[Enhancement] Refactor high-level APIs (#1410)

* add high-level inference api and run conditional model good.

* [high-level api] run unconditional model.

* [high-level api] add matting inferencer.

* [high-level api] add inpainting inferencer.

* [high-level api] add translation inferencer.

* [high-level api] add restoration inferencer.

* [high-level api] add inference functions

* [high-level api] add video interpolation inference

* [high-level api] add video restoration inferencer

* [high-level api] pass linter check

* [hight-level api] append  linter check

* [high-level api] delete old interface py code

* [high-level api] remove unused code.

* [high-level api] add comments for inferences.

* [high-level api] delete unused parameters and add extra parameters.

* [high-level api] add inference tutorial.

* [high-level api] add unit test for inference_functions

* [high-level api] fix path error.

* [high-level api] delete old unit test file.

* [high-level api] add ut for edit and conditional inferncer.

* [high-level api] fix edit ut bug and add ut of base_inference, inpainting.

* [high-level api] fix edit.py ut and add two uts.

* [high-level api] add result_out_dir to UTs and add two new uts.

* [high-level api] fix unconditional ut out of ram and add two uts.

* [high-level api] try to satisfy ut code coverage.

* [high-level api] use pytest.raises to catch ut error.

* [high-level api] add more test case in inference_functions

* [high-level api] add video restoration test case.

* [high-level api] video interpolation support dir input output and add ut case

* [high-level api] video restoration support input_dir and add uts.

* [high-level api] add more uts for inference funcs.

* [high-level api] fix bug in inference_functions

* [high-level api] add more uts.

* [high-level api] make colorization inference be tested.

* [high-level api] roll back last commit.

* [high-level api] delete unused code.

* [high-level api] remove default value.

* [high-level api] rename version to setting.

* [high-level api] add examples in edit.py and remove duplicated funcs.

* [high-level api] add log for functions  not used.

* [high-level api] load mean std from cfg and use basedataelement

* [high-level api] do unittest with cu102 version.

* [high-level api] add more uts.

* [high-level api] revert change in da2557b

* [high-level api] add uts.

* [high-level api] replace ckpt to http url./

* [high-level api] read config from metafile and download ckpt automatically.

* [high-level api] make default setting all to 0.

* [high-level api] add content in ipynb

* [high-level api] add ut for test_edit modification.

* [high-level api] fix task in scripts and metafiles

* [high-level api] read task name from metafile

* [high-level api] reproduce nafnet metafile

* [high-level api] put good example to inference ipynb

* [high-level api] revert inpainting demo to global local.

* [high-level api] add model setting and extra parameters in ipynb

* [high-level api] add README.md and more instructions in ipynb.

* [high-level api] append to last commit.

* [high-level api] fix typo.

* [high-level api] add ut to refresh building.

* [high-level api] fix readme review comments.

* [high-level api] refresh readme.

* [high-level api] refresh demo readme and fix typo

* [high-level api] resolve review comment

* [high-level api] fix type.

* [high-level api] revert change.

* [high-level api] misc change.

* [high-level api] fix type again.

Co-authored-by: liuwenran <[email protected]>

.dev_scripts/update_model_index.py

@@ -156,6 +156,8 @@ def parse_md(md_file):
         collection['Name'] = name
         collection_name = name
         is_liif = collection_name.upper() == 'LIIF'
+        task_line = lines[4]
+        task = task_line.strip().split(':')[-1].strip()
         while i < len(lines):
             # parse reference
             if lines[i].startswith('> ['):
@@ -202,7 +204,6 @@ def parse_md(md_file):
 
                 j = i + 2
                 while j < len(lines) and lines[j][0] == '|':
-                    task = get_task_name(md_file)
                     line = lines[j].split('|')[1:-1]
 
                     if line[config_idx].find('](') >= 0:

configs/aot_gan/metafile.yml

@@ -19,5 +19,5 @@ Models:
       PSNR: 19.01
       SSIM: 0.682
       l1 error: 7.07
-    Task: Aot_gan
+    Task: Inpainting
   Weights: https://openmmlab-share.oss-cn-hangzhou.aliyuncs.com/mmediting/inpainting/aot_gan/AOT-GAN_512x512_4x12_places_20220509-6641441b.pth

