samplerate: 256000

preprocess:
  stft:
    window_duration: 0.002
    window_overlap: 0.75
    window_fn: hann
  frequencies:
    max_freq: 120000
    min_freq: 10000
  size:
    height: 128
    resize_factor: 0.5
  spectrogram_transforms:
    - name: pcen
      time_constant: 0.1
      gain: 0.98
      bias: 2
      power: 0.5
    - name: spectral_mean_subtraction

architecture:
  name: UNetBackbone
  input_height: 128
  in_channels: 1
  encoder:
    layers:
      - name: FreqCoordConvDown
        out_channels: 32
      - name: FreqCoordConvDown
        out_channels: 64
      - name: LayerGroup
        layers:
          - name: FreqCoordConvDown
            out_channels: 128
          - name: ConvBlock
            out_channels: 256
  bottleneck:
    channels: 256
    layers:
      - name: SelfAttention
        attention_channels: 256
  decoder:
    layers:
      - name: FreqCoordConvUp
        out_channels: 64
      - name: FreqCoordConvUp
        out_channels: 32
      - name: LayerGroup
        layers:
          - name: FreqCoordConvUp
            out_channels: 32
          - name: ConvBlock
            out_channels: 32

postprocess:
  nms_kernel_size: 9
  detection_threshold: 0.01
  top_k_per_sec: 200