add part mmgeneration code

57e0e891 · limm · 04e07f48 · 57e0e891 · 57e0e891 · 57e0e891
Commit 57e0e891 authored Jun 16, 2025 by limm
20 changed files
--- a/configs/lsgan/lsgan_dcgan-archi_lr-1e-4_lsun-bedroom_64_b128x1_12m.py
+++ b/configs/lsgan/lsgan_dcgan-archi_lr-1e-4_lsun-bedroom_64_b128x1_12m.py
+_base_ = [
+    '../_base_/models/dcgan/dcgan_64x64.py',
+    '../_base_/datasets/unconditional_imgs_64x64.py',
+    '../_base_/default_runtime.py'
+]
+model = dict(
+    discriminator=dict(output_scale=4, out_channels=1),
+    gan_loss=dict(type='GANLoss', gan_type='lsgan'))
+# define dataset
+# you must set `samples_per_gpu` and `imgs_root`
+data = dict(
+    samples_per_gpu=128, train=dict(imgs_root='./data/lsun/bedroom_train'))
+optimizer = dict(
+    generator=dict(type='Adam', lr=0.0001, betas=(0.5, 0.99)),
+    discriminator=dict(type='Adam', lr=0.0001, betas=(0.5, 0.99)))
+# adjust running config
+lr_config = None
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=20)
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=10000)
+]
+evaluation = dict(
+    type='GenerativeEvalHook',
+    interval=10000,
+    metrics=dict(
+        type='FID', num_images=50000, inception_pkl=None, bgr2rgb=True),
+    sample_kwargs=dict(sample_model='orig'))
+total_iters = 100000
+# use ddp wrapper for faster training
+use_ddp_wrapper = True
+find_unused_parameters = False
+runner = dict(
+    type='DynamicIterBasedRunner',
+    is_dynamic_ddp=False,  # Note that this flag should be False.
+    pass_training_status=True)
+metrics = dict(
+    ms_ssim10k=dict(type='MS_SSIM', num_images=10000),
+    swd16k=dict(type='SWD', num_images=16384, image_shape=(3, 64, 64)),
+    fid50k=dict(type='FID', num_images=50000, inception_pkl=None))
--- a/configs/lsgan/lsgan_lsgan-archi_lr-1e-4_lsun-bedroom_128_b64x1_10m.py
+++ b/configs/lsgan/lsgan_lsgan-archi_lr-1e-4_lsun-bedroom_128_b64x1_10m.py
+_base_ = [
+    '../_base_/models/lsgan/lsgan_128x128.py',
+    '../_base_/datasets/unconditional_imgs_128x128.py',
+    '../_base_/default_runtime.py'
+]
+# define dataset
+# you must set `samples_per_gpu` and `imgs_root`
+data = dict(
+    samples_per_gpu=64, train=dict(imgs_root='./data/lsun/bedroom_train'))
+optimizer = dict(
+    generator=dict(type='Adam', lr=0.0001, betas=(0.5, 0.99)),
+    discriminator=dict(type='Adam', lr=0.0001, betas=(0.5, 0.99)))
+# adjust running config
+lr_config = None
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=20)
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=10000)
+]
+evaluation = dict(
+    type='GenerativeEvalHook',
+    interval=10000,
+    metrics=dict(
+        type='FID', num_images=50000, inception_pkl=None, bgr2rgb=True),
+    sample_kwargs=dict(sample_model='orig'))
+total_iters = 160000
+# use ddp wrapper for faster training
+use_ddp_wrapper = True
+find_unused_parameters = False
+runner = dict(
+    type='DynamicIterBasedRunner',
+    is_dynamic_ddp=False,  # Note that this flag should be False.
+    pass_training_status=True)
+metrics = dict(
+    ms_ssim10k=dict(type='MS_SSIM', num_images=10000),
+    swd16k=dict(type='SWD', num_images=16384, image_shape=(3, 128, 128)),
+    fid50k=dict(type='FID', num_images=50000, inception_pkl=None))
--- a/configs/lsgan/metafile.yml
+++ b/configs/lsgan/metafile.yml
+Collections:
+- Metadata:
+    Architecture:
+    - LSGAN
+  Name: LSGAN
+  Paper:
+  - https://openaccess.thecvf.com/content_iccv_2017/html/Mao_Least_Squares_Generative_ICCV_2017_paper.html
+  README: configs/lsgan/README.md
+Models:
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/lsgan/lsgan_dcgan-archi_lr-1e-3_celeba-cropped_64_b128x1_12m.py
+  In Collection: LSGAN
+  Metadata:
+    Training Data: CELEBA
+  Name: lsgan_dcgan-archi_lr-1e-3_celeba-cropped_64_b128x1_12m
+  Results:
+  - Dataset: CELEBA
+    Metrics:
+      FID: 11.9258
+      MS-SSIM: 0.3216
+      SWD: 6.16, 6.83, 37.64/16.87
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/lsgan/lsgan_celeba-cropped_dcgan-archi_lr-1e-3_64_b128x1_12m_20210429_144001-92ca1d0d.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/lsgan/lsgan_dcgan-archi_lr-1e-4_lsun-bedroom_64_b128x1_12m.py
+  In Collection: LSGAN
+  Metadata:
+    Training Data: LSUN
+  Name: lsgan_dcgan-archi_lr-1e-4_lsun-bedroom_64_b128x1_12m
+  Results:
+  - Dataset: LSUN
+    Metrics:
+      FID: 30.739
+      MS-SSIM: 0.0671
+      SWD: 5.66, 9.0, 18.6/11.09
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/lsgan/lsgan_lsun-bedroom_dcgan-archi_lr-1e-4_64_b128x1_12m_20210429_144602-ec4ec6bb.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/lsgan/lsgan_dcgan-archi_lr-1e-4_celeba-cropped_128_b64x1_10m.py
+  In Collection: LSGAN
+  Metadata:
+    Training Data: CELEBA
+  Name: lsgan_dcgan-archi_lr-1e-4_celeba-cropped_128_b64x1_10m
+  Results:
+  - Dataset: CELEBA
+    Metrics:
+      FID: 38.3752
+      MS-SSIM: 0.3691
+      SWD: 21.66, 9.83, 16.06, 70.76/29.58
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/lsgan/lsgan_celeba-cropped_dcgan-archi_lr-1e-4_128_b64x1_10m_20210429_144229-01ba67dc.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/lsgan/lsgan_lsgan-archi_lr-1e-4_lsun-bedroom_128_b64x1_10m.py
+  In Collection: LSGAN
+  Metadata:
+    Training Data: LSUN
+  Name: lsgan_lsgan-archi_lr-1e-4_lsun-bedroom_128_b64x1_10m
+  Results:
+  - Dataset: LSUN
+    Metrics:
+      FID: 51.55
+      MS-SSIM: 0.0612
+      SWD: 19.52, 9.99, 7.48, 14.3/12.82
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/lsgan/lsgan_lsun-bedroom_lsgan-archi_lr-1e-4_128_b64x1_10m_20210429_155605-cf78c0a8.pth
--- a/configs/pggan/README.md
+++ b/configs/pggan/README.md
+# PGGAN
+> [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://arxiv.org/abs/1710.10196)
+<!-- [ALGORITHM] -->
+## Abstract
+<!-- [ABSTRACT] -->
+We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses. This both speeds the training up and greatly stabilizes it, allowing us to produce images of unprecedented quality, e.g., CelebA images at 1024^2. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation. As an additional contribution, we construct a higher-quality version of the CelebA dataset.
