9a9084b3d6
Three optimizations from profiling the cross-check-dominated pipeline (9700X CPU, all pilot-validated on TestImage3/FixImage1): - Reuse the cross-check HR-matting@2048 forward as the segmentation mask (cross_check.reuse_as_seg, default ON; --no-cross-check-as-seg to opt out). Skips the BiRefNet@1024 load+forward entirely: ~66s -> ~45s, one less 0.9GB model. Trimap 99.8% identical, no structural change. - --precision bf16 now fans out to all three models: ViTMatte keeps its weight cast; both BiRefNets run their forward under autocast with a dispatcher-level AutocastCPU fp32 shim for torchvision::deform_conv2d (no bf16 CPU kernel, no autocast wrapper upstream). Shared hardware gate in bgfilter/precision.py falls back to fp32 off native-bf16 hardware. TestImage3: 51.9s -> 33.1s; alpha diff max 0.15, none >0.25. - MIMALLOC_PURGE_DELAY=0 (bgfilter/__init__.py, before torch loads): Windows torch's bundled mimalloc lazily retains ~10GB of freed BiRefNet activations, stacking under ViTMatte's attention peak. 2048x2048 bf16: peak 25.2 -> 21.4GB and slightly faster (73 -> 63s). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
89 lines
4.8 KiB
Python
89 lines
4.8 KiB
Python
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
import typer
|
|
from rich import print
|
|
|
|
from .config import load_settings, override_settings
|
|
from .pipeline import MattingPipeline, run_image
|
|
|
|
app = typer.Typer(help="Offline flat-background character matting.")
|
|
|
|
|
|
@app.command()
|
|
def main(
|
|
input: Path | None = typer.Option(None, "--input", "-i", exists=True, file_okay=True, dir_okay=False),
|
|
output: Path | None = typer.Option(None, "--output", "-o", file_okay=True, dir_okay=False),
|
|
input_dir: Path | None = typer.Option(None, "--input-dir", exists=True, file_okay=False, dir_okay=True),
|
|
output_dir: Path | None = typer.Option(None, "--output-dir", file_okay=False, dir_okay=True),
|
|
debug_dir: Path | None = typer.Option(None, "--debug-dir", file_okay=False, dir_okay=True),
|
|
config: Path | None = typer.Option(None, "--config", exists=True, file_okay=True, dir_okay=False),
|
|
model_name: str | None = typer.Option(None, "--model-name"),
|
|
device: str | None = typer.Option(None, "--device"),
|
|
precision: str | None = typer.Option(None, "--precision", help="Compute precision for all models (ViTMatte cast + BiRefNet autocast): fp32 (default) | bf16 (faster + halves matting activation memory; needs bf16-capable hardware, else falls back to fp32)"),
|
|
screen_color: str | None = typer.Option(None, "--screen-color", help="Background colour prior as #RRGGBB (default: auto-detect the flat background colour)"),
|
|
matting_method: str | None = typer.Option(None, "--matting-method"),
|
|
fallback_to_chroma_alpha: bool | None = typer.Option(None, "--fallback-to-chroma-alpha/--no-fallback-to-chroma-alpha"),
|
|
sure_bg_threshold: float | None = typer.Option(None, "--sure-bg-threshold", min=0.0, max=1.0),
|
|
sure_fg_threshold: float | None = typer.Option(None, "--sure-fg-threshold", min=0.0, max=1.0),
|
|
unknown_radius_ratio: float | None = typer.Option(None, "--unknown-radius-ratio", min=0.0),
|
|
fg_safe_radius_ratio: float | None = typer.Option(None, "--fg-safe-radius-ratio", min=0.0),
|
|
despill: bool | None = typer.Option(None, "--despill/--no-despill"),
|
|
cross_check: bool | None = typer.Option(None, "--cross-check/--no-cross-check", help="Second-opinion veto of background-hued residue between hair strands (default: on; costs one extra model inference)"),
|
|
cross_check_as_seg: bool | None = typer.Option(None, "--cross-check-as-seg/--no-cross-check-as-seg", help="Reuse the cross-check forward as the segmentation mask, skipping the primary seg model (default: on; saves ~20s on CPU; needs cross-check on)"),
|
|
trimap_mode: str | None = typer.Option(None, "--trimap-mode", help="Trimap mode (segmentation pipeline): directional | seg | directional-hard-bg"),
|
|
seg_backend: str | None = typer.Option(None, "--seg-backend", help="Segmentation backend: birefnet (default) | anime-seg"),
|
|
) -> None:
|
|
try:
|
|
settings = override_settings(
|
|
load_settings(config),
|
|
model_name=model_name,
|
|
device=device,
|
|
precision=precision,
|
|
screen_color=screen_color,
|
|
matting_method=matting_method,
|
|
fallback_to_chroma_alpha=fallback_to_chroma_alpha,
|
|
sure_bg_threshold=sure_bg_threshold,
|
|
sure_fg_threshold=sure_fg_threshold,
|
|
unknown_radius_ratio=unknown_radius_ratio,
|
|
fg_safe_radius_ratio=fg_safe_radius_ratio,
|
|
despill=despill,
|
|
cross_check=cross_check,
|
|
cross_check_as_seg=cross_check_as_seg,
|
|
trimap_mode=trimap_mode,
|
|
seg_backend=seg_backend,
|
|
)
|
|
|
|
if input_dir is not None:
|
|
if output_dir is None:
|
|
raise typer.BadParameter("--output-dir is required when --input-dir is used")
|
|
images = sorted(
|
|
p for p in input_dir.iterdir() if p.suffix.lower() in {".png", ".jpg", ".jpeg", ".webp"}
|
|
)
|
|
if not images:
|
|
raise typer.BadParameter(f"No supported images found in {input_dir}")
|
|
pipeline = MattingPipeline(settings)
|
|
for image_path in images:
|
|
out_path = output_dir / f"{image_path.stem}_rgba.png"
|
|
dbg = None if debug_dir is None else debug_dir / image_path.stem
|
|
result = pipeline.run_image(image_path, out_path, dbg)
|
|
print(f"[green]wrote[/green] {result['output']}")
|
|
return
|
|
|
|
if input is None or output is None:
|
|
raise typer.BadParameter("Use either --input/--output or --input-dir/--output-dir")
|
|
|
|
result = run_image(input, output, debug_dir, settings)
|
|
print(f"[green]wrote[/green] {result['output']}")
|
|
except RuntimeError as exc:
|
|
print(f"[red]error:[/red] {exc}")
|
|
raise typer.Exit(code=1) from exc
|
|
except ValueError as exc:
|
|
print(f"[red]config error:[/red] {exc}")
|
|
raise typer.Exit(code=1) from exc
|
|
|
|
|
|
if __name__ == "__main__":
|
|
app()
|