File size: 31,305 Bytes
2f382c4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 | #!/usr/bin/env python3
"""AccessibilityAmodal one-command mask, 2D completion, and 3D inference.
This is a lightweight login-node launcher. GPU work is submitted to Slurm via
``slurm/run_accesspath_demo.sbatch``; this process can wait for the
job and report the persistent result directory.
The third-party Accessibility3D model is accessed only through the project adapter
``tools/accessibility_3d_completion.py``.
"""
from __future__ import annotations
import argparse
import json
import os
import re
import shutil
import subprocess
import sys
import time
from datetime import datetime
from pathlib import Path
from accesspath3r.privacy import public_path, sanitize_text
PROJECT_ROOT = Path(__file__).resolve().parents[1]
SBATCH_SCRIPT = PROJECT_ROOT / "slurm" / "run_accesspath_demo.sbatch"
PRIMARY_3D_DIRNAME = "accessibility3d"
DEFAULT_PROMPT_CONFIG = (
PROJECT_ROOT / "configs" / "accessibility_mask_prompts_e5_v2.json"
)
STRUCTURAL_STAIRS_PROMPT_CONFIG = (
PROJECT_ROOT / "configs" / "accessibility_stairs_structural_occlusion_prompts.json"
)
OUTDOOR_STAIRS_NO_OCCLUSION_PROMPT_CONFIG = (
PROJECT_ROOT / "configs" / "accessibility_stairs_outdoor_no_occlusion_prompts.json"
)
CATEGORIES = ("curb_cut", "ramp", "stairs", "tactile_paving", "walkway")
GEOMETRY_ALLOWED_2D_STATUSES = {
"candidate_selected_for_review",
"skipped_empty_removal_mask",
}
TERMINAL_STATES = {
"BOOT_FAIL",
"CANCELLED",
"COMPLETED",
"DEADLINE",
"FAILED",
"NODE_FAIL",
"OUT_OF_MEMORY",
"PREEMPTED",
"REVOKED",
"TIMEOUT",
}
def safe_sample_id(value: str) -> str:
result = re.sub(r"[^A-Za-z0-9_-]+", "_", value).strip("_")
return result or "single_image"
def normalized_state(value: str) -> str:
return value.strip().split()[0].split("+")[0] if value.strip() else ""
def run_command(command: list[str]) -> subprocess.CompletedProcess[str]:
return subprocess.run(
command,
cwd=PROJECT_ROOT,
check=False,
capture_output=True,
text=True,
)
def query_job_state(job_id: str) -> str | None:
queued = run_command(["squeue", "-h", "-j", job_id, "-o", "%T"])
if queued.returncode == 0 and queued.stdout.strip():
return normalized_state(queued.stdout.splitlines()[0])
accounting = run_command(
[
"sacct",
"-n",
"-P",
"-j",
job_id,
"--format=JobIDRaw,State,ExitCode",
]
)
if accounting.returncode != 0:
return None
for line in accounting.stdout.splitlines():
fields = line.split("|")
if len(fields) >= 2 and fields[0] == job_id:
return normalized_state(fields[1])
return None
def format_clock(seconds: float) -> str:
seconds = max(0, int(round(seconds)))
hours, remainder = divmod(seconds, 3600)
minutes, seconds = divmod(remainder, 60)
if hours:
return f"{hours:d}:{minutes:02d}:{seconds:02d}"
return f"{minutes:02d}:{seconds:02d}"
def parse_timestamp(value: object) -> float | None:
if not isinstance(value, str):
return None
try:
return datetime.fromisoformat(value).timestamp()
except ValueError:
return None
def read_progress(output_dir: Path) -> dict | None:
try:
value = json.loads((output_dir / "progress.json").read_text(encoding="utf-8"))
except (FileNotFoundError, json.JSONDecodeError, OSError):
return None
return value if isinstance(value, dict) else None
def infer_progress_from_artifacts(
output_dir: Path,
sample_id: str,
include_generative_3d: bool,
) -> dict | None:
"""Provide useful progress for jobs launched before progress.json existed."""
