configs/config_scnet_other.yaml

audio:
  chunk_size: 485100 # 44100 * 11
  num_channels: 2
  sample_rate: 44100
  min_mean_abs: 0.000

model:
  sources:
    - drums
    - bass
    - other
    - vocals
  audio_channels: 2
  dims:
    - 4
    - 32
    - 64
    - 128
  nfft: 4096
  hop_size: 1024
  win_size: 4096
  normalized: True
  band_SR:
    - 0.175
    - 0.392
    - 0.433
  band_stride:
    - 1
    - 4
    - 16
  band_kernel:
    - 3
    - 4
    - 16
  conv_depths:
    - 3
    - 2
    - 1
  compress: 4
  conv_kernel: 3
  num_dplayer: 6
  expand: 1

training:
  batch_size: 10
  gradient_accumulation_steps: 1
  grad_clip: 0
  instruments:
    - drums
    - bass
    - other
    - vocals
  lr: 5.0e-04
  patience: 2
  reduce_factor: 0.95
  target_instrument: null
  num_epochs: 1000
  num_steps: 1000
  q: 0.95
  coarse_loss_clip: true
  ema_momentum: 0.999
  optimizer: adam
  other_fix: false # it's needed for checking on multisong dataset if other is actually instrumental
  use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true

augmentations:
  enable: true # enable or disable all augmentations (to fast disable if needed)
  loudness: true # randomly change loudness of each stem on the range (loudness_min; loudness_max)
  loudness_min: 0.5
  loudness_max: 1.5
  mixup: true # mix several stems of same type with some probability (only works for dataset types: 1, 2, 3)
  mixup_probs:
    !!python/tuple # 2 additional stems of the same type (1st with prob 0.2, 2nd with prob 0.02)
    - 0.2
    - 0.02
  mixup_loudness_min: 0.5
  mixup_loudness_max: 1.5

inference:
  batch_size: 8
  dim_t: 256
  num_overlap: 4
  normalize: true