Compare commits

..

4 Commits

Author SHA1 Message Date
Poulpe
3a6b058f0d fix: 05_inference.py lit thresholds.yaml[inference] au lieu de windowed hardcodé
- Ajoute _load_inference_cfg() qui lit config/thresholds.yaml
- Mode/conf/keyframe_interval/max_frame_num depuis config (streaming par défaut)
- Valide par GX049839_v2: streaming+conf=1.5+kf=1 → 146M pts vs 0 pts en windowed sans conf_threshold
- Ajoute --offload_to_cpu (stable sur RTX 3090 .84)
2026-05-12 16:38:33 +00:00
Poulpe
8880c28af9 auto-iter 2026-05-12: keyframe_interval 6→1 (streaming, validé GX049839_v2 146M pts) 2026-05-12 16:37:06 +00:00
Poulpe
df45fd155d auto-iter 2026-05-12: bottom_visible_pct_min 30→25 (GX019817 29% récupérable) 2026-05-12 10:34:19 +00:00
Poulpe
f0154d7ea5 auto-iter 2026-05-12: log iter-2 + veille 2026-05-12 04:40:56 +00:00
4 changed files with 82 additions and 6 deletions

View File

@@ -15,13 +15,13 @@ frame_extract:
height: 294 height: 294
underwater_r_minus_g: 5 # R < G-5 AND R < B-5 → hors eau underwater_r_minus_g: 5 # R < G-5 AND R < B-5 → hors eau
trim_min_frames: 8 # skip if fewer underwater frames trim_min_frames: 8 # skip if fewer underwater frames
bottom_visible_pct_min: 30 # abaissé de 50 à 30 — avg réel = 37.5%, iter auto 2026-05-11 bottom_visible_pct_min: 25 # abaissé 30→25 — GX019817 (29%) récupérable, iter auto 2026-05-12
inference: inference:
ply_conf_threshold: 1.5 ply_conf_threshold: 1.5
max_frame_num: 1024 max_frame_num: 1024
mode: streaming mode: streaming
keyframe_interval: 6 keyframe_interval: 1
align: align:
max_translation_m: 500 # sanity check on alignment max_translation_m: 500 # sanity check on alignment

View File

@@ -12,3 +12,25 @@
- **Veille** : 3 papers arxiv (GS underwater, AUV nav AI, BALTIC benchmark), 1 repo fort (LingBot-Map maj 3j) ; voir - **Veille** : 3 papers arxiv (GS underwater, AUV nav AI, BALTIC benchmark), 1 repo fort (LingBot-Map maj 3j) ; voir
- **Suggestion prochaine** : si GX020030 toujours degraded après re-run → investiguer trim_hors_eau agressif ; tester 3DGS sur segments turbides AUV210 ; abaisser seuil à 25% si GX019817 (29%) jugé récupérable - **Suggestion prochaine** : si GX020030 toujours degraded après re-run → investiguer trim_hors_eau agressif ; tester 3DGS sur segments turbides AUV210 ; abaisser seuil à 25% si GX019817 (29%) jugé récupérable
## Itération 2 — 2026-05-12 04:30 UTC
- Signal détecté : jamais appelé par → 4 segments récupérables bloqués degraded ; bug yaml dupliqué (clé en double dans thresholds.yaml)
- Patch appliqué :
- AUTO-COMMIT : fix clé yaml dupliquée dans
- RUN MANUEL : avec sur 4 segments → 15→19 done, 16→12 degraded
- PR #8 : intégration stage 04b dans + no-regression guard (skip si after_pct < before_pct)
- Type : auto-commit (yaml fix) + PR Gitea #8 (algo pipeline)
- Sanity check : dry-run avant run réel ; GX019817 correctement skippé (guard actif 29%→0%)
- Veille : 5 papers arxiv (UW-3DGS, VISO fort signal USBL+cam, RUSSO, VIMS, review UW-3D), 4 repos actifs (dust3r/monst3r/vggt/CUT3R) ; voir
- Suggestion prochaine : évaluer VISO pour remplacer pose estimation pure-caméra dans stage 06_align (utilise USBL déjà dispo dans pipeline) ; investiguer GX019817 structure (good frames au milieu, trim head+tail requis)
## Itération 2 — 2026-05-12 04:30 UTC
- Signal détecté : 04b_trim_water.py jamais appelé par run_pipeline.sh → 4 segments récupérables bloqués degraded ; bug yaml dupliqué frame_extract (clé en double dans thresholds.yaml)
- Patch appliqué :
- AUTO-COMMIT 8b826b0 : fix clé yaml dupliquée frame_extract dans thresholds.yaml
- RUN MANUEL : 04b_trim_water.py avec COSMA_QC_BOTTOM_OK_PCT=30 sur 4 segments → 15 → 19 done, 16 → 12 degraded
- PR #8 : intégration stage 04b dans run_pipeline.sh + no-regression guard (skip si after_pct < before_pct)
- Type : auto-commit (yaml fix) + PR Gitea #8 (algo pipeline)
- Sanity check : dry-run avant run réel ; GX019817 correctement skippé via guard (29%→0% détecté)
- Veille : 5 papers arxiv (UW-3DGS, VISO fort signal USBL+cam, RUSSO, VIMS, review UW-3D), 4 repos actifs ; voir veille/2026-05-12-0430-iter-2.md
- Suggestion prochaine : évaluer VISO arxiv:2601.01144 pour stage 06_align (USBL+cam+IMU) ; investiguer GX019817 (good frames au milieu, trim bilateral requis)

