Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Refactor] refactor data flow and engine library #1054

Merged
merged 26 commits into from
Aug 31, 2022
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
update model index
  • Loading branch information
zengyh1900 committed Aug 30, 2022
commit efab12f7a0b8888a121931e1ae512f3c403c8a92
2 changes: 1 addition & 1 deletion .pre-commit-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ repos:
- mdformat-openmmlab
- mdformat_frontmatter
- linkify-it-py
# TODO: uncomment this after mmengine release
# TODO: uncomment after mmengine rebase
# - repo: local
# hooks:
# - id: update-model-index
Expand Down
24 changes: 12 additions & 12 deletions configs/basicvsr_pp/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,12 +7,12 @@ Collections:
- https://arxiv.org/abs/2104.13371
README: configs/basicvsr_pp/README.md
Models:
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_600k-8xb1_reds4.py
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_8xb1-600k_reds4.py
In Collection: BasicVSR++
Metadata:
GPUs: 8 (Tesla V100-PCIE-32GB)
Training Data: REDS
Name: basicvsr-pp_c64n7_600k-8xb1_reds4
Name: basicvsr-pp_c64n7_8xb1-600k_reds4
Results:
- Dataset: REDS
Metrics:
Expand All @@ -24,12 +24,12 @@ Models:
Vimeo-90K-T (BIx4) PSNR (Y): 36.4445
Task: Basicvsr_pp
Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr_plusplus/basicvsr_plusplus_c64n7_8x1_600k_reds4_20210217-db622b2f.pth
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bi.py
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bi.py
In Collection: BasicVSR++
Metadata:
GPUs: 4 (Tesla V100-PCIE-32GB)
Training Data: VIMEO90K
Name: basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bi
Name: basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bi
Results:
- Dataset: VIMEO90K
Metrics:
Expand All @@ -41,12 +41,12 @@ Models:
Vimeo-90K-T (BIx4) PSNR (Y): 37.7864
Task: Basicvsr_pp
Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr_plusplus/basicvsr_plusplus_c64n7_8x1_300k_vimeo90k_bi_20210305-4ef437e2.pth
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bd.py
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bd.py
In Collection: BasicVSR++
Metadata:
GPUs: 4 (Tesla V100-PCIE-32GB)
Training Data: VIMEO90K
Name: basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bd
Name: basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bd
Results:
- Dataset: VIMEO90K
Metrics:
Expand All @@ -58,12 +58,12 @@ Models:
Vimeo-90K-T (BIx4) PSNR (Y): 34.7248
Task: Basicvsr_pp
Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr_plusplus/basicvsr_plusplus_c64n7_8x1_300k_vimeo90k_bd_20210305-ab315ab1.pth
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_600k-8xb1_reds4.py
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_8xb1-600k_reds4.py
In Collection: BasicVSR++
Metadata:
GPUs: 8 (Tesla V100-PCIE-32GB)
Training Data: REDS
Name: basicvsr-pp_c64n7_600k-8xb1_reds4
Name: basicvsr-pp_c64n7_8xb1-600k_reds4
Results:
- Dataset: REDS
Metrics:
Expand All @@ -75,12 +75,12 @@ Models:
Vimeo-90K-T (BIx4) SSIM (Y): 0.9411
Task: Basicvsr_pp
Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr_plusplus/basicvsr_plusplus_c64n7_8x1_600k_reds4_20210217-db622b2f.pth
