# Configuration: base_config.yaml
#
# Global training parameters. Consumed by training/train_semantic.py,
# training/train_frequency.py, and training/data/{dataset,datamodule}.py.

seed: 42
image_size: 512
batch_size: 16
num_workers: 0
lr: 0.0001

# Stream-specific settings.
semantic:
  pretrained: true
  freeze_backbone: true
  unfreeze_last_n_blocks: 2
  output_dim: 1024

frequency:
  pretrained: true
  freeze_backbone: false
  highpass_ratio: 0.08
  output_dim: 768

data:
  # Path to a manifest CSV with an `image_path,label` header (0=Real, 1=AI-Generated).
  # Falls back to an in-memory synthetic dataset for pipeline testing if this
  # path doesn't exist yet. Produced by (see training/data/import_hf.py and
  # training/data/shuffle_manifest.py):
  #   python -m training.data.import_hf --split train --output data/sid_subset --limit <N>
  #   python -m training.data.shuffle_manifest --input data/sid_subset/manifest.csv --output data/sid_subset/manifest_shuffled.csv
  manifest_path: data/sid_binary_10000/manifest.csv
  num_synthetic_samples: 32
  val_split: 0.2

log_level: INFO