MoCoV2Neck

class mmpretrain.models.necks.MoCoV2Neck(in_channels, hid_channels, out_channels, with_avg_pool=True, init_cfg=None)

The non-linear neck of MoCo v2: fc-relu-fc.

参数:

• in_channels (int) – Number of input channels.

• hid_channels (int) – Number of hidden channels.

• out_channels (int) – Number of output channels.

• with_avg_pool (bool) – Whether to apply the global average pooling after backbone. Defaults to True.

• init_cfg (dict or list[dict], optional) – Initialization config dict. Defaults to None.

forward(x)

Forward function.

参数:

x (Tuple[torch.Tensor]) – The feature map of backbone.

返回:

The output features.

返回类型:

Tuple[torch.Tensor]