||||
const hc = readHalconFlags();
|
||||
const body = {
|
||||
recipe: state.active_recipe,
|
||||
scene_id: state.scene.id,
|
||||
min_score: parseFloat(document.getElementById("p-min-score").value),
|
||||
max_matches: parseInt(document.getElementById("p-max-matches").value, 10),
|
||||
verify_threshold: 0.50,
|
||||
...hc,
|
||||
};
|
||||
const r = await fetch("/match_recipe", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify(body),
|
||||
});
|
||||
if (!r.ok) { setStatus(`Errore: ${await r.text()}`); return; }
|
||||
const data = await r.json();
|
||||
state.matches = data.matches;
|
||||
state.annotatedImg = await loadImage(
|
||||
`/image/${data.annotated_id}/raw?t=${Date.now()}`);
|
||||
renderScene();
|
||||
renderLegend();
|
||||
document.getElementById("t-train").textContent = "—";
|
||||
document.getElementById("t-find").textContent = `${data.find_time.toFixed(2)}s`;
|
||||
document.getElementById("t-var").textContent = data.num_variants;
|
||||
document.getElementById("t-match").textContent = data.matches.length;
|
||||
renderDiag(data.diag, data.matches.length);
|
||||
setStatus(`${data.matches.length} match trovati (ricetta ${state.active_recipe})`);
|
||||
}
|
||||
|
||||
async function doMatch() {
|
||||
// Path V: ricetta caricata → bypass training, solo find su scena
|
||||
if (state.active_recipe) {
|
||||
return doMatchRecipe();
|
||||
}
|
||||
if (!state.model) { setStatus("Carica modello"); return; }
|
||||
if (!state.scene) { setStatus("Carica scena"); return; }
|
||||
if (!state.roi) { setStatus("Seleziona ROI sul modello"); return; }
|
||||
@@ -373,6 +410,7 @@ async function doMatch() {
|
||||
document.getElementById("t-find").textContent = `${data.find_time.toFixed(2)}s`;
|
||||
document.getElementById("t-var").textContent = data.num_variants;
|
||||
document.getElementById("t-match").textContent = data.matches.length;
|
||||
renderDiag(data.diag, data.matches.length);
|
||||
setStatus(`${data.matches.length} match trovati${hasAdv ? " (avanzato)" : ""}`);
|
||||
}
|
||||
|
||||
@@ -400,6 +438,61 @@ function setStatus(s) {
|
||||
}
|
||||
|
||||
// ---------- Init ----------
|
||||
// ---------- CC: Diagnostica match ----------
|
||||
function renderDiag(diag, n_matches) {
|
||||
const el = document.getElementById("diag-content");
|
||||
if (!diag) {
|
||||
el.innerHTML = '<em style="color:#888">Diagnostica non disponibile</em>';
|
||||
return;
|
||||
}
|
||||
const dropTotal = (diag.drop_ncc_low || 0) + (diag.drop_min_score_post_avg || 0)
|
||||
+ (diag.drop_recall_low || 0) + (diag.drop_bbox_out_of_scene || 0)
|
||||
+ (diag.drop_nms_iou || 0);
|
||||
// Hint contestuali se 0 match
|
||||
let hint = "";
|
||||
if (n_matches === 0) {
|
||||
if (diag.n_after_pre_nms === 0) {
|
||||
hint = `<div style="color:#f88; margin-top:6px">⚠ Nessun candidato sopra soglia.
|
||||
Prova: ↓ <b>min_score</b> o ↓ <b>top_thresh</b> (currently ${diag.top_thresh_used.toFixed(2)})</div>`;
|
||||
} else if (diag.drop_ncc_low > 0 && dropTotal === diag.drop_ncc_low) {
|
||||
hint = `<div style="color:#f88; margin-top:6px">⚠ ${diag.drop_ncc_low} candidati droppati da NCC.
|
||||
Prova: ↓ <b>verify_threshold</b> (filtro_fp più leggero)</div>`;
|
||||
} else if (diag.drop_min_score_post_avg > 0) {
|
||||
hint = `<div style="color:#f88; margin-top:6px">⚠ ${diag.drop_min_score_post_avg} match sotto min_score post-NCC.