+<!-- [IMAGE] -->
+<div align=center>
+<img src="https://user-images.githubusercontent.com/28132635/143053374-c03894c3-6def-49c2-94ed-80c4accee726.JPG" />
+</div>
+## Results and models
+<div align="center">
+  <b> Results (compressed) from our PGGAN trained in CelebA-HQ@1024</b>
+  <br/>
+  <img src="https://user-images.githubusercontent.com/12726765/114009864-1df45400-9896-11eb-9d25-da9eabfe02ce.png" width="800"/>
+</div>
+|     Models      |    Details     | MS-SSIM |     SWD(xx,xx,xx,xx/avg)     |                               Config                                |                               Download                                |
+| :-------------: | :------------: | :-----: | :--------------------------: | :-----------------------------------------------------------------: | :-------------------------------------------------------------------: |
+|  pggan_128x128  | celeba-cropped | 0.3023  | 3.42, 4.04, 4.78, 20.38/8.15 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pggan/pggan_celeba-cropped_128_g8_12Mimgs.py) | [model](https://download.openmmlab.com/mmgen/pggan/pggan_celeba-cropped_128_g8_20210408_181931-85a2e72c.pth) |
+|  pggan_128x128  |  lsun-bedroom  | 0.0602  |  3.5, 2.96, 2.76, 9.65/4.72  | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pggan/pggan_lsun-bedroom_128_g8_12Mimgs.py) | [model](https://download.openmmlab.com/mmgen/pggan/pggan_lsun-bedroom_128x128_g8_20210408_182033-5e59f45d.pth) |
+| pggan_1024x1024 |   celeba-hq    | 0.3379  | 8.93, 3.98, 3.07, 2.64/4.655 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pggan/pggan_celeba-hq_1024_g8_12Mimg.py) | [model](https://download.openmmlab.com/mmgen/pggan/pggan_celeba-hq_1024_g8_20210408_181911-f1ef51c3.pth) |
+## Citation
+<summary align="right"><a href="https://arxiv.org/abs/1710.10196">PGGAN (arXiv'2017)</a></summary>
+```latex
+@article{karras2017progressive,
+  title={Progressive growing of gans for improved quality, stability, and variation},
+  author={Karras, Tero and Aila, Timo and Laine, Samuli and Lehtinen, Jaakko},
+  journal={arXiv preprint arXiv:1710.10196},
+  year={2017},
+  url={https://arxiv.org/abs/1710.10196},
+}
+```
--- a/configs/pggan/metafile.yml
+++ b/configs/pggan/metafile.yml
+Collections:
+- Metadata:
+    Architecture:
+    - PGGAN
+  Name: PGGAN
+  Paper:
+  - https://arxiv.org/abs/1710.10196
+  README: configs/pggan/README.md
+Models:
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pggan/pggan_celeba-cropped_128_g8_12Mimgs.py
+  In Collection: PGGAN
+  Metadata:
+    Training Data: CELEBA
+  Name: pggan_celeba-cropped_128_g8_12Mimgs
+  Results:
+  - Dataset: CELEBA
+    Metrics:
+      Details: celeba-cropped
+      MS-SSIM: 0.3023
+      SWD(xx,xx,xx,xx/avg): 3.42, 4.04, 4.78, 20.38/8.15
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pggan/pggan_celeba-cropped_128_g8_20210408_181931-85a2e72c.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pggan/pggan_lsun-bedroom_128_g8_12Mimgs.py
+  In Collection: PGGAN
+  Metadata:
+    Training Data: LSUN
+  Name: pggan_lsun-bedroom_128_g8_12Mimgs
+  Results:
+  - Dataset: LSUN
+    Metrics:
+      Details: lsun-bedroom
+      MS-SSIM: 0.0602
+      SWD(xx,xx,xx,xx/avg): 3.5, 2.96, 2.76, 9.65/4.72
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pggan/pggan_lsun-bedroom_128x128_g8_20210408_182033-5e59f45d.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pggan/pggan_celeba-hq_1024_g8_12Mimg.py
+  In Collection: PGGAN
+  Metadata:
+    Training Data: CELEBA
+  Name: pggan_celeba-hq_1024_g8_12Mimg
+  Results:
+  - Dataset: CELEBA
+    Metrics:
+      Details: celeba-hq
+      MS-SSIM: 0.3379
+      SWD(xx,xx,xx,xx/avg): 8.93, 3.98, 3.07, 2.64/4.655
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pggan/pggan_celeba-hq_1024_g8_20210408_181911-f1ef51c3.pth
--- a/configs/pggan/pggan_celeba-cropped_128_g8_12Mimgs.py
+++ b/configs/pggan/pggan_celeba-cropped_128_g8_12Mimgs.py
+_base_ = [
+    '../_base_/models/pggan/pggan_128x128.py',
+    '../_base_/datasets/grow_scale_imgs_128x128.py',
+    '../_base_/default_runtime.py'
+]
+optimizer = None
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=20)
+data = dict(
+    samples_per_gpu=64,
+    train=dict(
+        imgs_roots={'128': './data/celeba-cropped/cropped_images_aligned_png'},
+        gpu_samples_base=4,
+        # note that this should be changed with total gpu number
+        gpu_samples_per_scale={
+            '4': 64,
+            '8': 32,
+            '16': 16,
+            '32': 8,
+            '64': 4
+        }))
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(type='PGGANFetchDataHook', interval=1),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        priority='VERY_HIGH')
+]
+lr_config = None
+total_iters = 280000
+metrics = dict(
+    ms_ssim10k=dict(type='MS_SSIM', num_images=10000),
+    swd16k=dict(type='SWD', num_images=16384, image_shape=(3, 128, 128)))
--- a/configs/pggan/pggan_celeba-hq_1024_g8_12Mimg.py
+++ b/configs/pggan/pggan_celeba-hq_1024_g8_12Mimg.py
+_base_ = [
+    '../_base_/models/pggan/pggan_1024.py',
+    '../_base_/datasets/grow_scale_imgs_celeba-hq.py',
+    '../_base_/default_runtime.py'
+]
+optimizer = None
+checkpoint_config = dict(interval=5000, by_epoch=False, max_keep_ckpts=20)
+data = dict(
+    samples_per_gpu=64,
+    train=dict(
+        gpu_samples_base=4,
+        # note that this should be changed with total gpu number
+        gpu_samples_per_scale={
+            '4': 64,
+            '8': 32,
+            '16': 16,
+            '32': 8,
+            '64': 4
+        },
+    ))
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(type='PGGANFetchDataHook', interval=1),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        priority='VERY_HIGH')
+]
+lr_config = None
+total_iters = 280000
+metrics = dict(
+    ms_ssim10k=dict(type='MS_SSIM', num_images=10000),
+    swd16k=dict(type='SWD', num_images=16384, image_shape=(3, 1024, 1024)))
--- a/configs/pggan/pggan_lsun-bedroom_128_g8_12Mimgs.py
+++ b/configs/pggan/pggan_lsun-bedroom_128_g8_12Mimgs.py
+_base_ = [
+    '../_base_/models/pggan/pggan_128x128.py',
+    '../_base_/datasets/grow_scale_imgs_128x128.py',
+    '../_base_/default_runtime.py'
+]
+optimizer = None
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=20)
+data = dict(
+    samples_per_gpu=64,
+    train=dict(
+        imgs_roots={'128': './data/lsun/bedroom_train'},
+        gpu_samples_base=4,
