lhk229
a6a313d2d0
Adds bgfilter/segmentation.py: BiRefNetSegmenter produces a soft subject mask that defines topology -- it includes colour-contaminated foreground (green-tinted hair) and excludes see-through holes (finger gaps), the distinction chroma/colour cues cannot make. Validated on both samples: green hair -> foreground, finger gap -> background, both correct. Foundation of the semantic-guided redesign; the mask will drive trimap construction next, with ViTMatte still refining soft edges. - SegmentationSettings (ZhengPeng7/BiRefNet, 1024 input, fp32). - Deps: torchvision, timm, einops, kornia. Weights load from HuggingFace via trust_remote_code; behind a firewall set HF_ENDPOINT=https://hf-mirror.com and bypass the proxy. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
20 lines
168 B
Plaintext
20 lines
168 B
Plaintext
opencv-python
|
|
pillow
|
|
numpy
|
|
scipy
|
|
scikit-image
|
|
pymatting
|
|
torch
|
|
torchvision
|
|
transformers
|
|
accelerate
|
|
safetensors
|
|
huggingface_hub
|
|
timm
|
|
einops
|
|
kornia
|
|
tqdm
|
|
typer
|
|
rich
|
|
PyYAML
|