presentation_manifest = (
output_dir
/ "04_3d_completion"
/ "geometry"
/ "presentation_models"
/ "manifest.json"
)
legacy_variants_manifest = (
output_dir
/ "04_3d_completion"
/ "geometry"
/ "3d_variants"
/ "manifest.json"
)
if not presentation_manifest.is_file() and legacy_variants_manifest.is_file():
presentation_manifest = legacy_variants_manifest
learned_manifest = output_dir / PRIMARY_3D_DIRNAME / "manifest.json"
current_compatibility_manifest = (
output_dir / "04_3d_completion" / "visual_candidate" / "manifest.json"
)
if not learned_manifest.is_file() and current_compatibility_manifest.is_file():
learned_manifest = current_compatibility_manifest
final_marker = learned_manifest if include_generative_3d else presentation_manifest
if final_marker.is_file():
return {
"status": "completed",
"percent": 100.0,
"stage_label": "All outputs completed",
}
milestones = (
(
learned_manifest,
96.0,
"Accessibility3D CUDA Gaussian rotation and dense triangle mesh",
),
(
presentation_manifest,
74.0,
"Diagnostic category-constrained geometry",
),
(
output_dir / "04_3d_completion" / "geometry" / "completed_mesh_turntable_slow.gif",
44.0,
"Continuous-surface and solid 3D views",
),
(
output_dir / "04_3d_completion" / "geometry" / "geometry_manifest.json",
43.0,
"Basic 3D turntable preview",
),
(
output_dir / "03_2d_completion" / "completed_rgb_selected.png",
34.0,
"Depth and 3D geometry reconstruction",
),
(
output_dir / "02_masks" / "metadata.json",
20.0,
"GPU generative 2D completion and candidate selection",
),
(
output_dir / "01_sam3" / "summary.json",
16.0,
"Visible, hidden, amodal, and obstacle masks",
),
)
for marker, percent, label in milestones:
if marker.is_file():
return {"status": "running", "percent": percent, "stage_label": label}
return None
def interpolated_percent(progress: dict, now: float) -> float:
try:
percent = float(progress.get("percent", 0.0))
except (TypeError, ValueError):
percent = 0.0
if progress.get("status") != "running":
return max(0.0, min(100.0, percent))
try:
end_percent = float(progress.get("stage_end_percent", percent))
expected = float(progress.get("stage_expected_seconds", 0.0))
except (TypeError, ValueError):
return max(0.0, min(99.0, percent))
stage_started = parse_timestamp(progress.get("stage_started_at"))
if stage_started is None or expected <= 0 or end_percent <= percent:
return max(0.0, min(99.0, percent))
fraction = max(0.0, min(0.98, (now - stage_started) / expected))
interpolated = percent + (end_percent - percent) * fraction
return max(0.0, min(99.0, interpolated))
def estimated_remaining_seconds(
progress: dict | None,
now: float,
elapsed: float,
base_total: float,
) -> float:
"""Keep ETA conservative when a stage or an earlier stage runs long."""