+        # note that this should be changed with total gpu number
+        gpu_samples_per_scale={
+            '4': 64,
+            '8': 32,
+            '16': 16,
+            '32': 8,
+            '64': 4
+        },
+    ))
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(type='PGGANFetchDataHook', interval=1),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        priority='VERY_HIGH')
+]
+lr_config = None
+total_iters = 280000
+metrics = dict(
+    ms_ssim10k=dict(type='MS_SSIM', num_images=10000),
+    swd16k=dict(type='SWD', num_images=16384, image_shape=(3, 128, 128)))
--- a/configs/pix2pix/README.md
+++ b/configs/pix2pix/README.md
+# Pix2Pix
+> [Pix2Pix: Image-to-Image Translation with Conditional Adversarial Networks](https://openaccess.thecvf.com/content_cvpr_2017/html/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.html)
+<!-- [ALGORITHM] -->
+## Abstract
+<!-- [ABSTRACT] -->
+We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. We demonstrate that this approach is effective at synthesizing photos from label maps, reconstructing objects from edge maps, and colorizing images, among other tasks. Moreover, since the release of the pix2pix software associated with this paper, hundreds of twitter users have posted their own artistic experiments using our system. As a community, we no longer hand-engineer our mapping functions, and this work suggests we can achieve reasonable results without handengineering our loss functions either.
+<!-- [IMAGE] -->
+<div align=center>
+<img src="https://user-images.githubusercontent.com/28132635/143053385-1b03356d-43df-423b-88b2-7a82b73d2edd.JPG"/>
+</div>
+## Results and Models
+<div align="center">
+  <b> Results from Pix2Pix trained by MMGeneration</b>
+  <br/>
+  <img src="https://user-images.githubusercontent.com/22982797/114269080-4ff0ec00-9a37-11eb-92c4-1525864e0307.PNG" width="800"/>
+</div>
+We use `FID` and `IS` metrics to evaluate the generation performance of pix2pix.<sup>1</sup>
+| 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_facades_b1x1_80k.py) | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_1x1_80k_facades_20210902_170442-c0958d50.pth)   \| [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_aerial2maps_b1x1_220k.py) | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_a2b_1x1_219200_maps_convert-bgr_20210902_170729-59a31517.pth) |
+|  Ours  | maps2aerial | 88.4635  | 3.310 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_maps2aerial_b1x1_220k.py) | [model](https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_b2a_1x1_219200_maps_convert-bgr_20210902_170814-6d2eac4a.pth) |
+|  Ours  | edges2shoes | 84.3750  | 2.815 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_edges2shoes_b1x4_190k.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) |
+`FID` comparison with official:
+| 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** |
+`IS` 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** |
+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
+   the same manner as during the training phase. This differs
+   from the usual protocol in that we apply dropout at test time,
+   and we apply batch normalization using the statistics of
+   the test batch, rather than aggregated statistics of the training batch.*" (i.e., use model.train() mode), thus may lead to slightly different inference results every time.
+2. This is the training log before refactoring. Updated logs will be released soon.
+## Citation
+```latex
+@inproceedings{isola2017image,
+  title={Image-to-image translation with conditional adversarial networks},
+  author={Isola, Phillip and Zhu, Jun-Yan and Zhou, Tinghui and Efros, Alexei A},
+  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
+  pages={1125--1134},
+  year={2017},
+  url={https://openaccess.thecvf.com/content_cvpr_2017/html/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.html},
+}
+```
--- a/configs/pix2pix/metafile.yml
+++ b/configs/pix2pix/metafile.yml
+Collections:
+- Metadata:
+    Architecture:
+    - Pix2Pix
+  Name: Pix2Pix
+  Paper:
+  - https://openaccess.thecvf.com/content_cvpr_2017/html/Isola_Image-To-Image_Translation_With_CVPR_2017_paper.html
+  README: configs/pix2pix/README.md
+Models:
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_facades_b1x1_80k.py
+  In Collection: Pix2Pix
+  Metadata:
+    Training Data: FACADES
+  Name: pix2pix_vanilla_unet_bn_facades_b1x1_80k
+  Results:
+  - Dataset: FACADES
+    Metrics:
+      FID: 124.9773
+      IS: 1.62
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_1x1_80k_facades_20210902_170442-c0958d50.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_aerial2maps_b1x1_220k.py
+  In Collection: Pix2Pix
+  Metadata:
+    Training Data: MAPS
+  Name: pix2pix_vanilla_unet_bn_aerial2maps_b1x1_220k
+  Results:
+  - Dataset: MAPS
+    Metrics:
+      FID: 122.5856
+      IS: 3.137
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_a2b_1x1_219200_maps_convert-bgr_20210902_170729-59a31517.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_maps2aerial_b1x1_220k.py
+  In Collection: Pix2Pix
+  Metadata:
+    Training Data: MAPS
+  Name: pix2pix_vanilla_unet_bn_maps2aerial_b1x1_220k
+  Results:
+  - Dataset: MAPS
+    Metrics:
+      FID: 88.4635
+      IS: 3.31
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_b2a_1x1_219200_maps_convert-bgr_20210902_170814-6d2eac4a.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_edges2shoes_b1x4_190k.py
+  In Collection: Pix2Pix
+  Metadata:
+    Training Data: EDGES2SHOES
+  Name: pix2pix_vanilla_unet_bn_wo_jitter_flip_edges2shoes_b1x4_190k
+  Results:
+  - Dataset: EDGES2SHOES
+    Metrics:
+      FID: 84.375
+      IS: 2.815
+    Task: Image2Image Translation
+  Weights: https://download.openmmlab.com/mmgen/pix2pix/refactor/pix2pix_vanilla_unet_bn_wo_jitter_flip_1x4_186840_edges2shoes_convert-bgr_20210902_170902-0c828552.pth
--- a/configs/pix2pix/pix2pix_vanilla_unet_bn_aerial2maps_b1x1_220k.py
+++ b/configs/pix2pix/pix2pix_vanilla_unet_bn_aerial2maps_b1x1_220k.py
+_base_ = [
+    '../_base_/models/pix2pix/pix2pix_vanilla_unet_bn.py',
+    '../_base_/datasets/paired_imgs_256x256_crop.py',
+    '../_base_/default_runtime.py'
+]
+source_domain = 'aerial'
+target_domain = 'map'
+# model settings
+model = dict(
+    default_domain=target_domain,
+    reachable_domains=[target_domain],
+    related_domains=[target_domain, source_domain],
+    gen_auxiliary_loss=dict(
