MoCoV3Head

class mmpretrain.models.heads.MoCoV3Head(predictor, loss, temperature=1.0)

Head for MoCo v3 Pre-training.

This head builds a predictor, which can be any registered neck component. It also implements latent contrastive loss between two forward features. Part of the code is modified from: https://github.com/facebookresearch/moco-v3/blob/main/moco/builder.py.

参数:

• predictor (dict) – Config dict for module of predictor.

• loss (dict) – Config dict for module of loss functions.

• temperature (float) – The temperature hyper-parameter that controls the concentration level of the distribution. Defaults to 1.0.

loss(base_out, momentum_out)

Generate loss.

参数:

• base_out (torch.Tensor) – NxC features from base_encoder.

• momentum_out (torch.Tensor) – NxC features from momentum_encoder.

返回:

The loss tensor.

返回类型:

torch.Tensor