add part code

configs/_base_/schedules/imagenet_bs2048_coslr.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(
+        type='SGD', lr=0.8, momentum=0.9, weight_decay=0.0001, nesterov=True))
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.25,
+        by_epoch=True,
+        begin=0,
+        # about 2500 iterations for ImageNet-1k
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=95,
+        by_epoch=True,
+        begin=5,
+        end=100,
+    )
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=2048)

configs/_base_/schedules/imagenet_bs2048_rsb.py

+# optimizer
+optim_wrapper = dict(optimizer=dict(type='Lamb', lr=0.005, weight_decay=0.02))
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.0001,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=95,
+        eta_min=1.0e-6,
+        by_epoch=True,
+        begin=5,
+        end=100)
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=2048)

configs/_base_/schedules/imagenet_bs256.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001))
+
+# learning policy
+param_scheduler = dict(
+    type='MultiStepLR', by_epoch=True, milestones=[30, 60, 90], gamma=0.1)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/_base_/schedules/imagenet_bs256_140e.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001))
+
+# learning policy
+param_scheduler = dict(
+    type='MultiStepLR', by_epoch=True, milestones=[40, 80, 120], gamma=0.1)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=140, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/_base_/schedules/imagenet_bs256_200e_coslr_warmup.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001))
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.25,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True,
+    ),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=195,
+        by_epoch=True,
+        begin=5,
+        end=200,
+    )
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=200, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/_base_/schedules/imagenet_bs256_coslr.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001))
+
+# learning policy
+param_scheduler = dict(
+    type='CosineAnnealingLR', T_max=100, by_epoch=True, begin=0, end=100)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=100, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/_base_/schedules/imagenet_bs256_coslr_coswd_300e.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.0001))
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.001,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=295,
+        eta_min=1.0e-6,
+        by_epoch=True,
+        begin=5,
+        end=300),
+    dict(
+        type='CosineAnnealingParamScheduler',
+        param_name='weight_decay',
+        eta_min=0.00001,
+        by_epoch=True,
+        begin=0,
+        end=300)
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=300, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/_base_/schedules/imagenet_bs256_epochstep.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='SGD', lr=0.045, momentum=0.9, weight_decay=0.00004))
+
+# learning policy
+param_scheduler = dict(type='StepLR', by_epoch=True, step_size=1, gamma=0.98)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=300, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=256)

configs/_base_/schedules/imagenet_bs4096_AdamW.py

+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(type='AdamW', lr=0.003, weight_decay=0.3),
+    # specific to vit pretrain
+    paramwise_cfg=dict(custom_keys={
+        '.cls_token': dict(decay_mult=0.0),
+        '.pos_embed': dict(decay_mult=0.0)
+    }),
+)
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=1e-4,
+        by_epoch=True,
+        begin=0,
+        end=30,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=270,
+        by_epoch=True,
+        begin=30,
+        end=300,
+    )
+]
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=300, val_interval=1)
+val_cfg = dict()
+test_cfg = dict()
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR,
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=4096)

configs/_base_/schedules/imagenet_lars_coslr_200e.py

+# optimizer wrapper
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='LARS', lr=4.8, weight_decay=1e-6, momentum=0.9))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1e-4,
+        by_epoch=True,
+        begin=0,
+        end=10,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR', T_max=190, by_epoch=True, begin=10, end=200)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=200)

configs/_base_/schedules/imagenet_lars_coslr_90e.py

+# optimizer wrapper
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='LARS', lr=1.6, momentum=0.9, weight_decay=0.))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(type='CosineAnnealingLR', T_max=90, by_epoch=True, begin=0, end=90)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=90)
+val_cfg = dict()
+test_cfg = dict()

configs/_base_/schedules/imagenet_sgd_coslr_100e.py

+# optimizer wrapper
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.3, momentum=0.9, weight_decay=1e-6))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(type='CosineAnnealingLR', T_max=100, by_epoch=True, begin=0, end=100)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=100)
+val_cfg = dict()
+test_cfg = dict()

configs/_base_/schedules/imagenet_sgd_coslr_200e.py

+# optimizer wrapper
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.03, weight_decay=1e-4, momentum=0.9))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(type='CosineAnnealingLR', T_max=200, by_epoch=True, begin=0, end=200)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=200)

configs/_base_/schedules/imagenet_sgd_steplr_100e.py

+# optimizer wrapper
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=1e-4))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(type='MultiStepLR', by_epoch=True, milestones=[60, 80], gamma=0.1)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=100)
+val_cfg = dict()
+test_cfg = dict()