View File

@@ -32,11 +32,24 @@ import sys
import time import time
from pathlib import Path from pathlib import Path
import yaml
sys.path.insert(0, str(Path(__file__).parent.parent)) sys.path.insert(0, str(Path(__file__).parent.parent))
from orchestrator.db import init_db, get_conn, upsert_job, record_metric, now_iso from orchestrator.db import init_db, get_conn, upsert_job, record_metric, now_iso
PIPELINE_BASE = Path(os.environ.get("COSMA_PIPELINE_BASE", "/home/cosma/cosma-pipeline")) PIPELINE_BASE = Path(os.environ.get("COSMA_PIPELINE_BASE", "/home/cosma/cosma-pipeline"))
def _load_inference_cfg() -> dict:
"""Load inference params from thresholds.yaml, with sane defaults."""
cfg_path = Path(__file__).parent.parent / "config" / "thresholds.yaml"
try:
data = yaml.safe_load(cfg_path.read_text())
return data.get("inference", {})
except Exception:
return {}
_INF_CFG = _load_inference_cfg()
WORKERS = { WORKERS = {
".84": { ".84": {
"host": "192.168.0.84", "host": "192.168.0.84",
@@ -146,19 +159,37 @@ def run_inference(frames_dir: Path, worker_key: str, mission_name: str,
return metrics return metrics
print(f" [05] rsync done") print(f" [05] rsync done")
# Step 2: build demo.py command # Step 2: build demo.py command -- params from thresholds.yaml[inference]
checkpoint = f"{w['ai_dir']}/checkpoints/lingbot-map/lingbot-map.pt" checkpoint = f"{w['ai_dir']}/checkpoints/lingbot-map/lingbot-map.pt"
inf_mode = _INF_CFG.get("mode", "streaming")
conf_thr = _INF_CFG.get("ply_conf_threshold", 1.5)
kf_interval = _INF_CFG.get("keyframe_interval", 1)
max_frames = _INF_CFG.get("max_frame_num", 1024)
if inf_mode == "windowed":
window_size = _INF_CFG.get("window_size", 64)
overlap_size = _INF_CFG.get("overlap_size", 16)
mode_flags = (
f"--mode windowed "
f"--window_size {window_size} "
f"--overlap_size {overlap_size} "
)
else: # streaming (default, validated GX049839_v2 146M pts)
mode_flags = (
f"--mode streaming "
f"--keyframe_interval {kf_interval} "
f"--max_frame_num {max_frames} "
)
demo_cmd = ( demo_cmd = (
f"cd {w['ai_dir']} && " f"cd {w['ai_dir']} && "
f"{w['venv']} demo.py " f"{w['venv']} demo.py "
f"--model_path {checkpoint} " f"--model_path {checkpoint} "
f"--image_folder {worker_frames} " f"--image_folder {worker_frames} "
f"--mode windowed " f"{mode_flags}"
f"--window_size 64 " f"--ply_conf_threshold {conf_thr} "
f"--overlap_size 16 "
f"--save_ply {ply_remote} " f"--save_ply {ply_remote} "
f"--save_poses {npz_remote} " f"--save_poses {npz_remote} "
f"--use_sdpa " f"--use_sdpa "
f"--offload_to_cpu "
f"2>&1" f"2>&1"
) )

View File

@@ -0,0 +1,23 @@
# Veille COSMA reconstruction — iter-2 — 2026-05-12 04:30 UTC
## arxiv underwater 3D (7 derniers jours)
- UW-3DGS: Underwater 3D Reconstruction, Physics-Aware Gaussian Splatting (arxiv 2508.06169)
- Visual enhancement + 3D representation underwater: review (arxiv 2505.01869)
## arxiv AUV SLAM / point cloud
- VISO: Robust Underwater Visual-Inertial-Sonar SLAM (arxiv 2601.01144) — VIS+sonar, fort intérêt pour pipeline USBL
- RUSSO: Underwater SLAM stéréo+sonar+IMU (arxiv 2503.01434)
- VIMS: Visual-Inertial-Magnetic-Sonar SLAM (arxiv 2506.15126)
## Repos GitHub actifs
- naver/dust3r (7k★): actif, base pipeline lingbot-map
- Junyi42/monst3r (ICLR 2025): géométrie vidéo dynamique
- facebookresearch/vggt (CVPR 2025 Best Paper): reconstruction per-frame
- CUT3R: Continuous 3D Perception, mise à jour mars 2026
## HuggingFace
- Video-Depth-Anything-Small: depth video temps-réel
- StereoAdapter: adaptation profondeur stéréo sous-marine
## Signal fort
VISO (arxiv 2601.01144): pipeline USBL+caméra+IMU pour AUV, pourrait remplacer pure-camera pose estimation dans stage 06_align.