.gitignore

# Project
data/clusters/
data/embeddings/
data/temp/
wandb/
data/models/
data/webapp_cache/
data/analyzation/
data/cherrypicks/
data/hw_imgs/
/data/seed-images/*
/docgenie/playground/test.py
/docgenie/playground/handwritten_text/doc_vqa_handwriting_text_images
/docgenie/playground/handwritten_text/handwriting_raw_tokens
/docgenie/playground/handwritten_text/temp
data/datasets
data/models
data/cluster_plots
data/syn_dataset_statistics_plots
data/gt_embeddings
data/wandb_downloads
data/wandb_project_csvs
data/folders.txt
cache
runs
visualizations
.venv
**/**.__pycache__
/docgenie/playground/handwritten_text/doc_vqa_handwriting_text_images
/docgenie/playground/handwritten_text/temp
data/datasets
data/models

# Python
__pycache__/
*.py[cod]
*$py.class
*.so
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
*.log

# Virtual environments
venv/
env/
ENV/
.venv

# IDE
.vscode/
.idea/
*.swp
*.swo
*~
.DS_Store

# Jupyter Notebook
.ipynb_checkpoints
*.ipynb_checkpoints/

# Model artifacts - download separately
inference/
inference_new/
inference_hf/
model/experiments/hf_conditional_latent/cached_vae/
*.zip


# Datasets - download separately
docvqa-handwritten-sizes4/
syn_docvqa/
iam_dataset/
iam_dataset_processed/
iam_dataset_processed_partial/
docvqa-test/
docvqa-viselems/
docvqa-viselems2/
temp/
generations/

# Generated outputs
output/

# Backup files
*.bak
*.backup
*.tmp

# Testing
.pytest_cache/
.coverage
htmlcov/

# OS
./data/clusters_old/
Thumbs.db


# Training
training/
vae_evaluation/


# Logs and checkpoints
*.pt
# But allow the inference model for handwriting service
!handwriting_service/WordStylist/models/ema_ckpt.pt
*.ckpt
*.pth
*.safetensors

.env

# Playwright
node_modules/
/test-results/
/playwright-report/
/blob-report/
/playwright/.cache/
/playwright/.auth/


!data/models/
!data/models/handwriting/
!data/models/handwriting/char_vocab.json
!data/models/handwriting/config.yaml
!data/models/handwriting/writer_id_map.json
!data/models/handwriting/cached_vae/config.json
data/models/.locks*
data/models/baseline
data/models/legacy
data/models/models*
data/models/pretrained
test_run.py
test_vlm.ipynb
test.ipynb
test2.ipynb
test3.py
test4.py
test5.py
test6.py
data/results
data/results_old/
data/tmp/
docgenie/playground/extract_02_eval_metrics_from_wandb.py
docgenie/playground/extract_metrics_from_wandb.py
data/cached_subsets
data/mixed_datasets
data/results_backup_v1
data/results_v1
data/old-results/
data/embeddings
data/mixed_datasets
data/results_backup_v1
sync_datasets.sh
data/results_latest
data/results_latest copy