name: v9-c-cls

anchor:
  reg_max: 16
  strides: [8, 16, 32]

model:
  backbone:
    - Conv:
        args: {out_channels: 64, kernel_size: 3, stride: 2}
        source: 0
    - Conv:
        args: {out_channels: 128, kernel_size: 3, stride: 2}
    - RepNCSPELAN:
        args: {out_channels: 256, part_channels: 128}

    - ADown:
        args: {out_channels: 256}
    - RepNCSPELAN:
        args: {out_channels: 512, part_channels: 256}

    - ADown:
        args: {out_channels: 512}
    - RepNCSPELAN:
        args: {out_channels: 512, part_channels: 512}

    - ADown:
        args: {out_channels: 512}
    - RepNCSPELAN:
        args: {out_channels: 512, part_channels: 512}

  detection:
    - Classification:
        source: -1
        tags: Main
        output: True