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bi.py
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bi.py
In Collection: BasicVSR++
Metadata:
GPUs: 4 (Tesla V100-PCIE-32GB)
Training Data: VIMEO90K
Name: basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bi
Name: basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bi
Results:
- Dataset: VIMEO90K
Metrics:
Expand All @@ -92,12 +92,12 @@ Models:
Vimeo-90K-T (BIx4) SSIM (Y): 0.95
Task: Basicvsr_pp
Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr_plusplus/basicvsr_plusplus_c64n7_8x1_300k_vimeo90k_bi_20210305-4ef437e2.pth
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bd.py
- Config: configs/basicvsr_pp/basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bd.py
In Collection: BasicVSR++
Metadata:
GPUs: 4 (Tesla V100-PCIE-32GB)
Training Data: VIMEO90K
Name: basicvsr-pp_c64n7_300k-4xb2_vimeo90k-bd
Name: basicvsr-pp_c64n7_4xb2-300k_vimeo90k-bd
Results:
- Dataset: VIMEO90K
Metrics:
Expand Down
8 changes: 4 additions & 4 deletions configs/dic/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,25 +7,25 @@ Collections:
- https://arxiv.org/abs/2003.13063
README: configs/dic/README.md
Models:
- Config: configs/dic/dic_x8c48b6_150k-4xb2_celeba-hq.py
- Config: configs/dic/dic_x8c48b6_4xb2-150k_celeba-hq.py
In Collection: DIC
Metadata:
GPUs: 4 (Tesla PG503-216)
Training Data: CELEBA
Name: dic_x8c48b6_150k-4xb2_celeba-hq
Name: dic_x8c48b6_4xb2-150k_celeba-hq
Results:
- Dataset: CELEBA
Metrics:
PSNR: 25.2319
SSIM: 0.7422
Task: Dic
Weights: https://download.openmmlab.com/mmediting/restorers/dic/dic_x8c48b6_g4_150k_CelebAHQ_20210611-5d3439ca.pth
- Config: configs/dic/dic_gan-x8c48b6_500k-4xb2_celeba-hq.py
- Config: configs/dic/dic_gan-x8c48b6_4xb2-500k_celeba-hq.py
In Collection: DIC
Metadata:
GPUs: 4 (Tesla PG503-216)
Training Data: CELEBA
Name: dic_gan-x8c48b6_500k-4xb2_celeba-hq
Name: dic_gan-x8c48b6_4xb2-500k_celeba-hq
Results:
- Dataset: CELEBA
Metrics:
Expand Down
12 changes: 6 additions & 6 deletions configs/dim/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,12 +7,12 @@ Collections:
- https://arxiv.org/abs/1703.03872
README: configs/dim/README.md
Models:
- Config: configs/dim/dim_stage1-v16_1000k-1xb1_comp1k.py
- Config: configs/dim/dim_stage1-v16_1xb1-1000k_comp1k.py
In Collection: DIM
Metadata:
GPUs: '1'
Training Data: COMP1K
Name: dim_stage1-v16_1000k-1xb1_comp1k
Name: dim_stage1-v16_1xb1-1000k_comp1k
Results:
- Dataset: COMP1K
Metrics:
Expand All @@ -22,12 +22,12 @@ Models:
SAD: 53.8
Task: Dim
Weights: https://download.openmmlab.com/mmediting/mattors/dim/dim_stage1_v16_1x1_1000k_comp1k_SAD-53.8_20200605_140257-979a420f.pth
- Config: configs/dim/dim_stage2-v16-pln_1000k-1xb1_comp1k.py
- Config: configs/dim/dim_stage2-v16-pln_1xb1-1000k_comp1k.py
In Collection: DIM
Metadata:
GPUs: '1'
Training Data: COMP1K
Name: dim_stage2-v16-pln_1000k-1xb1_comp1k
Name: dim_stage2-v16-pln_1xb1-1000k_comp1k
Results:
- Dataset: COMP1K
Metrics:
Expand All @@ -37,12 +37,12 @@ Models:
SAD: 52.3
Task: Dim
Weights: https://download.openmmlab.com/mmediting/mattors/dim/dim_stage2_v16_pln_1x1_1000k_comp1k_SAD-52.3_20200607_171909-d83c4775.pth
