Hugging Face's logo

JonathanFhima
/
RLAD-SwinV2-Large

Transformers
ONNX
Safetensors
swinv2_segmenter
retinal-fundus
artery-vein-segmentation
medical-imaging
ophthalmology
swinv2
custom_code
Model card Files
xet
 Community
RLAD-SwinV2-Large / README.md

Commit History

13 days ago

  1. Drop the image-segmentation tag too - HF was inferring pipeline_tag back from it, which drove the misleading pipeline() snippet and task-specific Colab/Kaggle notebook templates (both assume single-label argmax output, which this multi-label model does not produce). artery-vein-segmentation tag already covers discoverability.

    JonathanFhima
    Verified signature
    cf1f116

  2. Remove pipeline_tag: the model is genuinely multi-label (artery/vein channels overlap), so forcing HF image-segmentation pipeline compatibility (argmax-based post_process_semantic_segmentation) would silently produce wrong results. Kept image-segmentation as a plain tag for discoverability.

    JonathanFhima
    Verified signature
    153cae0

  3. Quickstart: fully self-contained AutoModel + AutoImageProcessor snippet, no hf_hub_download needed

    JonathanFhima
    Verified signature
    5344068

  4. Add library_name: transformers (enables the Use this model button), give a full runnable inference snippet instead of just pointing at infer.py

    JonathanFhima
    Verified signature
    afc81b2

  5. Document the standard AutoModel(trust_remote_code=True) loading path; update weights path reference

    JonathanFhima
    Verified signature
    ba54a19

  6. Link the RLAD + PVBM end-to-end tutorial

    JonathanFhima
    Verified signature
    6817c98

  7. Note bfloat16 inference precision in Quickstart

    JonathanFhima
    Verified signature
    95ec695

14 days ago

  1. Link both RLAD and REYIA in the intro sentence

    JonathanFhima
    Verified signature
    10e691d

  2. Reorder: intro, qualitative examples, quickstart, example, results, ablations, license, citation

    JonathanFhima
    Verified signature
    653de4c

  3. Add explanatory sentence before Table 1

    JonathanFhima
    Verified signature
    a19c20a

  4. Condense intro and qualitative-figure section to one sentence each

    JonathanFhima
    Verified signature
    a8c0afb

  5. Move qualitative figure right after intro, remove How it works section

    JonathanFhima
    Verified signature
    e976b35

  6. LES2 is ENRICH; link UZLF to KU Leuven RDR, others to REYIA's own license detail

    JonathanFhima
    Verified signature
    ddacb59

  7. Add Tables 3-4, stop asserting UZLF's release status without evidence

    JonathanFhima
    Verified signature
    cdd735f

  8. Punch up the intro

    JonathanFhima
    Verified signature
    4e81616

  9. Add benchmark example predictions section

    JonathanFhima
    Verified signature
    d654a73

  10. Lead with paper title, add results table, concrete license statuses, trim to match REYIA's voice

    JonathanFhima
    Verified signature
    ca42171

  11. Fix naming: RLAD + SwinV2-Large is primary, LUNetV2 is the internal alias

    JonathanFhima
    Verified signature
    10d3de4

  12. Initial release: LUNetv2 SwinV2-Large retinal AV segmentation, RLAD-augmented

    JonathanFhima
    Verified signature
    7677375