adjusted_total = max(1.0, base_total)
if not progress or progress.get("status") != "running":
return max(0.0, adjusted_total - elapsed)
overall_started = parse_timestamp(progress.get("started_at"))
stage_started = parse_timestamp(progress.get("stage_started_at"))
try:
start_percent = float(progress.get("percent", 0.0))
stage_expected = float(progress.get("stage_expected_seconds", 0.0))
except (TypeError, ValueError):
return max(0.0, adjusted_total - elapsed)
if overall_started is not None and stage_started is not None:
planned_stage_start = max(0.0, start_percent) / 100.0 * base_total
actual_stage_start = max(0.0, stage_started - overall_started)
adjusted_total += max(0.0, actual_stage_start - planned_stage_start)
adjusted_total += max(0.0, now - stage_started - stage_expected)
return max(0.0, adjusted_total - elapsed)
class ProgressDisplay:
def __init__(self, job_id: str) -> None:
self.job_id = job_id
self.is_tty = sys.stdout.isatty()
self.last_key: tuple[str, str] | None = None
self.last_width = 0
def update(
self,
percent: float,
label: str,
elapsed: float,
eta: float | None,
state: str,
final: bool = False,
) -> None:
width = 28
filled = min(width, max(0, int(round(width * percent / 100.0))))
bar = "#" * filled + "-" * (width - filled)
if state == "PENDING":
timing = f"queue {format_clock(elapsed)} | GPU ETA ~{format_clock(eta or 0)}"
elif state == "FAILED":
timing = f"elapsed {format_clock(elapsed)} | failed"
elif eta is None:
timing = f"elapsed {format_clock(elapsed)} | ETA calculating"
elif eta <= 0 and not final:
timing = f"elapsed {format_clock(elapsed)} | finishing"
else:
timing = f"elapsed {format_clock(elapsed)} | ETA ~{format_clock(eta)}"
line = (
f"[Slurm {self.job_id}] [{bar}] {percent:5.1f}% | "
f"{label} | {timing}"
)
key = (state, label)
if self.is_tty:
padding = " " * max(0, self.last_width - len(line))
print(f"\r{line}{padding}", end="\n" if final else "", flush=True)
self.last_width = len(line)
elif key != self.last_key or final:
print(line, flush=True)
self.last_key = key
def wait_for_job(
job_id: str,
poll_seconds: float,
output_dir: Path,
sample_id: str,
include_generative_3d: bool,
estimated_seconds: float,
) -> str:
missing_polls = 0
submitted_at = time.monotonic()
running_at: float | None = None
display = ProgressDisplay(job_id)
while True:
state = query_job_state(job_id)
now_wall = time.time()
now_monotonic = time.monotonic()
progress = read_progress(output_dir) or infer_progress_from_artifacts(
output_dir,
sample_id,
include_generative_3d,
)
if state:
missing_polls = 0
if state == "RUNNING" and running_at is None:
running_at = now_monotonic
else:
# sacct can lag briefly after a job leaves squeue.
missing_polls += 1
if missing_polls >= 12 and not progress:
raise RuntimeError(
"Unable to read the job state from squeue or sacct. "
f"Check manually with: squeue -j {job_id}"
)
progress_status = progress.get("status") if progress else None
if progress_status == "completed":
runtime_started = parse_timestamp(progress.get("started_at"))
elapsed = now_wall - runtime_started if runtime_started else 0.0
display.update(100.0, "All outputs completed", elapsed, 0.0, "COMPLETED", final=True)
return "COMPLETED"
if progress_status == "failed":
runtime_started = parse_timestamp(progress.get("started_at"))
elapsed = now_wall - runtime_started if runtime_started else 0.0
display.update(
interpolated_percent(progress, now_wall),
str(progress.get("message") or progress.get("stage_label") or "GPU stage failed"),
elapsed,
None,
"FAILED",
final=True,
)
return "FAILED"
if state == "PENDING":
display.update(
0.0,
"Waiting for a GPU",
now_monotonic - submitted_at,
estimated_seconds,
state,
)
else:
if running_at is None:
running_at = now_monotonic
runtime_started = parse_timestamp(progress.get("started_at")) if progress else None
elapsed = (
max(0.0, now_wall - runtime_started)
if runtime_started is not None
else now_monotonic - running_at
)
total_estimate = estimated_seconds
if progress:
try:
total_estimate = float(progress.get("total_estimated_seconds", estimated_seconds))
except (TypeError, ValueError):
pass
percent = interpolated_percent(progress, now_wall) if progress else 0.0
label = (
str(progress.get("stage_label") or "Initializing GPU job")
if progress
else "Initializing GPU job"
)
display.update(
percent,
label,
elapsed,
estimated_remaining_seconds(progress, now_wall, elapsed, total_estimate),
state or "UNKNOWN",
final=bool(state in TERMINAL_STATES),
)
if state in TERMINAL_STATES:
return state
time.sleep(poll_seconds)
def estimate_runtime_seconds(args: argparse.Namespace) -> int:
# Broad SAM3 prompt evaluation and the presentation-model renderer scale
# with image size. These values are calibrated from the 1368x1824 9528
# run; GLB texture baking is accounted for separately because it dominated
# that job's final stage instead of behaving like the normal mesh export.
seconds = (5 if args.reviewed_visible_workspace else 150) + 13 + (24 if not args.no_depth else 6) + 3 + 420
if not args.no_2d:
seconds += 40
if args.fast_2d_baseline:
seconds += 12
if not args.no_generative_3d:
seconds += 75
if args.export_glb:
seconds += 540
return seconds
def build_parser() -> argparse.ArgumentParser:
parser = argparse.ArgumentParser(
description=(
"Submit one accessibility image to SAM3 mask inference, amodal/hidden "
"completion, 2D completion, Depth Anything geometry reconstruction, "
"and Accessibility3D CUDA Gaussian rendering with a dense triangle mesh."
)
)
parser.add_argument("image_pos", nargs="?", help="Input RGB image (positional form).")
parser.add_argument("--image", dest="image_opt", help="Input RGB image.")
parser.add_argument("--category", required=True, choices=CATEGORIES)
parser.add_argument("--sample-id", default=None)
parser.add_argument(
"--output-dir",
default=None,
help=(
"Persistent output directory. "
"Default: output/inference/<sample>_<time>."
),
)
parser.add_argument(
"--prompt-config",
default=None,
help=(
"Optional expert override for the mask prompt JSON. By default, a unified "
"target/occluder prompt bank is evaluated against the input image, so the "
"caller does not need to choose a scene-specific JSON."
),
)
parser.add_argument(
"--reviewed-visible-workspace",
default=None,
help=(
"A one-image workspace saved by serve_accessibility_visible_mask_review.py. "
"Requires explicit human approval; replaces the SAM3 visible-target proposal only."
),
)
parser.add_argument(
"--structural-occluder",
action="store_true",
help=(
"For stairs occluded by a pillar, newel post, banister, or railing. "
"Selects the dedicated structural-occlusion prompt config."
),
)
parser.add_argument(
"--no-target-occluder",
action="store_true",
help=(
"For a visible outdoor stair flight with no target-surface occluder. "
"Uses prompts that exclude permanent handrails and side walls from the obstacle mask."
),
)
parser.add_argument(
"--sd-2d",
action="store_true",
help="Legacy compatibility flag; GPU generative 2D completion is enabled by default.",
)
parser.add_argument(
"--fast-2d-baseline",
action="store_true",
help="Also produce the old OpenCV 2D baseline for comparison (not a primary result).",
)
parser.add_argument("--no-2d", action="store_true", help="Skip GPU generative 2D completion.")
parser.add_argument("--no-depth", action="store_true", help="Use debug perspective geometry instead of Depth Anything.")
parser.add_argument(
"--no-generative-3d",
action="store_true",
help="Skip the primary Accessibility3D CUDA rotation and dense learned mesh.",
)
parser.add_argument(
"--export-glb",
action="store_true",
help="Also export the Accessibility3D dense triangle result as mesh.glb.",
)
parser.add_argument("--allow-large-2d", action="store_true", help="Allow 2D completion masks larger than the normal safety gate.")
parser.add_argument("--no-wait", action="store_true", help="Submit and return immediately instead of waiting for results.")
parser.add_argument("--poll-seconds", type=float, default=5.0, help=argparse.SUPPRESS)
parser.add_argument("--dry-run", action="store_true", help="Validate and print the planned submission without submitting.")
