Hugging Face's logo

Spaces:
NMundhra
/
OCT-Image-Classifier-Model
Sleeping

App Files Community
OCT-Image-Classifier-Model / app.py

Commit History

  1. fix: harden _run_classification to handle Gradio 4+ FileData Pydantic model⁠

    NMundhra
    f8f0fd8

  2. fix(input): set gr.Image type='filepath' for Gradio 4+ API file handling

    NMundhra
    c97cde3

  3. fix(adapter): return dict mapping {'path': cam_img_path} for Gradio 4+ FileData serialization

    NMundhra
    f4753ed

  4. fix(adapter): save Grad-CAM overlay to temp filepath for Gradio FileData compatibility

    NMundhra
    1a222d7

  5. fix(app): add comprehensive image_input type handling for dictionary/path/PIL objects

    NMundhra
    754d54a

  6. fix(app): import spaces first and wrap demo.launch() inside main guard for ZeroGPU supervisor

    NMundhra
    3fe9172

  7. fix(app): call demo.launch() without hardcoded server_port for ZeroGPU container socket compatibility

    NMundhra
    258db9f

  8. fix(app): place demo.queue() and demo.launch() inside if HAS_GRADIO block

    NMundhra
    4aed69b

  9. fix(app): add demo.queue() and standard main guard launcher for Hugging Face Gradio supervisor

    NMundhra
    b43fb26

  10. fix(app): launch demo unconditionally at root level to prevent container exit 0

    NMundhra
    c0286fc

  11. fix: check HAS_ZEROGPU before @spaces.GPU to prevent connection reset on CPU hardware

    NMundhra
    cda4955

  1. Upload app.py with huggingface_hub

    NMundhra
    Verified signature
    1fa9e8d

  2. Upload app.py with huggingface_hub

    NMundhra
    Verified signature
    356d0f9

  1. Fix L1 gatekeeper ResNet-50 compatibility, integrate L1-L2-L3 pipeline and return Base64 GradCAMs

    NMundhra
    194eedd

  1. Hotfix: extract model_state_dict from checkpoint

    NMundhra
    04f512c

  2. Add Bucket upload and huggingface_hub

    NMundhra
    698a40b

  3. Track model weights with LFS

    NMundhra
    8ccabdf