_target_: text_recognizer.network.convnext.convnext.ConvNext
dim: 8
dim_mults: [2, 8]
depths: [2, 2]
attn:
  _target_: text_recognizer.network.convnext.transformer.Transformer
  attn:
    _target_: text_recognizer.network.convnext.transformer.Attention
    dim: 64
    heads: 4
    dim_head: 64
    scale: 8
  ff:
    _target_: text_recognizer.network.convnext.transformer.FeedForward
    dim: 64
    mult: 4