+        data_info=dict(
+            pred=f'fake_{target_domain}', target=f'real_{target_domain}')))
+# dataset settings
+domain_a = source_domain
+domain_b = target_domain
+img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+train_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(286, 286),
+        interpolation='bicubic'),
+    dict(
+        type='FixedCrop',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        crop_size=(256, 256)),
+    dict(
+        type='Flip',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        direction='horizontal'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(256, 256),
+        interpolation='bicubic'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+dataroot = 'data/paired/maps'
+data = dict(
+    train=dict(dataroot=dataroot, pipeline=train_pipeline),
+    val=dict(dataroot=dataroot, pipeline=test_pipeline, testdir='val'),
+    test=dict(dataroot=dataroot, pipeline=test_pipeline, testdir='val'))
+# optimizer
+optimizer = dict(
+    generators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)),
+    discriminators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)))
+# learning policy
+lr_config = None
+# checkpoint saving
+checkpoint_config = dict(interval=10000, save_optimizer=True, by_epoch=False)
+custom_hooks = [
+    dict(
+        type='MMGenVisualizationHook',
+        output_dir='training_samples',
+        res_name_list=[f'fake_{target_domain}'],
+        interval=5000)
+]
+runner = None
+use_ddp_wrapper = True
+# runtime settings
+total_iters = 220000
+workflow = [('train', 1)]
+exp_name = 'pix2pix_aerial2map'
+work_dir = f'./work_dirs/experiments/{exp_name}'
+num_images = 1098
+metrics = dict(
+    FID=dict(type='FID', num_images=num_images, image_shape=(3, 256, 256)),
+    IS=dict(
+        type='IS',
+        num_images=num_images,
+        image_shape=(3, 256, 256),
+        inception_args=dict(type='pytorch')))
+evaluation = dict(
+    type='TranslationEvalHook',
+    target_domain=domain_b,
+    interval=10000,
+    metrics=[
+        dict(type='FID', num_images=num_images, bgr2rgb=True),
+        dict(
+            type='IS',
+            num_images=num_images,
+            inception_args=dict(type='pytorch'))
+    ],
+    best_metric=['fid', 'is'])
--- a/configs/pix2pix/pix2pix_vanilla_unet_bn_facades_b1x1_80k.py
+++ b/configs/pix2pix/pix2pix_vanilla_unet_bn_facades_b1x1_80k.py
+_base_ = [
+    '../_base_/models/pix2pix/pix2pix_vanilla_unet_bn.py',
+    '../_base_/datasets/paired_imgs_256x256_crop.py',
+    '../_base_/default_runtime.py'
+]
+source_domain = 'mask'
+target_domain = 'photo'
+# model settings
+model = dict(
+    default_domain=target_domain,
+    reachable_domains=[target_domain],
+    related_domains=[target_domain, source_domain],
+    gen_auxiliary_loss=dict(
+        data_info=dict(
+            pred=f'fake_{target_domain}', target=f'real_{target_domain}')))
+# dataset settings
+domain_a = target_domain
+domain_b = source_domain
+img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+train_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(286, 286),
+        interpolation='bicubic'),
+    dict(
+        type='FixedCrop',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        crop_size=(256, 256)),
+    dict(
+        type='Flip',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        direction='horizontal'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(256, 256),
+        interpolation='bicubic'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+dataroot = 'data/paired/facades'
+data = dict(
+    train=dict(dataroot=dataroot, pipeline=train_pipeline),
+    val=dict(dataroot=dataroot, pipeline=test_pipeline),
+    test=dict(dataroot=dataroot, pipeline=test_pipeline))
+# optimizer
+optimizer = dict(
+    generators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)),
+    discriminators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)))
+# learning policy
+lr_config = None
+# checkpoint saving
+checkpoint_config = dict(interval=10000, save_optimizer=True, by_epoch=False)
+custom_hooks = [
+    dict(
+        type='MMGenVisualizationHook',
+        output_dir='training_samples',
+        res_name_list=[f'fake_{target_domain}'],
+        interval=5000)
+]
+runner = None
+use_ddp_wrapper = True
+# runtime settings
+total_iters = 80000
+workflow = [('train', 1)]
+exp_name = 'pix2pix_facades'
+work_dir = f'./work_dirs/experiments/{exp_name}'
+num_images = 106
+metrics = dict(
+    FID=dict(type='FID', num_images=num_images, image_shape=(3, 256, 256)),
+    IS=dict(
+        type='IS',
+        num_images=num_images,
+        image_shape=(3, 256, 256),
+        inception_args=dict(type='pytorch')))
+evaluation = dict(
+    type='TranslationEvalHook',
+    target_domain=domain_b,
+    interval=10000,
+    metrics=[
+        dict(type='FID', num_images=num_images, bgr2rgb=True),
+        dict(
+            type='IS',
+            num_images=num_images,
+            inception_args=dict(type='pytorch'))
+    ],
+    best_metric=['fid', 'is'])
--- a/configs/pix2pix/pix2pix_vanilla_unet_bn_maps2aerial_b1x1_220k.py
+++ b/configs/pix2pix/pix2pix_vanilla_unet_bn_maps2aerial_b1x1_220k.py
+_base_ = [
+    '../_base_/models/pix2pix/pix2pix_vanilla_unet_bn.py',
+    '../_base_/datasets/paired_imgs_256x256_crop.py',
+    '../_base_/default_runtime.py'
+]
+source_domain = 'map'
+target_domain = 'aerial'
+# model settings
+model = dict(
+    default_domain=target_domain,
+    reachable_domains=[target_domain],
+    related_domains=[target_domain, source_domain],
+    gen_auxiliary_loss=dict(
+        data_info=dict(
+            pred=f'fake_{target_domain}', target=f'real_{target_domain}')))
+# dataset settings
+domain_a = target_domain
+domain_b = source_domain
+img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+train_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(286, 286),
+        interpolation='bicubic'),
+    dict(
+        type='FixedCrop',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        crop_size=(256, 256)),
+    dict(
+        type='Flip',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        direction='horizontal'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(256, 256),
+        interpolation='bicubic'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+dataroot = 'data/paired/maps'
+data = dict(
+    train=dict(dataroot=dataroot, pipeline=train_pipeline),