|
||||
Prova: ↓ <b>min_score</b></div>`;
|
||||
} else if (diag.drop_recall_low > 0) {
|
||||
hint = `<div style="color:#f88; margin-top:6px">⚠ ${diag.drop_recall_low} match con recall < ${diag.min_recall_used}.
|
||||
Prova: ↓ <b>min_recall</b></div>`;
|
||||
} else if (diag.drop_bbox_out_of_scene > 0) {
|
||||
hint = `<div style="color:#f88; margin-top:6px">⚠ ${diag.drop_bbox_out_of_scene} match con bbox fuori scena.
|
||||
Centro derivato male: aumenta <b>min_score</b> o restringi <b>search_roi</b></div>`;
|
||||
}
|
||||
}
|
||||
const flags = [];
|
||||
if (diag.use_polarity) flags.push("polarity");
|
||||
if (diag.use_soft_score) flags.push("soft");
|
||||
if (diag.subpixel_lm) flags.push("subpix-LM");
|
||||
el.innerHTML = `
|
||||
<div><b>Pipeline pruning:</b></div>
|
||||
<div>varianti: ${diag.n_variants_total} → top_eval=${diag.n_variants_top_evaluated}
|
||||
→ top_pass=${diag.n_variants_top_passed} → full_eval=${diag.n_variants_full_evaluated}</div>
|
||||
<div><b>Candidati:</b> raw=${diag.n_raw_candidates}
|
||||
→ pre_nms=${diag.n_after_pre_nms} → final=${diag.n_final}</div>
|
||||
<div><b>Drop reasons:</b> NCC=${diag.drop_ncc_low}, score=${diag.drop_min_score_post_avg},
|
||||
recall=${diag.drop_recall_low}, bbox=${diag.drop_bbox_out_of_scene}, NMS=${diag.drop_nms_iou}</div>
|
||||
<div><b>Soglie:</b> top=${diag.top_thresh_used.toFixed(2)},
|
||||
min_score=${diag.min_score_used.toFixed(2)},
|
||||
NCC=${diag.verify_threshold_used.toFixed(2)},
|
||||
recall=${diag.min_recall_used.toFixed(2)}</div>
|
||||
${flags.length ? `<div><b>Flag attivi:</b> ${flags.join(", ")}</div>` : ""}
|
||||
${hint}
|
||||
`;
|
||||
// Auto-apri pannello se 0 match (segnala problema)
|
||||
if (n_matches === 0) {
|
||||
document.getElementById("diag-panel").open = true;
|
||||
}
|
||||
}
|
||||
|
||||
// ---------- Auto-tune (Halcon-style) ----------
|
||||
async function doAutoTune() {
|
||||
if (!state.model || !state.roi) {
|
||||
@@ -447,6 +540,57 @@ async function doAutoTune() {
|
||||
}
|
||||
}
|
||||
|
||||
// ---------- V: Recipe load/list/unload ----------
|
||||
async function refreshRecipeList() {
|
||||
try {
|
||||
const r = await fetch("/recipes");
|
||||
if (!r.ok) return;
|
||||
const j = await r.json();
|
||||
const sel = document.getElementById("hc-recipe-list");
|
||||
const cur = sel.value;
|
||||
sel.innerHTML = '<option value="">— ricette disponibili —</option>';
|
||||
for (const f of j.files) {
|
||||
const o = document.createElement("option");
|
||||
o.value = f.name;
|
||||
o.textContent = `${f.name} (${(f.size / 1024).toFixed(1)} KB)`;
|
||||
sel.appendChild(o);
|
||||
}
|
||||
if (cur) sel.value = cur;
|
||||
} catch (e) { /* silent */ }
|
||||
}
|
||||
|
||||
async function loadRecipe() {
|
||||
const sel = document.getElementById("hc-recipe-list");
|
||||
const name = sel.value;
|
||||
if (!name) {
|
||||
alert("Seleziona una ricetta dalla lista.");
|
||||
return;
|
||||
}
|
||||
try {
|
||||
const r = await fetch(`/recipes/${encodeURIComponent(name)}/load`, {
|
||||
method: "POST",
|
||||
});
|
||||
if (!r.ok) throw new Error(await r.text());
|
||||
const j = await r.json();
|
||||
state.active_recipe = j.name;
|
||||
document.getElementById("recipe-status").textContent =
|
||||
`Caricata: ${j.name} — ${j.n_variants} varianti, ` +
|
||||
`${j.template_size[0]}x${j.template_size[1]} px` +
|
||||
(j.use_polarity ? " (polarity)" : "");
|
||||