configs/basicvsr/metafile.yml

@@ -28,7 +28,7 @@ Models:
       Vimeo-90K-T (BDx4) SSIM (Y): 0.9286
       Vimeo-90K-T (BIx4) PSNR (Y): 36.2848
       Vimeo-90K-T (BIx4) SSIM (Y): 0.9395
-    Task: Basicvsr
+    Task: Video Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr/basicvsr_reds4_20120409-0e599677.pth
 - Config: configs/basicvsr/basicvsr_2xb4_vimeo90k-bi.py
   In Collection: BasicVSR
@@ -51,7 +51,7 @@ Models:
       Vimeo-90K-T (BDx4) SSIM (Y): 0.9316
       Vimeo-90K-T (BIx4) PSNR (Y): 37.2026
       Vimeo-90K-T (BIx4) SSIM (Y): 0.9451
-    Task: Basicvsr
+    Task: Video Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr/basicvsr_vimeo90k_bi_20210409-d2d8f760.pth
 - Config: configs/basicvsr/basicvsr_2xb4_vimeo90k-bd.py
   In Collection: BasicVSR
@@ -74,5 +74,5 @@ Models:
       Vimeo-90K-T (BDx4) SSIM (Y): 0.9499
       Vimeo-90K-T (BIx4) PSNR (Y): 34.6427
       Vimeo-90K-T (BIx4) SSIM (Y): 0.9335
-    Task: Basicvsr
+    Task: Video Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr/basicvsr_vimeo90k_bd_20210409-0154dd64.pth

configs/basicvsr_pp/metafile.yml

@@ -22,7 +22,7 @@ Models:
       Vid4 (BIx4) PSNR (Y): 27.7674
       Vimeo-90K-T (BDx4) PSNR (Y): 34.0372
       Vimeo-90K-T (BIx4) PSNR (Y): 36.4445
-    Task: Basicvsr_pp
+    Task: Video Super-Resolution
   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_4xb2-300k_vimeo90k-bi.py
   In Collection: BasicVSR++
@@ -39,7 +39,7 @@ Models:
       Vid4 (BIx4) PSNR (Y): 27.7882
       Vimeo-90K-T (BDx4) PSNR (Y): 33.8972
       Vimeo-90K-T (BIx4) PSNR (Y): 37.7864
-    Task: Basicvsr_pp
+    Task: Video Super-Resolution
   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_4xb2-300k_vimeo90k-bd.py
   In Collection: BasicVSR++
@@ -56,7 +56,7 @@ Models:
       Vid4 (BIx4) PSNR (Y): 26.4377
       Vimeo-90K-T (BDx4) PSNR (Y): 38.2054
       Vimeo-90K-T (BIx4) PSNR (Y): 34.7248
-    Task: Basicvsr_pp
+    Task: Video Super-Resolution
   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_8xb1-600k_reds4.py
   In Collection: BasicVSR++
@@ -73,7 +73,7 @@ Models:
       Vid4 (BIx4) SSIM (Y): 0.8444
       Vimeo-90K-T (BDx4) SSIM (Y): 0.9244
       Vimeo-90K-T (BIx4) SSIM (Y): 0.9411
-    Task: Basicvsr_pp
+    Task: Video Super-Resolution
   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_4xb2-300k_vimeo90k-bi.py
   In Collection: BasicVSR++
@@ -90,7 +90,7 @@ Models:
       Vid4 (BIx4) SSIM (Y): 0.8401
       Vimeo-90K-T (BDx4) SSIM (Y): 0.9195
       Vimeo-90K-T (BIx4) SSIM (Y): 0.95
-    Task: Basicvsr_pp
+    Task: Video Super-Resolution
   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_4xb2-300k_vimeo90k-bd.py
   In Collection: BasicVSR++
@@ -107,5 +107,5 @@ Models:
       Vid4 (BIx4) SSIM (Y): 0.8074
       Vimeo-90K-T (BDx4) SSIM (Y): 0.955
       Vimeo-90K-T (BIx4) SSIM (Y): 0.9351
-    Task: Basicvsr_pp
+    Task: Video Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/basicvsr_plusplus/basicvsr_plusplus_c64n7_8x1_300k_vimeo90k_bd_20210305-ab315ab1.pth

