[Fix] Revise readme to support metafile generation

configs/biggan/README.md

@@ -14,6 +14,7 @@ year={2019},
 url={https://openreview.net/forum?id=B1xsqj09Fm},
 }
 ```
+</details>
 
 The `BigGAN/BigGAN-Deep` is a conditional generation model that can generate both high-resolution and high-quality images by scaling up the batch size and the number of model parameters.
 

configs/cyclegan/metafile.yml

@@ -6,4 +6,144 @@ Collections:
   Paper:
   - https://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Unpaired_Image-To-Image_Translation_ICCV_2017_paper.html
   README: configs/cyclegan/README.md
-Models: []
+Models:
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_resnet_in_1x1_80k_facades.py
+  In Collection: README
+  Metadata:
+    Training Data: FACADES
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_resnet_in_1x1_80k_facades
+  Results:
+  - Dataset: FACADES
+    Metrics:
+      Dataset: facades
+      FID: 124.8033
+      IS: 1.792
+      Models: Ours
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_80k_facades_20210902_165905-5e2c0876.pth?versionId=CAEQMhiBgICA5rCs3RciIDNmNDdjYzE1YTBiYjRiOTQ4NTI2ZjgwYzMxMDZmZWNk
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_id0_resnet_in_1x1_80k_facades.py
+  In Collection: README
+  Metadata:
+    Training Data: FACADES
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_id0_resnet_in_1x1_80k_facades
+  Results:
+  - Dataset: FACADES
+    Metrics:
+      Dataset: facades-id0
+      FID: 125.1694
+      IS: 1.905
+      Models: Ours
+    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?versionId=CAEQMhiBgMCZ3rCs3RciIDk0NWIwMmZjNzRhMjRkMTdiMjEyNTdhYTBkMmU4MmRi
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_resnet_in_1x1_250k_summer2winter.py
+  In Collection: README
+  Metadata:
+    Training Data: SUMMER2WINTER
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_resnet_in_1x1_250k_summer2winter
+  Results:
+  - Dataset: SUMMER2WINTER
+    Metrics:
+      Dataset: summer2winter
+      FID: 83.7177
+      IS: 2.771
+      Models: Ours
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_246200_summer2winter_convert-bgr_20210902_165932-fcf08dc1.pth?versionId=CAEQMhiBgIDT37Cs3RciIDNhYzQ3ZWU3MzZjNTQ1ZmJiZmMyZGZiMTc1NzUyZDM1
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_id0_resnet_in_1x1_250k_summer2winter.py
+  In Collection: README
+  Metadata:
+    Training Data: SUMMER2WINTER
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_id0_resnet_in_1x1_250k_summer2winter
+  Results:
+  - Dataset: SUMMER2WINTER
+    Metrics:
+      Dataset: summer2winter-id0
+      FID: 83.1418
+      IS: 2.72
+      Models: Ours
+    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?versionId=CAEQMhiBgICe3rCs3RciIGNiM2JmNjViNmQ5ZTRhMTQ4YWI0YjFkOTdmNTE3MzFi
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_resnet_in_1x1_250k_winter2summer.py
+  In Collection: README
+  Metadata:
+    Training Data: Others
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_resnet_in_1x1_250k_winter2summer
+  Results:
+  - Dataset: Others
+    Metrics:
+      Dataset: winter2summer
+      FID: 72.8025
+      IS: 3.129