configs/arcface/README.md

+# ArcFace
+
+> [ArcFace: Additive Angular Margin Loss for Deep Face Recognition](https://arxiv.org/abs/1801.07698)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Recently, a popular line of research in face recognition is adopting margins in the well-established softmax loss function to maximize class separability. In this paper, we first introduce an Additive Angular Margin Loss (ArcFace), which not only has a clear geometric interpretation but also significantly enhances the discriminative power. Since ArcFace is susceptible to the massive label noise, we further propose sub-center ArcFace, in which each class contains K sub-centers and training samples only need to be close to any of the K positive sub-centers. Sub-center ArcFace encourages one dominant sub-class that contains the majority of clean faces and non-dominant sub-classes that include hard or noisy faces. Based on this self-propelled isolation, we boost the performance through automatically purifying raw web faces under massive real-world noise. Besides discriminative feature embedding, we also explore the inverse problem, mapping feature vectors to face images. Without training any additional generator or discriminator, the pre-trained ArcFace model can generate identity-preserved face images for both subjects inside and outside the training data only by using the network gradient and Batch Normalization (BN) priors. Extensive experiments demonstrate that ArcFace can enhance the discriminative feature embedding as well as strengthen the generative face synthesis.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/24734142/212606212-8ffc3cd2-dbc1-4abf-8924-22167f3f6e34.png" width="80%"/>
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Retrieve image**
+
+```python
+from mmpretrain import ImageRetrievalInferencer
+
+inferencer = ImageRetrievalInferencer('resnet50-arcface_inshop', prototype='demo/')
+predict = inferencer('demo/dog.jpg', topk=2)[0]
+print(predict[0])
+print(predict[1])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('resnet50-arcface_inshop', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Train/Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Train:
+
+```shell
+python tools/train.py configs/arcface/resnet50-arcface_8xb32_inshop.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/arcface/resnet50-arcface_8xb32_inshop.py https://download.openmmlab.com/mmclassification/v0/arcface/resnet50-arcface_inshop_20230202-b766fe7f.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Image Retrieval on InShop
+
+|           Model           |                      Pretrain                      | Params(M) | Flops(G) | Recall@1 | mAP@10 |                    Config                    |                      Download                      |
+| :-----------------------: | :------------------------------------------------: | :-------: | :------: | :------: | :----: | :------------------------------------------: | :------------------------------------------------: |
+| `resnet50-arcface_inshop` | [ImageNet-21k-mill](https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth) |   31.69   |  16.48   |  90.18   | 69.30  | [config](./resnet50-arcface_8xb32_inshop.py) | [model](https://download.openmmlab.com/mmclassification/v0/arcface/resnet50-arcface_inshop_20230202-b766fe7f.pth) \| [log](https://download.openmmlab.com/mmclassification/v0/arcface/resnet50-arcface_inshop_20230202-b766fe7f.log) |
+
+## Citation
+
+```bibtex
+@inproceedings{deng2018arcface,
+title={ArcFace: Additive Angular Margin Loss for Deep Face Recognition},
+author={Deng, Jiankang and Guo, Jia and Niannan, Xue and Zafeiriou, Stefanos},
+booktitle={CVPR},
+year={2019}
+}
+```

configs/arcface/metafile.yml

+Collections:
+  - Name: ArcFace
+    Metadata:
+      Training Data: InShop
+      Architecture:
+        - Additive Angular Margin Loss
+    Paper:
+      URL: https://arxiv.org/abs/1801.07698
+      Title: 'ArcFace: Additive Angular Margin Loss for Deep Face Recognition'
+    README: configs/arcface/README.md
+    Code:
+      Version: v1.0.0rc3
+      URL: https://github.com/open-mmlab/mmpretrain/blob/v1.0.0rc3/mmcls/models/heads/margin_head.py
+
+Models:
+  - Name: resnet50-arcface_inshop
+    Metadata:
+      FLOPs: 16571226112
+      Parameters: 31693888
+    In Collection: ArcFace
+    Results:
+      - Dataset: InShop
+        Metrics:
+          Recall@1: 90.18
+          mAP@10: 69.30
+        Task: Image Retrieval
+    Weights: https://download.openmmlab.com/mmclassification/v0/arcface/resnet50-arcface_inshop_20230202-b766fe7f.pth
+    Config: configs/arcface/resnet50-arcface_8xb32_inshop.py

