mirrors
/
mmselfsup
mirror of https://github.com/open-mmlab/mmselfsup.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[Refactor] refactor Metafile format (#478) 

* update metafile

* update format

* update metafile

* update mae
pull/567/head
Yixiao Fang 2022-10-12 11:06:53 +08:00
parent dee5b68880
commit 337e49e304
18 changed files with 541 additions and 160 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
configs/selfsup/barlowtwins/metafile.yml
View File

@ -19,10 +19,18 @@ Models:
Metadata:
Epochs: 300
Batch Size: 2048
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 71.66
Results: null
Config: configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220419-5ae15f89.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 71.8
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py
Weights: 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

44
configs/selfsup/byol/metafile.yml
View File

@ -14,39 +14,23 @@ Collections:
README: configs/selfsup/byol/README.md
Models:
- Name: byol_resnet50_8xb32-accum16-coslr-200e_in1k
In Collection: BYOL
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 71.72
Config: configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k_20220225-5c8b2c2e.pth
- Name: byol_resnet50_16xb256-coslr-200e_in1k
In Collection: BYOL
Metadata:
Epochs: 200
Batch Size: 4096
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 71.88
Results: null
Config: configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k_20220527-b6f8eedd.pth
- Name: byol_resnet50_8xb32-accum16-coslr-300e_in1k
In Collection: BYOL
Metadata:
Epochs: 300
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 72.93
Config: configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k_20220225-a0daa54a.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 4096
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 71.8
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth

0
configs/selfsup/cae/RAEDME.md → configs/selfsup/cae/README.md
View File

27
configs/selfsup/cae/metafile.yaml
View File

@ -1,27 +0,0 @@
Collections:
- Name: CAE
Metadata:
Training Data: ImageNet-1k
Training Techniques:
- AdamW
Training Resources: 8x A100-80G GPUs
Architecture:
- ViT
Paper:
URL: https://arxiv.org/abs/2202.03026
Title: "Context Autoencoder for Self-Supervised Representation Learning"
README: configs/selfsup/cae/README.md
Models:
- Name: cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k
In Collection: CAE
Metadata:
Epochs: 300
Batch Size: 2048
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.2
Config: configs/selfsup/cae/cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/cae/cae_vit-base-p16_16xb256-coslr-300e_in1k-224_20220427-4c786349.pth

35
configs/selfsup/cae/metafile.yml 100644
View File

@ -0,0 +1,35 @@
Collections:
- Name: CAE
Metadata:
Training Data: ImageNet-1k
Training Techniques:
- AdamW
Training Resources: 16x A100-80G GPUs
Architecture:
- ViT
Paper:
URL: https://arxiv.org/abs/2202.03026
Title: "Context Autoencoder for Self-Supervised Representation Learning"
README: configs/selfsup/cae/README.md
Models:
- Name: cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k
In Collection: CAE
Metadata:
Epochs: 300
Batch Size: 2048
Results: null
Config: configs/selfsup/cae/cae_vit-base-p16_16xb128-amp-coslr-300e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220825-404a1929.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 60.8
Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth

20
configs/selfsup/densecl/metafile.yml
View File

@ -19,10 +19,18 @@ Models:
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 63.62
Results: null
Config: configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k_20220225-8c7808fe.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 63.5
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth

27
configs/selfsup/mae/metafile.yaml
View File

@ -1,27 +0,0 @@
Collections:
- Name: MAE
Metadata:
Training Data: ImageNet-1k
Training Techniques:
- AdamW
Training Resources: 8x A100-80G GPUs
Architecture:
- ViT
Paper:
URL: https://arxiv.org/abs/2111.06377
Title: "Masked Autoencoders Are Scalable Vision Learners"
README: configs/selfsup/mae/README.md
Models:
- Name: mae_vit-base-p16_8xb512-coslr-400e_in1k
In Collection: MAE
Metadata:
Epochs: 400
Batch Size: 4096
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.1
Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-coslr-400e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/mae/mae_vit-base-p16_8xb512-coslr-400e_in1k-224_20220223-85be947b.pth

250
configs/selfsup/mae/metafile.yml 100644
View File

@ -0,0 +1,250 @@
Collections:
- Name: MAE
Metadata:
Training Data: ImageNet-1k
Training Techniques:
- AdamW
Training Resources: 8x A100-80G GPUs
Architecture:
- ViT
Paper:
URL: https://arxiv.org/abs/2111.06377
Title: "Masked Autoencoders Are Scalable Vision Learners"
README: configs/selfsup/mae/README.md
Models:
- Name: mae_vit-base-p16_8xb512-amp-coslr-300e_in1k
In Collection: MAE
Metadata:
Epochs: 300
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 60.8
Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.1
Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
- Name: mae_vit-base-p16_8xb512-amp-coslr-400e_in1k
In Collection: MAE
Metadata:
Epochs: 400
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 62.5
Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.3
Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
- Name: mae_vit-base-p16_8xb512-amp-coslr-800e_in1k
In Collection: MAE
Metadata:
Epochs: 800
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 65.1
Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.3
Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
- Name: mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k
In Collection: MAE
Metadata:
Epochs: 1600
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 67.1
Config: configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.5
Config: configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth
- Name: mae_vit-large-p16_8xb512-amp-coslr-400e_in1k
In Collection: MAE
Metadata:
Epochs: 400
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 70.7
Config: configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 50
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.2
Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
- Name: mae_vit-large-p16_8xb512-amp-coslr-800e_in1k
In Collection: MAE
Metadata:
Epochs: 800
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 73.7
Config: configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 50
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.4
Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
- Name: mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k
In Collection: MAE
Metadata:
Epochs: 1600
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 16384
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 75.5
Config: configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py
- Type: Image Classification
Metadata:
Epochs: 50
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 85.7
Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
- Name: mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py
In Collection: MAE
Metadata:
Epochs: 1600
Batch Size: 4096
Results: null
Config: configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 50
Batch Size: 1024
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 86.9
Config: configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth
- Type: Image Classification
Metadata:
Epochs: 50
Batch Size: 256
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 87.3
Config: configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth

20
configs/selfsup/mocov2/metafile.yml
View File

@ -20,10 +20,18 @@ Models:
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 67.58
Results: null
Config: configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k_20220225-89e03af4.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 67.5
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth

20
configs/selfsup/npid/metafile.yml
View File

@ -20,10 +20,18 @@ Models:
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 57.97
Results: null
Config: configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k_20220225-5fbbda2a.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 58.3
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth

20
configs/selfsup/relative_loc/metafile.yml
View File

@ -19,10 +19,18 @@ Models:
Metadata:
Epochs: 70
Batch Size: 512
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 38.78
Results: null
Config: configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220225-84784688.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 40.4
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth

20
configs/selfsup/rotation_pred/metafile.yml
View File

@ -19,10 +19,18 @@ Models:
Metadata:
Epochs: 70
Batch Size: 128
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 48.12
Results: null
Config: configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220225-5b9f06a0.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 47.0
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth

60
configs/selfsup/simclr/metafile.yml
View File

@ -19,22 +19,58 @@ Models:
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 62.56
Results: null
Config: configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k_20220428-46ef6bb9.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 4096
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 62.7
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth
- Name: simclr_resnet50_16xb256-coslr-200e_in1k
In Collection: SimCLR
Metadata:
Epochs: 200
Batch Size: 4096
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 66.66
Results: null
Config: configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k_20220428-8c24b063.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 4096
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 66.9
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth
- Name: simclr_resnet50_16xb256-coslr-800e_in1k
In Collection: SimCLR
Metadata:
Epochs: 200
Batch Size: 4096
Results: null
Config: configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 4096
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 69.2
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth

73
configs/selfsup/simmim/metafile.yml
View File

@ -7,22 +7,79 @@ Collections:
Training Resources: 16x A100 GPUs
Architecture:
- Swin
- ViT
Paper:
URL: https://arxiv.org/abs/2111.09886
Title: "SimMIM: A Simple Framework for Masked Image Modeling"
README: configs/selfsup/simmim/README.md
Models:
- Name: simmim_swin-base_8xb256-coslr-100e_in1k-192
- Name: simmim_swin-base_16xb128-coslr-100e_in1k-192
In Collection: SimMIM
Metadata:
Epochs: 100
Batch Size: 2048
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.9
Results: null
Config: configs/selfsup/simmim/simmim_swin-base_16xb128-coslr-100e_in1k-192.py
Weights: https://download.openmmlab.com/mmselfsup/simmim/simmim_swin-base_16xb128-coslr-100e_in1k-192_20220316-1d090125.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 2048
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 82.7
Config: configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 2048
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.5
Config: configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py
- Name: simmim_swin-base_16xb128-coslr-800e_in1k-192
In Collection: SimMIM
Metadata:
Epochs: 100
Batch Size: 2048
Results: null
Config: configs/selfsup/simmim/simmim_swin-base_16xb128-coslr-800e_in1k-192.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 2048
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 83.8
Config: configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth
- Name: simmim_swin-large_16xb128-coslr-800e_in1k-192
In Collection: SimMIM
Metadata:
Epochs: 100
Batch Size: 2048
Results: null
Config: configs/selfsup/simmim/simmim_swin-base_16xb128-coslr-800e_in1k-192.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 2048
Results:
- Task: Fine-tuning
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 84.8
Config: configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth

40
configs/selfsup/simsiam/metafile.yml
View File

@ -19,22 +19,38 @@ Models:
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 68.28
Results: null
Config: configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20220225-68a88ad8.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 4096
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 68.3
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth
- Name: simsiam_resnet50_8xb32-coslr-200e_in1k
In Collection: SimSiam
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 69.84
Results: null
Config: configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20220225-2f488143.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 90
Batch Size: 4096
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 69.8
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth

20
configs/selfsup/swav/metafile.yml
View File

@ -19,10 +19,18 @@ Models:
Metadata:
Epochs: 200
Batch Size: 256
Results:
- Task: Self-Supervised Image Classification
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 70.47
Results: null
Config: configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py
Weights: https://download.openmmlab.com/mmselfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220225-0497dd5d.pth
Weights: https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth
Downstream:
- Type: Image Classification
Metadata:
Epochs: 100
Batch Size: 256
Results:
- Task: Linear Evaluation
Dataset: ImageNet-1k
Metrics:
Top 1 Accuracy: 70.5
Config: configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py
Weights: https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth

2
docs/en/model_zoo.md
View File

@ -107,7 +107,7 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
<td>ResNet50</td>
<td>200</td>
<td>256</td>
<td>62.7</td>
<td>67.5</td>
<td>/</td>
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>

3
model-index.yml
View File

@ -12,6 +12,7 @@ Import:
- configs/selfsup/simclr/metafile.yml
- configs/selfsup/simsiam/metafile.yml
- configs/selfsup/swav/metafile.yml
- configs/selfsup/mae/metafile.yaml
- configs/selfsup/mae/metafile.yml
- configs/selfsup/simmim/metafile.yml
- configs/selfsup/barlowtwins/metafile.yml
- configs/selfsup/cae/metafile.yml