- Config: configs/dim/dim_stage3-v16-pln_1000k-1xb1_comp1k.py
- Config: configs/dim/dim_stage3-v16-pln_1xb1-1000k_comp1k.py
In Collection: DIM
Metadata:
GPUs: '1'
Training Data: COMP1K
Name: dim_stage3-v16-pln_1000k-1xb1_comp1k
Name: dim_stage3-v16-pln_1xb1-1000k_comp1k
Results:
- Dataset: COMP1K
Metrics:
Expand Down
12 changes: 6 additions & 6 deletions configs/edsr/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,12 +7,12 @@ Collections:
- https://arxiv.org/abs/1707.02921
README: configs/edsr/README.md
Models:
- Config: configs/edsr/edsr_x2c64b16_300k-1xb16_div2k.py
- Config: configs/edsr/edsr_x2c64b16_1xb16-300k_div2k.py
In Collection: EDSR
Metadata:
GPUs: '1'
Training Data: DIV2K
Name: edsr_x2c64b16_300k-1xb16_div2k
Name: edsr_x2c64b16_1xb16-300k_div2k
Results:
- Dataset: DIV2K
Metrics:
Expand All @@ -24,12 +24,12 @@ Models:
Set5 SSIM: 0.9372
Task: Edsr
Weights: https://download.openmmlab.com/mmediting/restorers/edsr/edsr_x2c64b16_1x16_300k_div2k_20200604-19fe95ea.pth
- Config: configs/edsr/edsr_x3c64b16_300k-1xb16_div2k.py
- Config: configs/edsr/edsr_x3c64b16_1xb16-300k_div2k.py
In Collection: EDSR
Metadata:
GPUs: '1'
Training Data: DIV2K
Name: edsr_x3c64b16_300k-1xb16_div2k
Name: edsr_x3c64b16_1xb16-300k_div2k
Results:
- Dataset: DIV2K
Metrics:
Expand All @@ -41,12 +41,12 @@ Models:
Set5 SSIM: 0.8912
Task: Edsr
Weights: https://download.openmmlab.com/mmediting/restorers/edsr/edsr_x3c64b16_1x16_300k_div2k_20200608-36d896f4.pth
- Config: configs/edsr/edsr_x4c64b16_300k-1xb16_div2k.py
- Config: configs/edsr/edsr_x4c64b16_1xb16-300k_div2k.py
In Collection: EDSR
Metadata:
GPUs: '1'
Training Data: DIV2K
Name: edsr_x4c64b16_300k-1xb16_div2k
Name: edsr_x4c64b16_1xb16-300k_div2k
Results:
- Dataset: DIV2K
Metrics:
Expand Down
32 changes: 16 additions & 16 deletions configs/edvr/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,96 +7,96 @@ Collections:
- https://arxiv.org/abs/1905.02716?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%253A+arxiv%252FQSXk+%2528ExcitingAds%2521+cs+updates+on+arXiv.org%2529
README: configs/edvr/README.md
Models:
- Config: configs/edvr/edvrm_wotsa_600k-8xb4_reds.py
- Config: configs/edvr/edvrm_wotsa_8xb4-600k_reds.py
In Collection: EDVR
Metadata:
GPUs: '8'
Training Data: REDS
Name: edvrm_wotsa_600k-8xb4_reds
Name: edvrm_wotsa_8xb4-600k_reds
Results:
- Dataset: REDS
Metrics:
PSNR: 30.343
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrm_wotsa_x4_8x4_600k_reds_20200522-0570e567.pth
- Config: configs/edvr/edvrm_600k-8xb4_reds.py
- Config: configs/edvr/edvrm_8xb4-600k_reds.py
In Collection: EDVR
Metadata:
GPUs: '8'
Training Data: REDS
Name: edvrm_600k-8xb4_reds
Name: edvrm_8xb4-600k_reds
Results:
- Dataset: REDS
Metrics:
PSNR: 30.4194
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrm_x4_8x4_600k_reds_20210625-e29b71b5.pth
- Config: configs/edvr/edvrl_wotsa-c128b40_lr2e-4-600k-8xb8_reds4.py
- Config: configs/edvr/edvrl_wotsa-c128b40_8xb8-lr2e-4-600k_reds4.py
In Collection: EDVR
Metadata:
GPUs: 8 (Tesla V100-PCIE-32GB)
Training Data: REDS
Name: edvrl_wotsa-c128b40_lr2e-4-600k-8xb8_reds4
Name: edvrl_wotsa-c128b40_8xb8-lr2e-4-600k_reds4
Results:
- Dataset: REDS
Metrics:
PSNR: 31.001