configs/arcface/resnet50-arcface_8xb32_inshop.py

+_base_ = [
+    '../_base_/datasets/inshop_bs32_448.py',
+    '../_base_/schedules/cub_bs64.py',
+    '../_base_/default_runtime.py',
+]
+
+pretrained = 'https://download.openmmlab.com/mmclassification/v0/resnet/resnet50_3rdparty-mill_in21k_20220331-faac000b.pth'  # noqa
+model = dict(
+    type='ImageToImageRetriever',
+    image_encoder=[
+        dict(
+            type='ResNet',
+            depth=50,
+            init_cfg=dict(
+                type='Pretrained', checkpoint=pretrained, prefix='backbone')),
+        dict(type='GlobalAveragePooling'),
+    ],
+    head=dict(
+        type='ArcFaceClsHead',
+        num_classes=3997,
+        in_channels=2048,
+        loss=dict(type='CrossEntropyLoss', loss_weight=1.0),
+        init_cfg=None),
+    prototype={{_base_.gallery_dataloader}})
+
+# runtime settings
+default_hooks = dict(
+    # log every 20 intervals
+    logger=dict(type='LoggerHook', interval=20),
+    # save last three checkpoints
+    checkpoint=dict(
+        type='CheckpointHook',
+        save_best='auto',
+        interval=1,
+        max_keep_ckpts=3,
+        rule='greater'))
+
+# optimizer
+optim_wrapper = dict(
+    optimizer=dict(
+        type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0005, nesterov=True))
+
+# learning policy
+param_scheduler = [
+    # warm up learning rate scheduler
+    dict(
+        type='LinearLR',
+        start_factor=0.01,
+        by_epoch=True,
+        begin=0,
+        end=5,
+        # update by iter
+        convert_to_iter_based=True),
+    # main learning rate scheduler
+    dict(
+        type='CosineAnnealingLR',
+        T_max=45,
+        by_epoch=True,
+        begin=5,
+        end=50,
+    )
+]
+
+train_cfg = dict(by_epoch=True, max_epochs=50, val_interval=1)
+
+auto_scale_lr = dict(enable=True, base_batch_size=256)
+
+custom_hooks = [
+    dict(type='PrepareProtoBeforeValLoopHook'),
+    dict(type='SyncBuffersHook')
+]

configs/barlowtwins/README.md

+# BarlowTwins
+
+> [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://arxiv.org/abs/2103.03230)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+Self-supervised learning (SSL) is rapidly closing the gap with supervised methods on large computer vision benchmarks. A successful approach to SSL is to learn embeddings which are invariant to distortions of the input sample. However, a recurring issue with this approach is the existence of trivial constant solutions. Most current methods avoid such solutions by careful implementation details. We propose an objective function that naturally avoids collapse by measuring the cross-correlation matrix between the outputs of two identical networks fed with distorted versions of a sample, and making it as close to the identity matrix as possible. This causes the embedding vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors. The method is called Barlow Twins, owing to neuroscientist H. Barlow's redundancy-reduction principle applied to a pair of identical networks. Barlow Twins does not require large batches nor asymmetry between the network twins such as a predictor network, gradient stopping, or a moving average on the weight updates. Intriguingly it benefits from very high-dimensional output vectors. Barlow Twins outperforms previous methods on ImageNet for semi-supervised classification in the low-data regime, and is on par with current state of the art for ImageNet classification with a linear classifier head, and for transfer tasks of classification and object detection.
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/36138628/163914714-082de804-0b5f-4024-94f9-880e6ef334fa.png" width="800" />
+</div>
+
+## How to use it?
+
+<!-- [TABS-BEGIN] -->
+
+**Predict image**
+
+```python
+from mmpretrain import inference_model
+
+predict = inference_model('resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k', 'demo/bird.JPEG')
+print(predict['pred_class'])
+print(predict['pred_score'])
+```
+
+**Use the model**
+
+```python
+import torch
+from mmpretrain import get_model
+
+model = get_model('barlowtwins_resnet50_8xb256-coslr-300e_in1k', pretrained=True)
+inputs = torch.rand(1, 3, 224, 224)
+out = model(inputs)
+print(type(out))
+# To extract features.
+feats = model.extract_feat(inputs)
+print(type(feats))
+```
+
+**Train/Test Command**
+
+Prepare your dataset according to the [docs](https://mmpretrain.readthedocs.io/en/latest/user_guides/dataset_prepare.html#prepare-dataset).
+
+Train:
+
+```shell
+python tools/train.py configs/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py
+```
+
+Test:
+
+```shell
+python tools/test.py configs/barlowtwins/benchmarks/resnet50_8xb32-linear-coslr-100e_in1k.py https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth
+```
+
+<!-- [TABS-END] -->
+
+## Models and results
+
+### Pretrained models
+
+| Model                                         | Params (M) | Flops (G) |                          Config                          |                                     Download                                     |
+| :-------------------------------------------- | :--------: | :-------: | :------------------------------------------------------: | :------------------------------------------------------------------------------: |
+| `barlowtwins_resnet50_8xb256-coslr-300e_in1k` |   174.54   |   4.11    | [config](barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.json) |
+
+### Image Classification on ImageNet-1k
+
+| Model                                     |                   Pretrain                   | Params (M) | Flops (G) | Top-1 (%) |                   Config                   |                   Download                    |
+| :---------------------------------------- | :------------------------------------------: | :--------: | :-------: | :-------: | :----------------------------------------: | :-------------------------------------------: |
+| `resnet50_barlowtwins-pre_8xb32-linear-coslr-100e_in1k` | [BARLOWTWINS](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth) |   25.56    |   4.11    |   71.80   | [config](benchmarks/resnet50_8xb32-linear-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth) \| [log](https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.json) |
+
+## Citation
+
+```bibtex
+@inproceedings{zbontar2021barlow,
+  title={Barlow twins: Self-supervised learning via redundancy reduction},
+  author={Zbontar, Jure and Jing, Li and Misra, Ishan and LeCun, Yann and Deny, St{\'e}phane},
+  booktitle={International Conference on Machine Learning},
+  year={2021},
+}
+```

