HorNet

class mmcls.models.backbones.HorNet(arch='tiny', in_channels=3, drop_path_rate=0.0, scale=0.3333333333333333, use_layer_scale=True, out_indices=(3,), frozen_stages=- 1, with_cp=False, gap_before_final_norm=True, init_cfg=None)

A PyTorch impl of : HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions Inspiration from https://github.com/raoyongming/HorNet :param arch: HorNet architecture.

If use string, choose from ‘tiny’, ‘small’, ‘base’ and ‘large’. If use dict, it should have below keys: - base_dim (int): The base dimensions of embedding. - depths (List[int]): The number of blocks in each stage. - orders (List[int]): The number of order of gnConv in each

stage.

• dw_cfg (List[dict]): The Config for dw conv.

Defaults to ‘tiny’.

参数

• in_channels (int) – Number of input image channels. Defaults to 3.

• drop_path_rate (float) – Stochastic depth rate. Defaults to 0.

• scale (float) – Scaling parameter of gflayer outputs. Defaults to 1/3.

• use_layer_scale (bool) – Whether to use use_layer_scale in HorNet block. Defaults to True.

• out_indices (Sequence[int]) – Output from which stages. Default: (3, ).

• frozen_stages (int) – Stages to be frozen (stop grad and set eval mode). -1 means not freezing any parameters. Defaults to -1.

• with_cp (bool) – Use checkpoint or not. Using checkpoint will save some memory while slowing down the training speed. Defaults to False.

• gap_before_final_norm (bool) – Whether to globally average the feature map before the final norm layer. In the official repo, it’s only used in classification task. Defaults to True.

• init_cfg (dict, optional) – The Config for initialization. Defaults to None.