add part mmgeneration code

57e0e891 · limm · 04e07f48 · 57e0e891 · 57e0e891 · 57e0e891
Commit 57e0e891 authored Jun 16, 2025 by limm
20 changed files
--- a/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-e_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,
+        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-f_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_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),
+    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-f_ffhq_256-896_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-896_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),
+    discriminator=dict(
+        type='MSStyleGAN2Discriminator', in_size=256, with_adaptive_pool=True))
+
+train_cfg = dict(
+    num_upblocks=6,
+    multi_input_scales=[0, 4, 10],
+    multi_scale_probability=[0.5, 0.25, 0.25])
+
+data = dict(
+    samples_per_gpu=3,
+    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 = 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-h_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-h_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=False,
+        interp_pad=4,
+        no_pad=True,
+        head_pos_size=(6, 6),
+        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-i_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-i_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=False,
+        interp_pad=4,
+        no_pad=True,
+        head_pos_size=(6, 6),
+        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-j_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-j_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=False,
+        interp_pad=4,
+        no_pad=True,
+        head_pos_size=(6, 6),
+        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-k_ffhq_256-512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-k_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=False,
+        interp_pad=4,
+        no_pad=True,
+        head_pos_size=(6, 6),
+        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/singan_csg_bohemian.py
+++ b/configs/positional_encoding_in_gans/singan_csg_bohemian.py
+_base_ = ['../singan/singan_bohemian.py']
+
+num_scales = 10  # start from zero
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE',
+        num_scales=num_scales,
+        padding=1,
+        pad_at_head=False,
+        first_stage_in_channels=2,
+        positional_encoding=dict(type='CSG')),
+    discriminator=dict(num_scales=num_scales))
+
+train_cfg = dict(first_fixed_noises_ch=2)
+
+data = dict(
+    train=dict(
+        img_path='./data/singan/bohemian.png',
+        min_size=25,
+        max_size=500,
+    ))
+
+dist_params = dict(backend='nccl')
+total_iters = 22000
--- a/configs/positional_encoding_in_gans/singan_csg_fish.py
+++ b/configs/positional_encoding_in_gans/singan_csg_fish.py
+_base_ = ['../singan/singan_fish.py']
+
+num_scales = 10  # start from zero
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE',
+        num_scales=num_scales,
+        padding=1,
+        pad_at_head=False,
+        first_stage_in_channels=2,
+        positional_encoding=dict(type='CSG')),
+    discriminator=dict(num_scales=num_scales))
+
+train_cfg = dict(first_fixed_noises_ch=2)
+
+data = dict(
+    train=dict(
+        img_path='./data/singan/fish-crop.jpg',
+        min_size=25,
+        max_size=300,
+    ))
+
+dist_params = dict(backend='nccl')
+total_iters = 22000
--- a/configs/positional_encoding_in_gans/singan_interp-pad_balloons.py
+++ b/configs/positional_encoding_in_gans/singan_interp-pad_balloons.py
+_base_ = ['../singan/singan_balloons.py']
+
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE', interp_pad=True, noise_with_pad=True))
+
+train_cfg = dict(fixed_noise_with_pad=True)
+
+dist_params = dict(backend='nccl')
--- a/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_balloons.py
+++ b/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_balloons.py
+_base_ = ['../singan/singan_balloons.py']
+
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE', interp_pad=True, noise_with_pad=True),
+    discriminator=dict(norm_cfg=None))
+
+train_cfg = dict(fixed_noise_with_pad=True)
+
+dist_params = dict(backend='nccl')
--- a/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_fish.py
+++ b/configs/positional_encoding_in_gans/singan_interp-pad_disc-nobn_fish.py
+_base_ = ['../singan/singan_fish.py']
+
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE', interp_pad=True, noise_with_pad=True),
+    discriminator=dict(norm_cfg=None))
+
+train_cfg = dict(fixed_noise_with_pad=True)
+
+data = dict(
+    train=dict(
+        img_path='./data/singan/fish-crop.jpg',
+        min_size=25,
+        max_size=300,
+    ))
+
+dist_params = dict(backend='nccl')
--- a/configs/positional_encoding_in_gans/singan_spe-dim4_bohemian.py
+++ b/configs/positional_encoding_in_gans/singan_spe-dim4_bohemian.py
+_base_ = ['../singan/singan_bohemian.py']
+
+embedding_dim = 4
+num_scales = 10  # start from zero
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE',
+        num_scales=num_scales,
+        padding=1,
+        pad_at_head=False,
+        first_stage_in_channels=embedding_dim * 2,
+        positional_encoding=dict(
+            type='SPE',
+            embedding_dim=embedding_dim,
+            padding_idx=0,
+            init_size=512,
+            div_half_dim=False,
+            center_shift=200)),
+    discriminator=dict(num_scales=num_scales))
+
+train_cfg = dict(first_fixed_noises_ch=embedding_dim * 2)
+
+data = dict(
+    train=dict(
+        img_path='./data/singan/bohemian.png',
+        min_size=25,
+        max_size=500,
+    ))
+
+dist_params = dict(backend='nccl')
+total_iters = 22000
--- a/configs/positional_encoding_in_gans/singan_spe-dim4_fish.py
+++ b/configs/positional_encoding_in_gans/singan_spe-dim4_fish.py