configs/barlowtwins/barlowtwins_resnet50_8xb256-coslr-1000e_in1k.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs32_byol.py',
+    '../_base_/default_runtime.py',
+]
+# datasets
+train_dataloader = dict(batch_size=256)
+
+# model settings
+model = dict(
+    type='BarlowTwins',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        norm_cfg=dict(type='SyncBN'),
+        zero_init_residual=True),
+    neck=dict(
+        type='NonLinearNeck',
+        in_channels=2048,
+        hid_channels=8192,
+        out_channels=8192,
+        num_layers=3,
+        with_last_bn=False,
+        with_last_bn_affine=False,
+        with_avg_pool=True,
+        init_cfg=dict(
+            type='Kaiming', distribution='uniform', layer=['Linear'])),
+    head=dict(
+        type='LatentCrossCorrelationHead',
+        in_channels=8192,
+        loss=dict(type='CrossCorrelationLoss')))
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='LARS', lr=1.6, momentum=0.9, weight_decay=1e-6),
+    paramwise_cfg=dict(
+        custom_keys={
+            'bn': dict(decay_mult=0, lr_mult=0.024, lars_exclude=True),
+            'bias': dict(decay_mult=0, lr_mult=0.024, lars_exclude=True),
+            # bn layer in ResNet block downsample module
+            'downsample.1': dict(
+                decay_mult=0, lr_mult=0.024, lars_exclude=True),
+        }))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.6e-4,
+        by_epoch=True,
+        begin=0,
+        end=10,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=990,
+        eta_min=0.0016,
+        by_epoch=True,
+        begin=10,
+        end=1000,
+        convert_to_iter_based=True)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=1000)
+default_hooks = dict(checkpoint=dict(max_keep_ckpts=3))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=2048)

configs/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py

+_base_ = [
+    '../_base_/datasets/imagenet_bs32_byol.py',
+    '../_base_/default_runtime.py',
+]
+# datasets
+train_dataloader = dict(batch_size=256)
+
+# model settings
+model = dict(
+    type='BarlowTwins',
+    backbone=dict(
+        type='ResNet',
+        depth=50,
+        norm_cfg=dict(type='SyncBN'),
+        zero_init_residual=True),
+    neck=dict(
+        type='NonLinearNeck',
+        in_channels=2048,
+        hid_channels=8192,
+        out_channels=8192,
+        num_layers=3,
+        with_last_bn=False,
+        with_last_bn_affine=False,
+        with_avg_pool=True,
+        init_cfg=dict(
+            type='Kaiming', distribution='uniform', layer=['Linear'])),
+    head=dict(
+        type='LatentCrossCorrelationHead',
+        in_channels=8192,
+        loss=dict(type='CrossCorrelationLoss')))
+
+# optimizer
+optim_wrapper = dict(
+    type='OptimWrapper',
+    optimizer=dict(type='LARS', lr=1.6, momentum=0.9, weight_decay=1e-6),
+    paramwise_cfg=dict(
+        custom_keys={
+            'bn': dict(decay_mult=0, lr_mult=0.024, lars_exclude=True),
+            'bias': dict(decay_mult=0, lr_mult=0.024, lars_exclude=True),
+            # bn layer in ResNet block downsample module
+            'downsample.1': dict(
+                decay_mult=0, lr_mult=0.024, lars_exclude=True),
+        }))
+
+# learning rate scheduler
+param_scheduler = [
+    dict(
+        type='LinearLR',
+        start_factor=1.6e-4,
+        by_epoch=True,
+        begin=0,
+        end=10,
+        convert_to_iter_based=True),
+    dict(
+        type='CosineAnnealingLR',
+        T_max=290,
+        eta_min=0.0016,
+        by_epoch=True,
+        begin=10,
+        end=300,
+        convert_to_iter_based=True)
+]
+
+# runtime settings
+train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=300)
+default_hooks = dict(checkpoint=dict(max_keep_ckpts=3))
+
+# NOTE: `auto_scale_lr` is for automatically scaling LR
+# based on the actual training batch size.
+auto_scale_lr = dict(base_batch_size=2048)