configs/biggan/metafile.yml

@@ -15,7 +15,7 @@ Models:
   Results:
   - Dataset: Others
     Metrics: {}
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan_cifar10_32x32_b25x2_500k_20210728_110906-08b61a44.pth
 - Config: configs/biggan/biggan_ajbrock-sn_8xb32-1500kiters_imagenet1k-128x128.py
   In Collection: BigGAN
@@ -25,7 +25,7 @@ Models:
   Results:
   - Dataset: Others
     Metrics: {}
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan_imagenet1k_128x128_b32x8_best_fid_iter_1232000_20211111_122548-5315b13d.pth
 - Config: configs/biggan/biggan_ajbrock-sn_8xb32-1500kiters_imagenet1k-128x128.py
   In Collection: BigGAN
@@ -35,7 +35,7 @@ Models:
   Results:
   - Dataset: Others
     Metrics: {}
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan_imagenet1k_128x128_b32x8_best_is_iter_1328000_20211111_122911-28c688bc.pth
 - Config: configs/biggan/biggan_cvt-BigGAN-PyTorch-rgb_imagenet1k-128x128.py
   In Collection: BigGAN
@@ -47,7 +47,7 @@ Models:
     Metrics:
       FID: 10.1414
       IS: 96.728
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan_imagenet1k_128x128_cvt_BigGAN-PyTorch_rgb_20210730_125223-3e353fef.pth
 - Config: configs/biggan/biggan-deep_cvt-hugging-face-rgb_imagenet1k-128x128.py
   In Collection: BigGAN
@@ -59,7 +59,7 @@ Models:
     Metrics:
       FID: 5.9471
       IS: 107.161
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan-deep_imagenet1k_128x128_cvt_hugging-face_rgb_20210728_111659-099e96f9.pth
 - Config: configs/biggan/biggan-deep_cvt-hugging-face_rgb_imagenet1k-256x256.py
   In Collection: BigGAN
@@ -71,7 +71,7 @@ Models:
     Metrics:
       FID: 11.3151
       IS: 135.107
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan-deep_imagenet1k_256x256_cvt_hugging-face_rgb_20210728_111735-28651569.pth
 - Config: configs/biggan/biggan-deep_cvt-hugging-face_rgb_imagenet1k-512x512.py
   In Collection: BigGAN
@@ -83,5 +83,5 @@ Models:
     Metrics:
       FID: 16.8728
       IS: 124.368
-    Task: Biggan
+    Task: Conditional GANs
   Weights: https://download.openmmlab.com/mmgen/biggan/biggan-deep_imagenet1k_512x512_cvt_hugging-face_rgb_20210728_112346-a42585f2.pth

configs/cain/metafile.yml

@@ -18,5 +18,5 @@ Models:
     Metrics:
       PSNR: 34.601
       SSIM: 0.9578
-    Task: Cain
+    Task: Video Interpolation
   Weights: https://download.openmmlab.com/mmediting/video_interpolators/cain/cain_b5_g1b32_vimeo90k_triplet_20220530-3520b00c.pth