+    val=dict(dataroot=dataroot, pipeline=test_pipeline, testdir='val'),
+    test=dict(dataroot=dataroot, pipeline=test_pipeline, testdir='val'))
+# optimizer
+optimizer = dict(
+    generators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)),
+    discriminators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)))
+# learning policy
+lr_config = None
+# checkpoint saving
+checkpoint_config = dict(interval=10000, save_optimizer=True, by_epoch=False)
+custom_hooks = [
+    dict(
+        type='MMGenVisualizationHook',
+        output_dir='training_samples',
+        res_name_list=[f'fake_{target_domain}'],
+        interval=5000)
+]
+runner = None
+use_ddp_wrapper = True
+# runtime settings
+total_iters = 220000
+workflow = [('train', 1)]
+exp_name = 'pix2pix_maps2aerial'
+work_dir = f'./work_dirs/experiments/{exp_name}'
+num_images = 1098
+metrics = dict(
+    FID=dict(type='FID', num_images=num_images, image_shape=(3, 256, 256)),
+    IS=dict(
+        type='IS',
+        num_images=num_images,
+        image_shape=(3, 256, 256),
+        inception_args=dict(type='pytorch')))
+evaluation = dict(
+    type='TranslationEvalHook',
+    target_domain=domain_b,
+    interval=10000,
+    metrics=[
+        dict(type='FID', num_images=num_images, bgr2rgb=True),
+        dict(
+            type='IS',
+            num_images=num_images,
+            inception_args=dict(type='pytorch'))
+    ],
+    best_metric=['fid', 'is'])
--- a/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_edges2shoes_b1x4_190k.py
+++ b/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_edges2shoes_b1x4_190k.py
+_base_ = [
+    '../_base_/models/pix2pix/pix2pix_vanilla_unet_bn.py',
+    '../_base_/datasets/paired_imgs_256x256.py', '../_base_/default_runtime.py'
+]
+source_domain = 'edges'
+target_domain = 'photo'
+# model settings
+model = dict(
+    default_domain=target_domain,
+    reachable_domains=[target_domain],
+    related_domains=[target_domain, source_domain],
+    gen_auxiliary_loss=dict(
+        data_info=dict(
+            pred=f'fake_{target_domain}', target=f'real_{target_domain}')))
+# dataset settings
+domain_a = source_domain
+domain_b = target_domain
+img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
+train_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(286, 286),
+        interpolation='bicubic'),
+    dict(
+        type='FixedCrop',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        crop_size=(256, 256)),
+    dict(
+        type='Flip',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        direction='horizontal'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+test_pipeline = [
+    dict(
+        type='LoadPairedImageFromFile',
+        io_backend='disk',
+        key='pair',
+        domain_a=domain_a,
+        domain_b=domain_b,
+        flag='color'),
+    dict(
+        type='Resize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        scale=(256, 256),
+        interpolation='bicubic'),
+    dict(type='RescaleToZeroOne', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Normalize',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        to_rgb=False,
+        **img_norm_cfg),
+    dict(type='ImageToTensor', keys=[f'img_{domain_a}', f'img_{domain_b}']),
+    dict(
+        type='Collect',
+        keys=[f'img_{domain_a}', f'img_{domain_b}'],
+        meta_keys=[f'img_{domain_a}_path', f'img_{domain_b}_path'])
+]
+dataroot = 'data/paired/edges2shoes'
+data = dict(
+    train=dict(dataroot=dataroot, pipeline=train_pipeline),
+    val=dict(dataroot=dataroot, pipeline=test_pipeline, testdir='val'),
+    test=dict(dataroot=dataroot, pipeline=test_pipeline, testdir='val'))
+# optimizer
+optimizer = dict(
+    generators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)),
+    discriminators=dict(type='Adam', lr=2e-4, betas=(0.5, 0.999)))
+# learning policy
+lr_config = None
+# checkpoint saving
+checkpoint_config = dict(interval=10000, save_optimizer=True, by_epoch=False)
+custom_hooks = [
+    dict(
+        type='MMGenVisualizationHook',
+        output_dir='training_samples',
+        res_name_list=[f'fake_{target_domain}'],
+        interval=5000)
+]
+runner = None
+use_ddp_wrapper = True
+# runtime settings
+total_iters = 190000
+workflow = [('train', 1)]
+exp_name = 'pix2pix_edges2shoes_wo_jitter_flip'
+work_dir = f'./work_dirs/experiments/{exp_name}'
+num_images = 200
+metrics = dict(
+    FID=dict(type='FID', num_images=num_images, image_shape=(3, 256, 256)),
+    IS=dict(
+        type='IS',
+        num_images=num_images,
+        image_shape=(3, 256, 256),
+        inception_args=dict(type='pytorch')))
+evaluation = dict(
+    type='TranslationEvalHook',
+    target_domain=domain_b,
+    interval=10000,
+    metrics=[
+        dict(type='FID', num_images=num_images, bgr2rgb=True),
+        dict(
+            type='IS',
+            num_images=num_images,
+            inception_args=dict(type='pytorch'))
+    ],
+    best_metric=['fid', 'is'])
--- a/configs/positional_encoding_in_gans/README.md
+++ b/configs/positional_encoding_in_gans/README.md
+# Positional Encoding in GANs
+> [Positional Encoding as Spatial Inductive Bias in GANs](https://openaccess.thecvf.com/content/CVPR2021/html/Xu_Positional_Encoding_As_Spatial_Inductive_Bias_in_GANs_CVPR_2021_paper.html)
+<!-- [ALGORITHM] -->
+## Abstract
+<!-- [ABSTRACT] -->
+SinGAN shows impressive capability in learning internal patch distribution despite its limited effective receptive field. We are interested in knowing how such a translation-invariant convolutional generator could capture the global structure with just a spatially i.i.d. input. In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators. Such positional encoding is indispensable for generating images with high fidelity. The same phenomenon is observed in other generative architectures such as DCGAN and PGGAN. We further show that zero padding leads to an unbalanced spatial bias with a vague relation between locations. To offer a better spatial inductive bias, we investigate alternative positional encodings and analyze their effects. Based on a more flexible positional encoding explicitly, we propose a new multi-scale training strategy and demonstrate its effectiveness in the state-of-the-art unconditional generator StyleGAN2. Besides, the explicit spatial inductive bias substantially improve SinGAN for more versatile image manipulation.