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrl_wotsa_c128b40_8x8_lr2e-4_600k_reds4_20211228-d895a769.pth
- Config: configs/edvr/edvrl_c128b40_lr2e-4-600k-8xb8_reds4.py
- Config: configs/edvr/edvrl_c128b40_8xb8-lr2e-4-600k_reds4.py
In Collection: EDVR
Metadata:
GPUs: 8 (Tesla V100-PCIE-32GB)
Training Data: REDS
Name: edvrl_c128b40_lr2e-4-600k-8xb8_reds4
Name: edvrl_c128b40_8xb8-lr2e-4-600k_reds4
Results:
- Dataset: REDS
Metrics:
PSNR: 31.0467
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrl_c128b40_8x8_lr2e-4_600k_reds4_20220104-4509865f.pth
- Config: configs/edvr/edvrm_wotsa_600k-8xb4_reds.py
- Config: configs/edvr/edvrm_wotsa_8xb4-600k_reds.py
In Collection: EDVR
Metadata:
GPUs: '8'
Training Data: REDS
Name: edvrm_wotsa_600k-8xb4_reds
Name: edvrm_wotsa_8xb4-600k_reds
Results:
- Dataset: REDS
Metrics:
SSIM: 0.8664
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrm_wotsa_x4_8x4_600k_reds_20200522-0570e567.pth
- Config: configs/edvr/edvrm_600k-8xb4_reds.py
- Config: configs/edvr/edvrm_8xb4-600k_reds.py
In Collection: EDVR
Metadata:
GPUs: '8'
Training Data: REDS
Name: edvrm_600k-8xb4_reds
Name: edvrm_8xb4-600k_reds
Results:
- Dataset: REDS
Metrics:
SSIM: 0.8684
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrm_x4_8x4_600k_reds_20210625-e29b71b5.pth
- Config: configs/edvr/edvrl_wotsa-c128b40_lr2e-4-600k-8xb8_reds4.py
- Config: configs/edvr/edvrl_wotsa-c128b40_8xb8-lr2e-4-600k_reds4.py
In Collection: EDVR
Metadata:
GPUs: 8 (Tesla V100-PCIE-32GB)
Training Data: REDS
Name: edvrl_wotsa-c128b40_lr2e-4-600k-8xb8_reds4
Name: edvrl_wotsa-c128b40_8xb8-lr2e-4-600k_reds4
Results:
- Dataset: REDS
Metrics:
SSIM: 0.8784
Task: Edvr
Weights: https://download.openmmlab.com/mmediting/restorers/edvr/edvrl_wotsa_c128b40_8x8_lr2e-4_600k_reds4_20211228-d895a769.pth
- Config: configs/edvr/edvrl_c128b40_lr2e-4-600k-8xb8_reds4.py
- Config: configs/edvr/edvrl_c128b40_8xb8-lr2e-4-600k_reds4.py
In Collection: EDVR
Metadata:
GPUs: 8 (Tesla V100-PCIE-32GB)
Training Data: REDS
Name: edvrl_c128b40_lr2e-4-600k-8xb8_reds4
Name: edvrl_c128b40_8xb8-lr2e-4-600k_reds4
Results:
- Dataset: REDS
Metrics:
Expand Down
8 changes: 4 additions & 4 deletions configs/esrgan/metafile.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,12 +7,12 @@ Collections:
- https://arxiv.org/abs/1809.00219
README: configs/esrgan/README.md
Models:
- Config: configs/esrgan/esrgan_psnr-x4c64b23g32_1000k-1xb16_div2k.py
- Config: configs/esrgan/esrgan_psnr-x4c64b23g32_1xb16-1000k_div2k.py
In Collection: ESRGAN
Metadata:
GPUs: '1'
Training Data: DIV2K
Name: esrgan_psnr-x4c64b23g32_1000k-1xb16_div2k
Name: esrgan_psnr-x4c64b23g32_1xb16-1000k_div2k
Results:
- Dataset: DIV2K
Metrics:
Expand All @@ -24,12 +24,12 @@ Models:
Set5 SSIM: 0.8559
Task: Esrgan
Weights: https://download.openmmlab.com/mmediting/restorers/esrgan/esrgan_psnr_x4c64b23g32_1x16_1000k_div2k_20200420-bf5c993c.pth
- Config: configs/esrgan/esrgan_x4c64b23g32_400k-1xb16_div2k.py
- Config: configs/esrgan/esrgan_x4c64b23g32_1xb16-400k_div2k.py
In Collection: ESRGAN
Metadata:
GPUs: '1'
Training Data: DIV2K
Name: esrgan_x4c64b23g32_400k-1xb16_div2k
Name: esrgan_x4c64b23g32_1xb16-400k_div2k
Results:
- Dataset: DIV2K
Metrics:
Expand Down
Loading