configs/cyclegan/metafile.yml

@@ -20,7 +20,7 @@ Models:
     Metrics:
       FID: 124.8033
       IS: 1.792
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_80k_facades_20210902_165905-5e2c0876.pth
 - Config: configs/cyclegan/cyclegan_lsgan-id0-resnet-in_1xb1-80kiters_facades.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -33,7 +33,7 @@ Models:
     Metrics:
       FID: 125.1694
       IS: 1.905
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_id0_resnet_in_1x1_80k_facades_convert-bgr_20210902_164411-d8e72b45.pth
 - Config: configs/cyclegan/cyclegan_lsgan-resnet-in_1xb1-250kiters_summer2winter.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -46,7 +46,7 @@ Models:
     Metrics:
       FID: 83.7177
       IS: 2.771
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_246200_summer2winter_convert-bgr_20210902_165932-fcf08dc1.pth
 - Config: configs/cyclegan/cyclegan_lsgan-id0-resnet-in_1xb1-250kiters_summer2winter.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -59,7 +59,7 @@ Models:
     Metrics:
       FID: 83.1418
       IS: 2.72
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_id0_resnet_in_1x1_246200_summer2winter_convert-bgr_20210902_165640-8b825581.pth
 - Config: configs/cyclegan/cyclegan_lsgan-resnet-in_1xb1-250kiters_summer2winter.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -72,7 +72,7 @@ Models:
     Metrics:
       FID: 72.8025
       IS: 3.129
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_246200_summer2winter_convert-bgr_20210902_165932-fcf08dc1.pth
 - Config: configs/cyclegan/cyclegan_lsgan-id0-resnet-in_1xb1-250kiters_summer2winter.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -85,7 +85,7 @@ Models:
     Metrics:
       FID: 73.5001
       IS: 3.107
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_id0_resnet_in_1x1_246200_summer2winter_convert-bgr_20210902_165640-8b825581.pth
 - Config: configs/cyclegan/cyclegan_lsgan-resnet-in_1xb1-270kiters_horse2zebra.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -98,7 +98,7 @@ Models:
     Metrics:
       FID: 64.5225
       IS: 1.418
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_266800_horse2zebra_convert-bgr_20210902_170004-a32c733a.pth
 - Config: configs/cyclegan/cyclegan_lsgan-id0-resnet-in_1xb1-270kiters_horse2zebra.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -111,7 +111,7 @@ Models:
     Metrics:
       FID: 74.777
       IS: 1.542
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_id0_resnet_in_1x1_266800_horse2zebra_convert-bgr_20210902_165724-77c9c806.pth
 - Config: configs/cyclegan/cyclegan_lsgan-resnet-in_1xb1-270kiters_horse2zebra.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -124,7 +124,7 @@ Models:
     Metrics:
       FID: 141.1517
       IS: 3.154
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_266800_horse2zebra_convert-bgr_20210902_170004-a32c733a.pth
 - Config: configs/cyclegan/cyclegan_lsgan-id0-resnet-in_1xb1-270kiters_horse2zebra.py
   In Collection: 'CycleGAN: Unpaired Image-to-Image Translation Using Cycle-Consistent
@@ -137,5 +137,5 @@ Models:
     Metrics:
       FID: 134.3728
       IS: 3.091
-    Task: Cyclegan
+    Task: Image2Image Translation
   Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_id0_resnet_in_1x1_266800_horse2zebra_convert-bgr_20210902_165724-77c9c806.pth

configs/dcgan/metafile.yml

@@ -19,7 +19,7 @@ Models:
   - Dataset: Others
     Metrics:
       MS-SSIM: 0.1395
-    Task: Dcgan
+    Task: Unconditional GANs
   Weights: https://download.openmmlab.com/mmgen/base_dcgan_mnist-64_b128x1_Glr4e-4_Dlr1e-4_5k_20210512_163926-207a1eaf.pth
 - Config: configs/dcgan/dcgan_1xb128-300kiters_celeba-cropped-64.py
   In Collection: Unsupervised Representation Learning with Deep Convolutional Generative
@@ -31,7 +31,7 @@ Models:
   - Dataset: CELEBA
     Metrics:
       MS-SSIM: 0.2899
-    Task: Dcgan
+    Task: Unconditional GANs
   Weights: https://download.openmmlab.com/mmgen/base_dcgan_celeba-cropped_64_b128x1_300kiter_20210408_161607-1f8a2277.pth
 - Config: configs/dcgan/dcgan_1xb128-5epoches_lsun-bedroom-64x64.py
   In Collection: Unsupervised Representation Learning with Deep Convolutional Generative
@@ -43,5 +43,5 @@ Models:
   - Dataset: Others
     Metrics:
       MS-SSIM: 0.2095
-    Task: Dcgan
+    Task: Unconditional GANs
   Weights: https://download.openmmlab.com/mmgen/base_dcgan_lsun-bedroom_64_b128x1_5e_20210408_161713-117c498b.pth

configs/deepfillv1/metafile.yml

@@ -19,7 +19,7 @@ Models:
       PSNR: 23.429
       SSIM: 0.862
       l1 error: 11.019
-    Task: Deepfillv1
+    Task: Inpainting
   Weights: https://download.openmmlab.com/mmediting/inpainting/deepfillv1/deepfillv1_256x256_8x2_places_20200619-c00a0e21.pth
 - Config: configs/deepfillv1/deepfillv1_4xb4_celeba-256x256.py
   In Collection: DeepFillv1
@@ -33,5 +33,5 @@ Models:
       PSNR: 26.878
       SSIM: 0.911
       l1 error: 6.677
-    Task: Deepfillv1
+    Task: Inpainting
   Weights: https://download.openmmlab.com/mmediting/inpainting/deepfillv1/deepfillv1_256x256_4x4_celeba_20200619-dd51a855.pth