+<!-- [IMAGE] -->
+<div align=center>
+<img src="https://user-images.githubusercontent.com/28132635/143053767-c6a503b2-87ff-434a-a439-d9fb0e98d804.JPG"/>
+</div>
+## Results and models for MS-PIE
+<div align="center">
+  <b> 896x896 results generated from a 256 generator using MS-PIE</b>
+  <br/>
+  <img src="https://download.openmmlab.com/mmgen/pe_in_gans/mspie_256-896_demo.png" width="800"/>
+</div>
+|            Models            | Reference in Paper |     Scales     | FID50k |   P&R10k    |                            Config                            |                            Download                             |
+| :--------------------------: | :----------------: | :------------: | :----: | :---------: | :----------------------------------------------------------: | :-------------------------------------------------------------: |
+|  stylegan2_c2_256_baseline   |   Tab.5 config-a   |      256       |  5.56  | 75.92/51.24 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_256_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/stylegan2_c2_config-a_ffhq_256x256_b3x8_1100k_20210406_145127-71d9634b.pth) |
+|  stylegan2_c2_512_baseline   |   Tab.5 config-b   |      512       |  4.91  | 75.65/54.58 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/stylegan2_c2_config-b_ffhq_512x512_b3x8_1100k_20210406_145142-e85e5cf4.pth) |
+| ms-pie_stylegan2_c2_config-c |   Tab.5 config-c   | 256, 384, 512  |  3.35  | 73.84/55.77 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k_20210406_144824-9f43b07d.pth) |
+| ms-pie_stylegan2_c2_config-d |   Tab.5 config-d   | 256, 384, 512  |  3.50  | 73.28/56.16 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k_20210406_144840-dbefacf6.pth) |
+| ms-pie_stylegan2_c2_config-e |   Tab.5 config-e   | 256, 384, 512  |  3.15  | 74.13/56.88 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k_20210406_144906-98d5a42a.pth) |
+| ms-pie_stylegan2_c2_config-f |   Tab.5 config-f   | 256, 384, 512  |  2.93  | 73.51/57.32 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-512_b3x8_1100k_20210406_144927-4f4d5391.pth) |
+| ms-pie_stylegan2_c1_config-g |   Tab.5 config-g   | 256, 384, 512  |  3.40  | 73.05/56.45 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k_20210406_144758-2df61752.pth) |
+| ms-pie_stylegan2_c2_config-h |   Tab.5 config-h   | 256, 384, 512  |  4.01  | 72.81/54.35 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-h_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-h_ffhq_256-512_b3x8_1100k_20210406_145006-84cf3f48.pth) |
+| ms-pie_stylegan2_c2_config-i |   Tab.5 config-i   | 256, 384, 512  |  3.76  | 73.26/54.71 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-i_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-i_ffhq_256-512_b3x8_1100k_20210406_145023-c2b0accf.pth) |
+| ms-pie_stylegan2_c2_config-j |   Tab.5 config-j   | 256, 384, 512  |  4.23  | 73.11/54.63 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-j_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-j_ffhq_256-512_b3x8_1100k_20210406_145044-c407481b.pth) |
+| ms-pie_stylegan2_c2_config-k |   Tab.5 config-k   | 256, 384, 512  |  4.17  | 73.05/51.07 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-k_ffhq_256-512_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-k_ffhq_256-512_b3x8_1100k_20210406_145105-6d8cc39f.pth) |
+| ms-pie_stylegan2_c2_config-f | higher-resolution  | 256, 512, 896  |  4.10  | 72.21/50.29 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-896_b3x8_1100k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-896_b3x8_1100k_20210406_144943-6c18ad5d.pth) |
+| ms-pie_stylegan2_c1_config-f | higher-resolution  | 256, 512, 1024 |  6.24  | 71.79/49.92 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k.py) | [model](https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k_20210406_144716-81cbdc96.pth) |
+Note that we report the FID and P&R metric (FFHQ dataset) in the largest scale.
+## Results and Models for SinGAN
+<div align="center">
+  <b> Positional Encoding in SinGAN</b>
+  <br/>
+  <img src="https://nbei.github.io/gan-pos-encoding/teaser-web-singan.png" width="800"/>
+</div>
+|              Model              |                        Data                         | Num Scales |                        Config                         |                        Download                         |
+| :-----------------------------: | :-------------------------------------------------: | :--------: | :---------------------------------------------------: | :-----------------------------------------------------: |
+|         SinGAN + no pad         | [balloons.png](https://download.openmmlab.com/mmgen/dataset/singan/balloons.png) |     8      | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_interp-pad_balloons.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_balloons_20210406_180014-96f51555.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_balloons_20210406_180014-96f51555.pkl) |
+| SinGAN + no pad + no bn in disc | [balloons.png](https://download.openmmlab.com/mmgen/dataset/singan/balloons.png) |     8      | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_balloons.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_disc-nobn_balloons_20210406_180059-7d63e65d.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_disc-nobn_balloons_20210406_180059-7d63e65d.pkl) |
+| SinGAN + no pad + no bn in disc | [fish.jpg](https://download.openmmlab.com/mmgen/dataset/singan/fish-crop.jpg) |     10     | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_fish.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_disc-nobn_fis_20210406_175720-9428517a.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_disc-nobn_fis_20210406_175720-9428517a.pkl) |
+|          SinGAN + CSG           | [fish.jpg](https://download.openmmlab.com/mmgen/dataset/singan/fish-crop.jpg) |     10     | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_csg_fish.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_csg_fis_20210406_175532-f0ec7b61.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_csg_fis_20210406_175532-f0ec7b61.pkl) |
+|          SinGAN + CSG           | [bohemian.png](https://download.openmmlab.com/mmgen/dataset/singan/bohemian.png) |     10     | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_csg_bohemian.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_csg_bohemian_20210407_195455-5ed56db2.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_csg_bohemian_20210407_195455-5ed56db2.pkl) |
+|        SinGAN + SPE-dim4        | [fish.jpg](https://download.openmmlab.com/mmgen/dataset/singan/fish-crop.jpg) |     10     | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_spe-dim4_fish.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim4_fish_20210406_175933-f483a7e3.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim4_fish_20210406_175933-f483a7e3.pkl) |
+|        SinGAN + SPE-dim4        | [bohemian.png](https://download.openmmlab.com/mmgen/dataset/singan/bohemian.png) |     10     | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_spe-dim4_bohemian.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim4_bohemian_20210406_175820-6e484a35.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim4_bohemian_20210406_175820-6e484a35.pkl) |
+|        SinGAN + SPE-dim8        | [bohemian.png](https://download.openmmlab.com/mmgen/dataset/singan/bohemian.png) |     10     | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_spe-dim8_bohemian.py) | [ckpt](https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim8_bohemian_20210406_175858-7faa50f3.pth) \| [pkl](https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim8_bohemian_20210406_175858-7faa50f3.pkl) |
+## Citation
+```latex
+@article{xu2020positional,
+  title={Positional Encoding as Spatial Inductive Bias in GANs},
+  author={Xu, Rui and Wang, Xintao and Chen, Kai and Zhou, Bolei and Loy, Chen Change},
+  journal={arXiv preprint arXiv:2012.05217},
+  year={2020},
+  url={https://openaccess.thecvf.com/content/CVPR2021/html/Xu_Positional_Encoding_As_Spatial_Inductive_Bias_in_GANs_CVPR_2021_paper.html},