return parser
def resolve_args(args: argparse.Namespace, parser: argparse.ArgumentParser) -> dict[str, str]:
if bool(args.image_pos) == bool(args.image_opt):
parser.error("provide exactly one image, either positional or with --image")
image = Path(args.image_opt or args.image_pos).expanduser().resolve()
if not image.is_file():
parser.error(
"input image does not exist: "
f"{public_path(image, project_root=PROJECT_ROOT)}"
)
if args.poll_seconds < 2:
parser.error("--poll-seconds must be at least 2")
if args.structural_occluder and args.category != "stairs":
parser.error("--structural-occluder currently applies only to --category stairs")
if args.no_target_occluder and args.category != "stairs":
parser.error("--no-target-occluder currently applies only to --category stairs")
if args.structural_occluder and args.no_target_occluder:
parser.error("--structural-occluder and --no-target-occluder are mutually exclusive")
if (args.structural_occluder or args.no_target_occluder) and args.prompt_config:
parser.error("choose one of --structural-occluder, --no-target-occluder, or --prompt-config")
reviewed_visible_workspace = None
if args.reviewed_visible_workspace:
reviewed_visible_workspace = Path(args.reviewed_visible_workspace).expanduser().resolve()
if not reviewed_visible_workspace.is_dir():
parser.error(
"reviewed-visible workspace does not exist: "
f"{public_path(reviewed_visible_workspace, project_root=PROJECT_ROOT)}"
)
if args.structural_occluder:
prompt_config = STRUCTURAL_STAIRS_PROMPT_CONFIG
elif args.no_target_occluder:
prompt_config = OUTDOOR_STAIRS_NO_OCCLUSION_PROMPT_CONFIG
elif args.prompt_config:
prompt_config = Path(args.prompt_config).expanduser().resolve()
else:
prompt_config = DEFAULT_PROMPT_CONFIG
if not prompt_config.is_file():
parser.error(
"prompt config does not exist: "
f"{public_path(prompt_config, project_root=PROJECT_ROOT)}"
)
if not SBATCH_SCRIPT.is_file():
parser.error(
"Slurm script does not exist: "
f"{public_path(SBATCH_SCRIPT, project_root=PROJECT_ROOT)}"
)
if shutil.which("sbatch") is None:
parser.error("sbatch is unavailable; run this command on the configured Slurm server")
sample_id = safe_sample_id(args.sample_id or image.stem)
if args.output_dir:
output_dir = Path(args.output_dir).expanduser().resolve()
else:
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
output_dir = PROJECT_ROOT / "output" / "inference" / f"{sample_id}_{timestamp}"
return {
"IMAGE": str(image),
"CATEGORY": args.category,
"SAMPLE_ID": sample_id,
"OUTPUT_DIR": str(output_dir),
"PROMPT_CONFIG": str(prompt_config),
"RUN_GPU_2D": "0" if args.no_2d else "1",
"RUN_FAST_2D": "1" if args.fast_2d_baseline else "0",
"ALLOW_LARGE_2D": "1" if args.allow_large_2d else "0",
"RUN_DEPTH": "0" if args.no_depth else "1",
"RUN_ACCESSIBILITYAMODAL_VISUAL_3D": "0" if args.no_generative_3d else "1",
"EXPORT_ACCESSIBILITYAMODAL_VISUAL_GLB": "1" if args.export_glb else "0",
"NO_TARGET_OCCLUDER": "1" if args.no_target_occluder else "0",
"REVIEWED_VISIBLE_WORKSPACE": str(reviewed_visible_workspace) if reviewed_visible_workspace else "",
}
def print_result_paths(
output_dir: Path,
sample_id: str,
include_gpu_2d: bool,
include_generative_3d: bool,
include_glb: bool,
reviewed_visible: bool = False,
) -> None:
def shown(path: Path) -> str:
return public_path(
path,
project_root=PROJECT_ROOT,
output_root=output_dir,
)