configs/deepfillv2/metafile.yml

@@ -19,7 +19,7 @@ Models:
       PSNR: 22.398
       SSIM: 0.815
       l1 error: 8.635
-    Task: Deepfillv2
+    Task: Inpainting
   Weights: https://download.openmmlab.com/mmediting/inpainting/deepfillv2/deepfillv2_256x256_8x2_places_20200619-10d15793.pth
 - Config: configs/deepfillv2/deepfillv2_8xb2_celeba-256x256.py
   In Collection: DeepFillv2
@@ -33,5 +33,5 @@ Models:
       PSNR: 25.721
       SSIM: 0.871
       l1 error: 5.411
-    Task: Deepfillv2
+    Task: Inpainting
   Weights: https://download.openmmlab.com/mmediting/inpainting/deepfillv2/deepfillv2_256x256_8x2_celeba_20200619-c96e5f12.pth

configs/dic/metafile.yml

@@ -18,7 +18,7 @@ Models:
     Metrics:
       PSNR: 25.2319
       SSIM: 0.7422
-    Task: Dic
+    Task: Image Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/dic/dic_x8c48b6_g4_150k_CelebAHQ_20210611-5d3439ca.pth
 - Config: configs/dic/dic_gan-x8c48b6_4xb2-500k_celeba-hq.py
   In Collection: DIC
@@ -31,5 +31,5 @@ Models:
     Metrics:
       PSNR: 23.6241
       SSIM: 0.6721
-    Task: Dic
+    Task: Image Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/dic/dic_gan_x8c48b6_g4_500k_CelebAHQ_20210625-3b89a358.pth

configs/dim/metafile.yml

@@ -20,7 +20,7 @@ Models:
       GRAD: 32.7
       MSE: 0.017
       SAD: 53.8
-    Task: Dim
+    Task: Matting
   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_1xb1-1000k_comp1k.py
   In Collection: DIM
@@ -35,7 +35,7 @@ Models:
       GRAD: 29.4
       MSE: 0.016
       SAD: 52.3
-    Task: Dim
+    Task: Matting
   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_1xb1-1000k_comp1k.py
   In Collection: DIM
@@ -50,5 +50,5 @@ Models:
       GRAD: 29.0
       MSE: 0.015
       SAD: 50.6
-    Task: Dim
+    Task: Matting
   Weights: https://download.openmmlab.com/mmediting/mattors/dim/dim_stage3_v16_pln_1x1_1000k_comp1k_SAD-50.6_20200609_111851-647f24b6.pth

configs/edsr/metafile.yml

@@ -22,7 +22,7 @@ Models:
       Set14 SSIM: 0.8874
       Set5 PSNR: 35.7592
       Set5 SSIM: 0.9372
-    Task: Edsr
+    Task: Image Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/edsr/edsr_x2c64b16_1x16_300k_div2k_20200604-19fe95ea.pth
 - Config: configs/edsr/edsr_x3c64b16_1xb16-300k_div2k.py
   In Collection: EDSR
@@ -39,7 +39,7 @@ Models:
       Set14 SSIM: 0.8022
       Set5 PSNR: 32.3301
       Set5 SSIM: 0.8912
-    Task: Edsr
+    Task: Image Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/edsr/edsr_x3c64b16_1x16_300k_div2k_20200608-36d896f4.pth
 - Config: configs/edsr/edsr_x4c64b16_1xb16-300k_div2k.py
   In Collection: EDSR
@@ -56,5 +56,5 @@ Models:
       Set14 SSIM: 0.7366
       Set5 PSNR: 30.2223
       Set5 SSIM: 0.85
-    Task: Edsr
+    Task: Image Super-Resolution
   Weights: https://download.openmmlab.com/mmediting/restorers/edsr/edsr_x4c64b16_1x16_300k_div2k_20200608-3c2af8a3.pth