Yixiao Fang 08dc8c75d3
[Refactor] Add selfsup algorithms. (#1389)
* remove basehead

* add moco series

* add byol simclr simsiam

* add ut

* update configs

* add simsiam hook

* add and refactor beit

* update ut

* add cae

* update extract_feat

* refactor cae

* add mae

* refactor data preprocessor

* update heads

* add maskfeat

* add milan

* add simmim

* add mixmim

* fix lint

* fix ut

* fix lint

* add eva

* add densecl

* add barlowtwins

* add swav

* fix lint

* update readtherdocs rst

* update docs

* update

* Decrease UT memory usage

* Fix docstring

* update DALLEEncoder

* Update model docs

* refactor dalle encoder

* update docstring

* fix ut

* fix config error

* add val_cfg and test_cfg

* refactor clip generator

* fix lint

* pass check

* fix ut

* add lars

* update type of BEiT in configs

* Use MMEngine style momentum in EMA.

* apply mmpretrain solarize

---------

Co-authored-by: mzr1996 <mzr1996@163.com>
2023-03-06 16:53:15 +08:00

32 lines
711 B
Python

# Copyright (c) OpenMMLab. All rights reserved.
import torch
from mmengine.model import BaseModule
from mmpretrain.registry import MODELS
@MODELS.register_module()
class SwAVHead(BaseModule):
"""Head for SwAV Pre-training.
Args:
loss (dict): Config dict for module of loss functions.
"""
def __init__(self, loss: dict) -> None:
super().__init__()
self.loss_module = MODELS.build(loss)
def loss(self, pred: torch.Tensor) -> torch.Tensor:
"""Generate loss.
Args:
pred (torch.Tensor): NxC input features.
Returns:
torch.Tensor: The SwAV loss.
"""
loss = self.loss_module(pred)
return loss