print("\nResults:")
print(f" output root: {shown(output_dir)}")
if include_gpu_2d:
print(
f" quick review: "
f"{shown(output_dir / '00_quick_review' / 'overview.jpg')}"
)
if reviewed_visible:
print(f" reviewed visible: {shown(output_dir / '01_reviewed_visible' / 'metadata.json')}")
else:
print(f" SAM3 overlay: {shown(output_dir / '01_sam3' / 'samples' / sample_id / 'overlay.png')}")
print(f" mask overlay: {shown(output_dir / '02_masks' / 'mask_overlay.png')}")
print(f" visible mask: {shown(output_dir / '02_masks' / 'target_visible.png')}")
print(f" hidden mask: {shown(output_dir / '02_masks' / 'hidden.png')}")
print(f" amodal mask: {shown(output_dir / '02_masks' / 'target_amodal.png')}")
print(f" obstacle mask: {shown(output_dir / '02_masks' / 'obstacle.png')}")
if include_gpu_2d:
print(f" GPU 2D selected: {shown(output_dir / '03_2d_completion' / 'completed_rgb_selected.png')}")
print(f" GPU 2D candidates: {shown(output_dir / '03_2d_completion' / 'candidate_comparison.jpg')}")
print(f" depth diagnostic: {shown(output_dir / '04_3d_completion' / 'geometry' / 'completed_depth_vis.png')}")
print(f" point-cloud debug: {shown(output_dir / '04_3d_completion' / 'geometry' / 'completed_point_cloud.ply')}")
print(f" geometry debug: {shown(output_dir / '04_3d_completion' / 'geometry' / 'completed_mesh.ply')}")
print(f" geometry fallback: {shown(output_dir / '04_3d_completion' / 'turntable' / 'turntable.gif')}")
print(
" presentation 3D: "
f"{shown(output_dir / '04_3d_completion' / 'geometry' / 'presentation_models')}"
)
if include_generative_3d:
visual_dir = output_dir / PRIMARY_3D_DIRNAME
print(f" quality checks: {shown(output_dir / '05_quality_checks' / 'verification.json')}")
print(f" primary 3D GIF: {shown(visual_dir / 'sample_gaussian.gif')}")
print(f" mesh normal diag: {shown(visual_dir / 'sample_mesh.gif')}")
print(f" primary 3D views: {shown(visual_dir / 'multiview_contact_sheet.jpg')}")
print(f" dense face mesh: {shown(visual_dir / 'mesh.ply')}")
if include_glb:
print(f" textured 3D GLB: {shown(visual_dir / 'mesh.glb')}")
def main(argv: list[str] | None = None) -> int:
parser = build_parser()
args = parser.parse_args(argv)
job_env = resolve_args(args, parser)
output_dir = Path(job_env["OUTPUT_DIR"])
sample_id = job_env["SAMPLE_ID"]
print("AccessibilityAmodal one-command inference")
print(
" image: "
f"{public_path(job_env['IMAGE'], project_root=PROJECT_ROOT)}"
)
print(f" category: {job_env['CATEGORY']}")
if job_env["REVIEWED_VISIBLE_WORKSPACE"]:
print(" visible mask: human-reviewed workspace (SAM3 proposal bypassed)")
print(" prompt config: not used after reviewed-mask validation")
else:
print(
" prompt config: "
f"{public_path(job_env['PROMPT_CONFIG'], project_root=PROJECT_ROOT)}"
)
print(
" output: "
f"{public_path(output_dir, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
print(" GPU execution: Slurm, one GPU (5090 partition)")
print(
" 3D outputs: diagnostic depth/point cloud"
+ (
" + primary Accessibility3D CUDA Gaussian rotation/dense mesh"
if not args.no_generative_3d
else " + category-geometry fallback"
)
)
estimated_seconds = estimate_runtime_seconds(args)
print(
f" estimated time: about {format_clock(estimated_seconds)} after GPU starts "
"(Slurm queue excluded)"
)
command = ["sbatch", "--parsable", "--export=ALL", str(SBATCH_SCRIPT)]
if args.dry_run:
print("Dry run; no job submitted.")