+}
+```
--- a/configs/positional_encoding_in_gans/metafile.yml
+++ b/configs/positional_encoding_in_gans/metafile.yml
+Collections:
+- Metadata:
+    Architecture:
+    - Positional Encoding in GANs
+  Name: Positional Encoding in GANs
+  Paper:
+  - https://openaccess.thecvf.com/content/CVPR2021/html/Xu_Positional_Encoding_As_Spatial_Inductive_Bias_in_GANs_CVPR_2021_paper.html
+  README: configs/positional_encoding_in_gans/README.md
+Models:
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_256_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: stylegan2_c2_ffhq_256_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 5.56
+      P&R10k: 75.92/51.24
+      Reference in Paper: Tab.5 config-a
+      Scales: 256.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/stylegan2_c2_config-a_ffhq_256x256_b3x8_1100k_20210406_145127-71d9634b.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: stylegan2_c2_ffhq_512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 4.91
+      P&R10k: 75.65/54.58
+      Reference in Paper: Tab.5 config-b
+      Scales: 512.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/stylegan2_c2_config-b_ffhq_512x512_b3x8_1100k_20210406_145142-e85e5cf4.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 3.35
+      P&R10k: 73.84/55.77
+      Reference in Paper: Tab.5 config-c
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k_20210406_144824-9f43b07d.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 3.5
+      P&R10k: 73.28/56.16
+      Reference in Paper: Tab.5 config-d
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k_20210406_144840-dbefacf6.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 3.15
+      P&R10k: 74.13/56.88
+      Reference in Paper: Tab.5 config-e
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k_20210406_144906-98d5a42a.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-f_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 2.93
+      P&R10k: 73.51/57.32
+      Reference in Paper: Tab.5 config-f
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-512_b3x8_1100k_20210406_144927-4f4d5391.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 3.4
+      P&R10k: 73.05/56.45
+      Reference in Paper: Tab.5 config-g
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k_20210406_144758-2df61752.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-h_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-h_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 4.01
+      P&R10k: 72.81/54.35
+      Reference in Paper: Tab.5 config-h
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-h_ffhq_256-512_b3x8_1100k_20210406_145006-84cf3f48.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-i_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-i_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 3.76
+      P&R10k: 73.26/54.71
+      Reference in Paper: Tab.5 config-i
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-i_ffhq_256-512_b3x8_1100k_20210406_145023-c2b0accf.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-j_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-j_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 4.23
+      P&R10k: 73.11/54.63
+      Reference in Paper: Tab.5 config-j
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-j_ffhq_256-512_b3x8_1100k_20210406_145044-c407481b.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-k_ffhq_256-512_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-k_ffhq_256-512_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 4.17
+      P&R10k: 73.05/51.07
+      Reference in Paper: Tab.5 config-k
+      Scales: 256, 384, 512
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-k_ffhq_256-512_b3x8_1100k_20210406_145105-6d8cc39f.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-896_b3x8_1100k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c2_config-f_ffhq_256-896_b3x8_1100k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 4.1
+      P&R10k: 72.21/50.29
+      Reference in Paper: higher-resolution
+      Scales: 256, 512, 896
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-896_b3x8_1100k_20210406_144943-6c18ad5d.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: FFHQ
+  Name: mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k
+  Results:
+  - Dataset: FFHQ
+    Metrics:
+      FID50k: 6.24
+      P&R10k: 71.79/49.92
+      Reference in Paper: higher-resolution
+      Scales: 256, 512, 1024
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k_20210406_144716-81cbdc96.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_interp-pad_balloons.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_interp-pad_balloons
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 8.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_balloons_20210406_180014-96f51555.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_balloons.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_interp-pad_disc-nobn_balloons
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 8.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_disc-nobn_balloons_20210406_180059-7d63e65d.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_fish.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_interp-pad_disc-nobn_fish
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 10.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_interp-pad_disc-nobn_fis_20210406_175720-9428517a.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_csg_fish.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_csg_fish
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 10.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_csg_fis_20210406_175532-f0ec7b61.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_csg_bohemian.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_csg_bohemian
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 10.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_csg_bohemian_20210407_195455-5ed56db2.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_spe-dim4_fish.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_spe-dim4_fish
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 10.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim4_fish_20210406_175933-f483a7e3.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_spe-dim4_bohemian.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_spe-dim4_bohemian
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 10.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim4_bohemian_20210406_175820-6e484a35.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/positional_encoding_in_gans/singan_spe-dim8_bohemian.py
+  In Collection: Positional Encoding in GANs
+  Metadata:
+    Training Data: Others
+  Name: singan_spe-dim8_bohemian
+  Results:
+  - Dataset: Others
+    Metrics:
+      Num Scales: 10.0
+    Task: Unconditional GANs
+  Weights: https://download.openmmlab.com/mmgen/pe_in_gans/singan_spe-dim8_bohemian_20210406_175858-7faa50f3.pth
--- a/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k.py
+_base_ = [
+    '../_base_/datasets/ffhq_flip.py',
+    '../_base_/models/stylegan/stylegan2_base.py',
+    '../_base_/default_runtime.py'
+]
+model = dict(
+    type='MSPIEStyleGAN2',
+    generator=dict(
+        type='MSStyleGANv2Generator',
+        head_pos_encoding=dict(
+            type='SPE',
+            embedding_dim=256,
+            padding_idx=0,
+            init_size=256,
+            center_shift=100),
+        deconv2conv=True,
+        up_after_conv=True,
+        up_config=dict(scale_factor=2, mode='bilinear', align_corners=True),
+        out_size=256,
+        channel_multiplier=1),
+    discriminator=dict(
+        type='MSStyleGAN2Discriminator', in_size=256, with_adaptive_pool=True))
+train_cfg = dict(
+    num_upblocks=6,
+    multi_input_scales=[0, 4, 12],
+    multi_scale_probability=[0.5, 0.25, 0.25])
+data = dict(
+    samples_per_gpu=2,
+    train=dict(dataset=dict(
+        imgs_root='./data/ffhq/images')))  # path for 1024 scales
+ema_half_life = 10.