document.getElementById("recipe-status").style.color = "#0c0";
|
||||
document.getElementById("btn-unload-recipe").disabled = false;
|
||||
} catch (e) {
|
||||
alert(`Errore caricamento: ${e.message}`);
|
||||
}
|
||||
}
|
||||
|
||||
function unloadRecipe() {
|
||||
state.active_recipe = null;
|
||||
document.getElementById("recipe-status").textContent = "Nessuna ricetta caricata";
|
||||
document.getElementById("recipe-status").style.color = "#888";
|
||||
document.getElementById("btn-unload-recipe").disabled = true;
|
||||
}
|
||||
|
||||
// ---------- V: Save recipe ----------
|
||||
async function saveRecipe() {
|
||||
if (!state.model || !state.roi) {
|
||||
@@ -480,6 +624,7 @@ async function saveRecipe() {
|
||||
if (!r.ok) throw new Error(await r.text());
|
||||
const j = await r.json();
|
||||
alert(`Ricetta salvata: ${j.name}\n${j.n_variants} varianti, ${j.size} bytes`);
|
||||
refreshRecipeList();
|
||||
} catch (e) {
|
||||
alert(`Errore salvataggio: ${e.message}`);
|
||||
}
|
||||
@@ -515,6 +660,11 @@ window.addEventListener("DOMContentLoaded", async () => {
|
||||
document.getElementById("btn-autotune").addEventListener("click", doAutoTune);
|
||||
document.getElementById("btn-save-recipe").addEventListener("click",
|
||||
saveRecipe);
|
||||
document.getElementById("btn-load-recipe").addEventListener("click",
|
||||
loadRecipe);
|
||||
document.getElementById("btn-unload-recipe").addEventListener("click",
|
||||
unloadRecipe);
|
||||
refreshRecipeList();
|
||||
const slider = document.getElementById("p-min-score");
|
||||
slider.addEventListener("input", (e) => {
|
||||
document.getElementById("v-score").textContent =
|
||||
|
||||
@@ -190,6 +190,16 @@
|
||||
<input type="text" id="hc-recipe-name" placeholder="nome_ricetta" style="flex:1">
|
||||
<button class="btn" id="btn-save-recipe" type="button">💾 Salva</button>
|
||||
</div>
|
||||
<div style="display:flex; gap:6px; margin-top:6px; align-items:center">
|
||||
<select id="hc-recipe-list" style="flex:1">
|
||||
<option value="">— ricette disponibili —</option>
|
||||
</select>
|
||||
<button class="btn" id="btn-load-recipe" type="button">📂 Carica</button>
|
||||
<button class="btn" id="btn-unload-recipe" type="button" disabled>✖ Stacca</button>
|
||||
</div>
|
||||
<div id="recipe-status" style="margin-top:4px; font-size:11px; color:#888">
|
||||
Nessuna ricetta caricata
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</details>
|
||||
@@ -204,6 +214,16 @@
|
||||
<div class="kv"><span>find:</span><span id="t-find">-</span></div>
|
||||
<div class="kv"><span>varianti:</span><span id="t-var">-</span></div>
|
||||
<div class="kv"><span>match:</span><span id="t-match">-</span></div>
|
||||
|
||||
<details id="diag-panel" style="margin-top:10px">
|
||||
<summary>🔍 Diagnostica (CC)</summary>
|
||||
<div id="diag-content" style="font-family:monospace; font-size:11px;
|
||||
background:#1a1a1a; padding:8px;
|
||||
border-radius:3px; margin-top:6px;
|
||||
line-height:1.5">
|
||||
<em style="color:#888">Esegui un MATCH per vedere la diagnostica</em>
|
||||
</div>
|
||||
</details>
|
||||
</section>
|
||||
</main>
|
||||
|
||||
|
||||
@@ -12,6 +12,9 @@ dependencies = [
|
||||
"uvicorn[standard]>=0.34",
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
pm2d-eval = "pm2d.eval:main"
|
||||
|
||||
[dependency-groups]
|
||||
dev = [
|
||||
"httpx>=0.28.1",
|
||||
|
||||
Reference in New Issue
Block a user