shown_command = [*command[:-1], public_path(command[-1], project_root=PROJECT_ROOT)]
print(" " + " ".join(shown_command))
return 0
environment = os.environ.copy()
environment.update(job_env)
submitted = subprocess.run(
command,
cwd=PROJECT_ROOT,
env=environment,
check=False,
capture_output=True,
text=True,
)
if submitted.returncode != 0:
detail = submitted.stderr.strip() or submitted.stdout.strip()
raise RuntimeError(
"Slurm submission failed: "
+ sanitize_text(
detail,
project_root=PROJECT_ROOT,
output_root=output_dir,
sensitive_paths=(job_env["IMAGE"], job_env["PROMPT_CONFIG"]),
)
)
job_id = submitted.stdout.strip().split(";")[0]
if not job_id.isdigit():
raise RuntimeError(f"Could not parse Slurm job ID from: {submitted.stdout!r}")
print(f"Submitted Slurm job {job_id}")
print(f" stdout: Logs/slurm-{job_id}.out")
print(f" stderr: Logs/slurm-{job_id}.err")
if args.no_wait:
print(f"Monitor with: squeue -j {job_id}")
print_result_paths(
output_dir,
sample_id,
not args.no_2d,
not args.no_generative_3d,
args.export_glb,
bool(job_env["REVIEWED_VISIBLE_WORKSPACE"]),
)
return 0
try:
state = wait_for_job(
job_id,
args.poll_seconds,
output_dir,
sample_id,
not args.no_generative_3d,
estimated_seconds,
)
except KeyboardInterrupt:
print(
f"\nStopped waiting; Slurm job {job_id} is still managed separately. "
f"Cancel it only if needed with: scancel {job_id}",
file=sys.stderr,
)
return 130
if state != "COMPLETED":
raise RuntimeError(
f"Slurm job {job_id} ended with state {state}. "
f"Inspect Logs/slurm-{job_id}.err"
)
expected = output_dir / "02_masks" / "mask_overlay.png"
if not expected.is_file():
raise RuntimeError(
f"Slurm job {job_id} completed but the expected mask output is missing: "
f"{public_path(expected, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
preflight_path = output_dir / "05_quality_checks" / "preflight.json"
if preflight_path.is_file():
try:
preflight = json.loads(preflight_path.read_text(encoding="utf-8"))
except (json.JSONDecodeError, OSError):
preflight = {}
if preflight.get("decision") != "accept":
print(
"\n3D generation was intentionally withheld because the mask/structure "
"preflight requires re-prompting or human review."
)
print(
" verification: "
f"{public_path(preflight_path, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
print("Automatic masks are review candidates, not ground truth.")
return 0
completion_manifest_path = output_dir / "03_2d_completion" / "manifest.json"
if not args.no_2d:
if not completion_manifest_path.is_file():
raise RuntimeError(
"Slurm job completed but the 2D completion manifest is missing: "
f"{public_path(completion_manifest_path, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
try:
completion_manifest = json.loads(
completion_manifest_path.read_text(encoding="utf-8")
)
except (json.JSONDecodeError, OSError) as exc:
raise RuntimeError("The 2D completion manifest is unreadable") from exc
completion_status = completion_manifest.get("status")
if completion_status not in GEOMETRY_ALLOWED_2D_STATUSES:
print(
"\nThe 2D result needs review and was not used to condition 3D: "
f"{completion_status!r}. Accessibility3D used the original RGB and strict "
"three-value mask instead."
)
comparison = output_dir / "03_2d_completion" / "candidate_comparison.jpg"
if comparison.is_file():
print(
" candidates: "
f"{public_path(comparison, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
if not args.no_generative_3d:
verification_path = output_dir / "05_quality_checks" / "verification.json"
if not verification_path.is_file():
raise RuntimeError(
"Slurm job completed but the generated-3D verification report is missing: "
f"{public_path(verification_path, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
try:
verification = json.loads(verification_path.read_text(encoding="utf-8"))
except (json.JSONDecodeError, OSError) as exc:
raise RuntimeError("Generated-3D verification report is unreadable") from exc
if verification.get("decision") != "accept":
print(
"\nThe Accessibility3D result remains available for human review, but its "
"structured verification did not accept automatic use."
)
print(
" verification: "
f"{public_path(verification_path, project_root=PROJECT_ROOT, output_root=output_dir)}"
)
print_result_paths(
output_dir,
sample_id,
not args.no_2d,
not args.no_generative_3d,
args.export_glb,
bool(job_env["REVIEWED_VISIBLE_WORKSPACE"]),
)
print("\nAutomatic masks are review candidates, not ground truth.")
return 0
if __name__ == "__main__":
raise SystemExit(main())
|