+      Models: Ours
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_246200_summer2winter_convert-bgr_20210902_165932-fcf08dc1.pth?versionId=CAEQMhiBgIDT37Cs3RciIDNhYzQ3ZWU3MzZjNTQ1ZmJiZmMyZGZiMTc1NzUyZDM1
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_id0_resnet_in_1x1_250k_winter2summer.py
+  In Collection: README
+  Metadata:
+    Training Data: Others
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_id0_resnet_in_1x1_250k_winter2summer
+  Results:
+  - Dataset: Others
+    Metrics:
+      Dataset: winter2summer-id0
+      FID: 73.5001
+      IS: 3.107
+      Models: Ours
+    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?versionId=CAEQMhiBgICe3rCs3RciIGNiM2JmNjViNmQ5ZTRhMTQ4YWI0YjFkOTdmNTE3MzFi
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_resnet_in_1x1_270k_horse2zebra.py
+  In Collection: README
+  Metadata:
+    Training Data: HORSE2ZEBRA
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_resnet_in_1x1_270k_horse2zebra
+  Results:
+  - Dataset: HORSE2ZEBRA
+    Metrics:
+      Dataset: horse2zebra
+      FID: 64.5225
+      IS: 1.418
+      Models: Ours
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_266800_horse2zebra_convert-bgr_20210902_170004-a32c733a.pth?versionId=CAEQMhiBgMD327Cs3RciIDhkMjhhZDJkYjliYTQyM2M5MzU5ZDYxZGNhZGI5Njc4
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_id0_resnet_in_1x1_270k_horse2zebra.py
+  In Collection: README
+  Metadata:
+    Training Data: HORSE2ZEBRA
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_id0_resnet_in_1x1_270k_horse2zebra
+  Results:
+  - Dataset: HORSE2ZEBRA
+    Metrics:
+      Dataset: horse2zebra-id0
+      FID: 74.777
+      IS: 1.542
+      Models: Ours
+    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?versionId=CAEQMhiBgICF4rCs3RciIDA1YzcxZDI3ZmQwNjRhYTBiZjgzMGJmZWY3MmVhNDZj
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_resnet_in_1x1_270k_zebra2horse.py
+  In Collection: README
+  Metadata:
+    Training Data: Others
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_resnet_in_1x1_270k_zebra2horse
+  Results:
+  - Dataset: Others
+    Metrics:
+      Dataset: zebra2horse
+      FID: 141.1517
+      IS: 3.154
+      Models: Ours
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/cyclegan/refactor/cyclegan_lsgan_resnet_in_1x1_266800_horse2zebra_convert-bgr_20210902_170004-a32c733a.pth?versionId=CAEQMhiBgMD327Cs3RciIDhkMjhhZDJkYjliYTQyM2M5MzU5ZDYxZGNhZGI5Njc4
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/cyclegan/cyclegan_lsgan_id0_resnet_in_1x1_270k_zebra2horse.py
+  In Collection: README
+  Metadata:
+    Training Data: Others
+  Name: https:----github.com--open-mmlab--mmgeneration--tree--master--cyclegan--cyclegan_lsgan_id0_resnet_in_1x1_270k_zebra2horse
+  Results:
+  - Dataset: Others
+    Metrics:
+      Dataset: zebra2horse-id0
+      FID: 134.3728
+      IS: 3.091
+      Models: Ours
+    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?versionId=CAEQMhiBgICF4rCs3RciIDA1YzcxZDI3ZmQwNjRhYTBiZjgzMGJmZWY3MmVhNDZj

configs/dcgan/README.md

@@ -15,6 +15,7 @@
   url={https://arxiv.org/abs/1511.06434},
 }
 ```
+</details>
 