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        interp_cfg=dict(momentum=0.5**(32. / (ema_half_life * 1000.))),
+        priority='VERY_HIGH')
+]
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=40)
+lr_config = None
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+cudnn_benchmark = False
+total_iters = 1500002
+metrics = dict(
+    fid50k=dict(
+        type='FID',
+        num_images=50000,
+        inception_pkl='work_dirs/inception_pkl/ffhq-256-50k-rgb.pkl',
+        bgr2rgb=True),
+    pr10k3=dict(type='PR', num_images=10000, k=3))
--- a/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k.py
+_base_ = [
+    '../_base_/datasets/ffhq_flip.py',
+    '../_base_/models/stylegan/stylegan2_base.py',
+    '../_base_/default_runtime.py'
+]
+model = dict(
+    type='MSPIEStyleGAN2',
+    generator=dict(
+        type='MSStyleGANv2Generator',
+        head_pos_encoding=dict(
+            type='SPE',
+            embedding_dim=256,
+            padding_idx=0,
+            init_size=256,
+            center_shift=100),
+        deconv2conv=True,
+        up_after_conv=True,
+        up_config=dict(scale_factor=2, mode='bilinear', align_corners=True),
+        out_size=256,
+        channel_multiplier=1),
+    discriminator=dict(
+        type='MSStyleGAN2Discriminator',
+        in_size=256,
+        with_adaptive_pool=True,
+        channel_multiplier=1))
+train_cfg = dict(
+    num_upblocks=6,
+    multi_input_scales=[0, 2, 4],
+    multi_scale_probability=[0.5, 0.25, 0.25])
+data = dict(
+    samples_per_gpu=3,
+    train=dict(dataset=dict(imgs_root='./data/ffhq/ffhq_imgs/ffhq_512')))
+ema_half_life = 10.
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        interp_cfg=dict(momentum=0.5**(32. / (ema_half_life * 1000.))),
+        priority='VERY_HIGH')
+]
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=40)
+lr_config = None
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+cudnn_benchmark = False
+total_iters = 1100002
+metrics = dict(
+    fid50k=dict(
+        type='FID',
+        num_images=50000,
+        inception_pkl='work_dirs/inception_pkl/ffhq-256-50k-rgb.pkl',
+        bgr2rgb=True),
+    pr10k3=dict(type='PR', num_images=10000, k=3))
--- a/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k.py
+_base_ = [
+    '../_base_/datasets/ffhq_flip.py',
+    '../_base_/models/stylegan/stylegan2_base.py',
+    '../_base_/default_runtime.py'
+]
+model = dict(
+    type='MSPIEStyleGAN2',
+    generator=dict(
+        type='MSStyleGANv2Generator',
+        head_pos_encoding=None,
+        deconv2conv=True,
+        up_after_conv=True,
+        head_pos_size=(4, 4),
+        interp_head=True,
+        up_config=dict(scale_factor=2, mode='bilinear', align_corners=True),
+        out_size=256),
+    discriminator=dict(
+        type='MSStyleGAN2Discriminator', in_size=256, with_adaptive_pool=True))
+train_cfg = dict(
+    num_upblocks=6,
+    multi_input_scales=[0, 2, 4],
+    multi_scale_probability=[0.5, 0.25, 0.25])
+data = dict(
+    samples_per_gpu=3,
+    train=dict(dataset=dict(imgs_root='./data/ffhq/ffhq_imgs/ffhq_512')))
+ema_half_life = 10.
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        interp_cfg=dict(momentum=0.5**(32. / (ema_half_life * 1000.))),
+        priority='VERY_HIGH')
+]
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=40)
+lr_config = None
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+cudnn_benchmark = False
+total_iters = 1100002
+metrics = dict(
+    fid50k=dict(
+        type='FID',
+        num_images=50000,
+        inception_pkl='work_dirs/inception_pkl/ffhq-256-50k-rgb.pkl',
+        bgr2rgb=True),
+    pr10k3=dict(type='PR', num_images=10000, k=3))
--- a/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k.py
+_base_ = [
+    '../_base_/datasets/ffhq_flip.py',
+    '../_base_/models/stylegan/stylegan2_base.py',
+    '../_base_/default_runtime.py'
+]
+model = dict(
+    type='MSPIEStyleGAN2',
+    generator=dict(
+        type='MSStyleGANv2Generator',
+        head_pos_encoding=dict(type='CSG'),
+        deconv2conv=True,
+        up_after_conv=True,
+        head_pos_size=(4, 4),
+        up_config=dict(scale_factor=2, mode='bilinear', align_corners=True),
+        out_size=256),
+    discriminator=dict(
+        type='MSStyleGAN2Discriminator', in_size=256, with_adaptive_pool=True))
+train_cfg = dict(
+    num_upblocks=6,
+    multi_input_scales=[0, 2, 4],
+    multi_scale_probability=[0.5, 0.25, 0.25])
+data = dict(
+    samples_per_gpu=3,
+    train=dict(dataset=dict(imgs_root='./data/ffhq/ffhq_imgs/ffhq_512')))
+ema_half_life = 10.
+custom_hooks = [
+    dict(
+        type='VisualizeUnconditionalSamples',
+        output_dir='training_samples',
+        interval=5000),
+    dict(
+        type='ExponentialMovingAverageHook',
+        module_keys=('generator_ema', ),
+        interval=1,
+        interp_cfg=dict(momentum=0.5**(32. / (ema_half_life * 1000.))),
+        priority='VERY_HIGH')
+]
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=40)
+lr_config = None
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+cudnn_benchmark = False
+total_iters = 1100002
+metrics = dict(
+    fid50k=dict(
+        type='FID',
+        num_images=50000,
+        inception_pkl='work_dirs/inception_pkl/ffhq-256-50k-rgb.pkl',
+        bgr2rgb=True),
+    pr10k3=dict(type='PR', num_images=10000, k=3))