ClsBatchNormNeck¶
- class mmpretrain.models.necks.ClsBatchNormNeck(input_features, affine=False, eps=1e-06, init_cfg=None)[源代码]¶
Normalize cls token across batch before head.
This module is proposed by MAE, when running linear probing.
- 参数:
input_features (int) – The dimension of features.
affine (bool) – a boolean value that when set to
True
, this module has learnable affine parameters. Defaults to False.eps (float) – a value added to the denominator for numerical stability. Defaults to 1e-6.
init_cfg (Dict or List[Dict], optional) – Config dict for weight initialization. Defaults to None.