 ## Results and models
 

configs/ggan/README.md

@@ -15,6 +15,7 @@
   url={https://arxiv.org/abs/1705.02894},
 }
 ```
+</details>
 
 ## Results and models
 

configs/lsgan/README.md

@@ -16,6 +16,7 @@
   url={https://openaccess.thecvf.com/content_iccv_2017/html/Mao_Least_Squares_Generative_ICCV_2017_paper.html},
 }
 ```
+</details>
 
 ## Results and models
 

configs/pggan/README.md

@@ -19,7 +19,9 @@
   <br/>
   <img src="https://user-images.githubusercontent.com/12726765/114009864-1df45400-9896-11eb-9d25-da9eabfe02ce.png" width="800"/>
 </div>
+</details>
 
+## Results and models
 
 |     Models      |    Details     | MS-SSIM |     SWD(xx,xx,xx,xx/avg)     |                                                        Config                                                         |                                                    Download                                                    |
 | :-------------: | :------------: | :-----: | :--------------------------: | :-------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------: |

configs/pix2pix/README.md

@@ -17,6 +17,7 @@
   url={https://openaccess.thecvf.com/content_cvpr_2017/html/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.html},
 }
 ```
+</details>
 
 ## Results and Models
 <div align="center">
@@ -26,25 +27,27 @@
 </div>
 We use `FID` and `IS` metrics to evaluate the generation performance of pix2pix.<sup>1</sup>
 
-`FID` evaluation:
+| Models |   Dataset   |   FID    |  IS   |                                                                     Config                                                                      |                                                                                                                     Download                                                                                                                     |
+| :----: | :---------: | :------: | :---: | :---------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
+|  Ours  |   facades   | 124.9773 | 1.620 |           [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_1x1_80k_facades.py)           |                [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_1x1_80k_facades_20210902_170442-c0958d50.pth?versionId=CAEQMhiBgICb8fTj3RciIGU2NmViM2QyYzJkODQ0MDBhYTFhMGE2YzNmMTA0ODk3)   \| [log](https://download.openmmlab.com/mmgen/pix2pix/pix2pix_vanilla_unet_bn_1x1_80k_facades_20210317_172625.log.json)<sup>2</sup>
+|  Ours  | aerial2maps | 122.5856 | 3.137 |        [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_1x1_220k_aerial2maps.py)         |          [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_a2b_1x1_219200_maps_convert-bgr_20210902_170729-59a31517.pth?versionId=CAEQMhiBgICH9vTj3RciIDdiNGRmYTNlZjhlMjQ0ODc4OTJiOGEzMjY0YTJlZmQ5)          |
+|  Ours  | maps2aerial | 88.4635  | 3.310 |        [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_1x1_220k_maps2aerial.py)         |          [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_b2a_1x1_219200_maps_convert-bgr_20210902_170814-6d2eac4a.pth?versionId=CAEQMhiBgMC08PTj3RciIGE4ODVkZWU0MTYyMTQ0MWJhZjE0YThmY2M2NDJmZjNi)          |
+|  Ours  | edges2shoes | 84.3750  | 2.815 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_190k_edges2shoes.py) | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_186840_edges2shoes_convert-bgr_20210902_170902-0c828552.pth?versionId=CAEQMhiBgIC57vTj3RciIGZlNmQ4ZDJhN2E1MDQ5ZmJiOWJmYTY5MDg1ZTc0N2Vi) |
 
-| Dataset  | [facades](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_1x1_80k_facades.py) | [aerial2maps](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_1x1_220k_aerial2maps.py) | [maps2aerial](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_1x1_220k_maps2aerial.py) | [edges2shoes](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_190k_edges2shoes.py) |   average    |
-| :------: | :--------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------: | :----------: |
-| official |                                                         **119.135**                                                          |                                                              149.731                                                              |                                                              102.072                                                              |                                                                       **75.774**                                                                       |   111.678    |
-|       ours       | 124.9773 |    **122.5856** |      **88.4635**  |         84.3750   |     **105.1003**  |
 
-`IS` evaluation:
+`FID` comparison with official:
 
-| Dataset  |  facades  | aerial2maps  | maps2aerial  | edges2shoes |  average  |
-| :------: | :-------: | :-------: | :-------: | :---------: | :-------: |
-| official |   **1.650**   |   2.529   |   **3.552**   |    2.766    |   2.624   |
-|   ours   | 1.620 | **3.137** | 3.310 |  **2.815**  | **2.7205** |
+| Dataset  |   facades   | aerial2maps  | maps2aerial | edges2shoes |   average    |
+| :------: | :---------: | :----------: | :---------: | :---------: | :----------: |
+| official | **119.135** |   149.731    |   102.072   | **75.774**  |   111.678    |
+|   ours   |  124.9773   | **122.5856** | **88.4635** |   84.3750   | **105.1003** |
 
-Model and log downloads:
+`IS` comparison with official:
 
-| Dataset  |                                                                                                                        facades                                                                                                                        |                                                                  aerial2maps                                                                  |                                                                  maps2aerial                                                                |                                                                         edges2shoes                                                                          |
-| :------: | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------------: |
-| download | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_1x1_80k_facades_20210902_170442-c0958d50.pth?versionId=CAEQMhiBgICb8fTj3RciIGU2NmViM2QyYzJkODQ0MDBhYTFhMGE2YzNmMTA0ODk3) \| [log](https://download.openmmlab.com/mmgen/pix2pix/pix2pix_vanilla_unet_bn_1x1_80k_facades_20210317_172625.log.json)<sup>2</sup> | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_a2b_1x1_219200_maps_convert-bgr_20210902_170729-59a31517.pth?versionId=CAEQMhiBgICH9vTj3RciIDdiNGRmYTNlZjhlMjQ0ODc4OTJiOGEzMjY0YTJlZmQ5) | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_b2a_1x1_219200_maps_convert-bgr_20210902_170814-6d2eac4a.pth?versionId=CAEQMhiBgMC08PTj3RciIGE4ODVkZWU0MTYyMTQ0MWJhZjE0YThmY2M2NDJmZjNi) | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_186840_edges2shoes_convert-bgr_20210902_170902-0c828552.pth?versionId=CAEQMhiBgIC57vTj3RciIGZlNmQ4ZDJhN2E1MDQ5ZmJiOWJmYTY5MDg1ZTc0N2Vi) |
+| Dataset  |  facades  | aerial2maps | maps2aerial | edges2shoes |  average   |
+| :------: | :-------: | :---------: | :---------: | :---------: | :--------: |
+| official | **1.650** |    2.529    |  **3.552**  |    2.766    |   2.624    |
+|   ours   |   1.620   |  **3.137**  |    3.310    |  **2.815**  | **2.7205** |
 
 Note:
 1. we strictly follow the [paper](http://openaccess.thecvf.com/content_cvpr_2017/papers/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.pdf) setting in Section 3.3: "*At inference time, we run the generator net in exactly