mirror of
https://github.com/open-mmlab/mmclassification.git
synced 2025-06-03 21:53:55 +08:00
08dc8c75d3
* 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>
43 lines
1.3 KiB
Python
43 lines
1.3 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
from typing import Dict, List
|
|
|
|
import torch
|
|
|
|
from mmpretrain.registry import MODELS
|
|
from mmpretrain.structures import DataSample
|
|
from .base import BaseSelfSupervisor
|
|
|
|
|
|
@MODELS.register_module()
|
|
class BarlowTwins(BaseSelfSupervisor):
|
|
"""BarlowTwins.
|
|
|
|
Implementation of `Barlow Twins: Self-Supervised Learning via Redundancy
|
|
Reduction <https://arxiv.org/abs/2103.03230>`_.
|
|
Part of the code is borrowed from:
|
|
`<https://github.com/facebookresearch/barlowtwins/blob/main/main.py>`_.
|
|
"""
|
|
|
|
def loss(self, inputs: List[torch.Tensor], data_samples: List[DataSample],
|
|
**kwargs) -> Dict[str, torch.Tensor]:
|
|
"""The forward function in training.
|
|
|
|
Args:
|
|
inputs (List[torch.Tensor]): The input images.
|
|
data_samples (List[DataSample]): All elements required
|
|
during the forward function.
|
|
|
|
Returns:
|
|
Dict[str, torch.Tensor]: A dictionary of loss components.
|
|
"""
|
|
assert isinstance(inputs, list)
|
|
img_v1 = inputs[0]
|
|
img_v2 = inputs[1]
|
|
|
|
z1 = self.neck(self.backbone(img_v1))[0] # NxC
|
|
z2 = self.neck(self.backbone(img_v2))[0] # NxC
|
|
|
|
loss = self.head.loss(z1, z2)
|
|
losses = dict(loss=loss)
|
|
return losses
|