Enhancer / models /CodeFormer

Commit History

  1. feat: package isolated two-step Kaggle GPU verification

    supli6669
    7f910bb

  1. fix: restore pipeline correctness and gate training on verified data

    supli6669
    f7c0974

  1. fix(scheduler): patch BasicSR CosineAnnealingRestartLR out-of-bounds crash on resume

    supli6669
    02920b7
  2. fix(pipeline): force zero distortion on pure quality, fix radio state sync, and extend training to 6000 iters

    supli6669
    2371881

  1. fix(kaggle): prune intermediate checkpoints and increase save_checkpoint_freq to prevent disk full

    supli6669
    44a1f54
  2. fix(kaggle): resolve CUDA OOM, KeyError tensor(32) in ONNX export, and checkpoint export path

    supli6669
    c4cb165
  3. feat: v3 ONNX support, ArcFace paths, CPU batch fix, kaggle runner, get_available_models UI

    supli6669
    258dc9e
  4. fix: resolve GPU training bottleneck (num_gpu=1, batch_size=4, prefetch_mode=cuda, workers=4)

    supli6669
    1bc0fd7
  5. fix: reset resume_state to null for clean cloud GPU training and fix export command

    supli6669
    f2922e6
  6. fix: ensure basicsr/version.py is tracked and generated properly

    supli6669
    9908062

  1. chore: clean up temporary log files, test images, and cache

    supli6669
    ea8aeb5

  1. feat: enforce held-out benchmark workflow

    supli6669
    0193004

  1. feat: complete Phase 6 Stage II Transformer fine-tuning setup and verification with exit code 0

    supli6669
    a706587
  2. feat: verify Phase 7 A/B Model & Preset Pipeline with exit code 0

    supli6669
    a83a4d3
  3. feat: verify Phase 3 ArcFace Identity Loss integration with exit code 0

    supli6669
    422604f
  4. feat: add 20 specialized project skills for image quality enhancement and CPU performance

    supli6669
    d6d0cbd

  1. feat: integrate Wink Quality Engine, skin grain retention, eye/lip sparkle, and update Obsidian vault

    supli6669
    f26e2a6
  2. feat(model): integrate ArcFace identity loss into CodeFormer training pipeline (Phase 3)

    supli6669
    2916487
  3. fix(hf): integrate Static INT8 ONNX build into Dockerfile and fix thread state guard in app.py

    supli6669
    b42379b
  4. fix: add gc.collect() in train.py to prevent memory leak during long CPU runs

    supli6669
    d74ed13
  5. fix: train_custom.py never writes to original yml — use temp file to prevent total_iter corruption

    supli6669
    21dc5ba
  6. feat: add sequential model improvement roadmap (Phase 1 complete — yml config fixes)

    supli6669
    7d99559

  1. feat: optimize training parameters, fix pipeline sequential bug, update UI default fidelity, and configure HF Spaces auto-deployment in Docker mode

    supli6669
    fd6554d
  2. Fix training crash on CPU, reduce val_freq, add OpenCV env vars

    supli6669
    4607230
  3. CPU optimizations and UI defaults

    supli6669
    da2865e

  1. feat: optimize CPU performance and add agents rules

    supli6669
    0229606

  1. feat: add Google Colab GPU notebook, ONNX export script, and pipeline ONNX optimization

    supli6669
    f3ee5ae

  1. feat: extend CodeFormer training from iter 1000 to 2000

    supli6669
    2fa8691
  2. fix: resume from iter 915 and reduce checkpoint freq to 50 to prevent disk overflow

    supli6669
    2865df8
  3. chore: bump total_iter to 1000 for CodeFormer and Real-ESRGAN

    supli6669
    c9fea6d

  1. feat: add multi-category dataset crawler + Real-ESRGAN training pipeline⁠

    supli6669
    46aa171
  2. fix: resolve basicSR training loop termination bug when changing dataset size

    supli6669
    57d52e7
  3. merge: resolve conflicts in train_custom.py and CodeFormer_stage3_custom.yml

    supli6669
    e9e5430
  4. feat: add custom stage 3 training runner and fix Windows/CPU resume path compatibility in BasicSR

    supli6669
    7c275a5
  5. feat: implement custom training configurations and runner script for model improvement

    supli6669
    d06e6ed
  6. feat: add CPU-based toy training configs and fix net_g.module AttributeError for CPU training

    supli6669
    a282d8c
  7. fix: resolve NameError in app.py and upgrade Gradio APIs in web-demos

    supli6669
    4b89faf
  8. feat: clone CodeFormer, download pretrained weights, and verify imports

    supli6669
    eeaf8b6