+_base_ = ['../singan/singan_fish.py']
+
+embedding_dim = 4
+num_scales = 10  # start from zero
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE',
+        num_scales=num_scales,
+        padding=1,
+        pad_at_head=False,
+        first_stage_in_channels=embedding_dim * 2,
+        positional_encoding=dict(
+            type='SPE',
+            embedding_dim=embedding_dim,
+            padding_idx=0,
+            init_size=512,
+            div_half_dim=False,
+            center_shift=200)),
+    discriminator=dict(num_scales=num_scales))
+
+data = dict(
+    train=dict(
+        img_path='./data/singan/fish-crop.jpg',
+        min_size=25,
+        max_size=300,
+    ))
+
+dist_params = dict(backend='nccl')
+total_iters = 22000
--- a/configs/positional_encoding_in_gans/singan_spe-dim8_bohemian.py
+++ b/configs/positional_encoding_in_gans/singan_spe-dim8_bohemian.py
+_base_ = ['../singan/singan_bohemian.py']
+
+embedding_dim = 4
+num_scales = 10  # start from zero
+model = dict(
+    type='PESinGAN',
+    generator=dict(
+        type='SinGANMSGeneratorPE',
+        num_scales=num_scales,
+        padding=1,
+        pad_at_head=False,
+        first_stage_in_channels=embedding_dim * 2,
+        positional_encoding=dict(
+            type='SPE',
+            embedding_dim=embedding_dim,
+            padding_idx=0,
+            init_size=512,
+            div_half_dim=False,
+            center_shift=200)),
+    discriminator=dict(num_scales=num_scales))
+
+train_cfg = dict(first_fixed_noises_ch=embedding_dim * 2)
+
+data = dict(
+    train=dict(
+        img_path='./data/singan/bohemian.png',
+        min_size=25,
+        max_size=500,
+    ))
+
+dist_params = dict(backend='nccl')
+total_iters = 22000
--- a/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_256_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_256_b3x8_1100k.py
+"""Config for the `config-f` setting in StyleGAN2."""
+
+_base_ = [
+    '../_base_/datasets/ffhq_flip.py',
+    '../_base_/models/stylegan/stylegan2_base.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(generator=dict(out_size=256), discriminator=dict(in_size=256))
+
+data = dict(
+    samples_per_gpu=3,
+    train=dict(dataset=dict(imgs_root='./data/ffhq/ffhq_imgs/ffhq_256')))
+
+ema_half_life = 10.  # G_smoothing_kimg
+
+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')
+]
+
+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))
+
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=30)
+lr_config = None
+
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+
+total_iters = 1100002
--- a/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_512_b3x8_1100k.py
+++ b/configs/positional_encoding_in_gans/stylegan2_c2_ffhq_512_b3x8_1100k.py
+"""Config for the `config-f` setting in StyleGAN2."""
+
+_base_ = [
+    '../_base_/datasets/ffhq_flip.py',
+    '../_base_/models/stylegan/stylegan2_base.py',
+    '../_base_/default_runtime.py'
+]
+
+model = dict(generator=dict(out_size=512), discriminator=dict(in_size=512))
+
+data = dict(
+    samples_per_gpu=3,
+    train=dict(dataset=dict(imgs_root='./data/ffhq/ffhq_imgs/ffhq_512')))
+
+ema_half_life = 10.  # G_smoothing_kimg
+
+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')
+]
+
+metrics = dict(
+    fid50k=dict(
+        type='FID',
+        num_images=50000,
+        inception_pkl='work_dirs/inception_pkl/ffhq-512-50k-rgb.pkl',
+        bgr2rgb=True),
+    pr10k3=dict(type='PR', num_images=10000, k=3))
+
+checkpoint_config = dict(interval=10000, by_epoch=False, max_keep_ckpts=30)
+lr_config = None
+
+log_config = dict(
+    interval=100,
+    hooks=[
+        dict(type='TextLoggerHook'),
+        # dict(type='TensorboardLoggerHook'),
+    ])
+
+total_iters = 1100002
--- a/configs/sagan/README.md
+++ b/configs/sagan/README.md
+# SAGAN
+
+> [Self-attention generative adversarial networks](https://proceedings.mlr.press/v97/zhang19d.html)
+
+<!-- [ALGORITHM] -->
+
+## Abstract
+
+<!-- [ABSTRACT] -->
+
+In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details as a function of only spatially local points in lower-resolution feature maps. In SAGAN, details can be generated using cues from all feature locations. Moreover, the discriminator can check that highly detailed features in distant portions of the image are consistent with each other. Furthermore, recent work has shown that generator conditioning affects GAN performance. Leveraging this insight, we apply spectral normalization to the GAN generator and find that this improves training dynamics. The proposed SAGAN performs better than prior work, boosting the best published Inception score from 36.8 to 52.52 and reducing Fréchet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset. Visualization of the attention layers shows that the generator leverages neighborhoods that correspond to object shapes rather than local regions of fixed shape.
+
+<!-- [IMAGE] -->
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/28132635/143054130-8cc1d9b7-df13-4fdb-8dbf-af4b2c15ed28.JPG"/>
+</div>
+
+## Results and models
+
+<div align="center">
+  <b> Results from our SAGAN trained in CIFAR10</b>
+  <br/>
+  <img src="https://user-images.githubusercontent.com/28132635/127619657-67f2e62d-52e4-43d2-931f-6d0e6e019813.png" width="400"/>
+</div>
+
+|           Models           | Dataset  | Inplace ReLU | dist_step | Total Batchsize (BZ_PER_GPU * NGPU) | Total Iters\* |  Iter  |   IS    |   FID   |           Config           |           Download           |           Log           |
+| :------------------------: | :------: | :----------: | :-------: | :---------------------------------: | :-----------: | :----: | :-----: | :-----: | :------------------------: | :--------------------------: | :---------------------: |
+| SAGAN-32x32-woInplaceReLU Best IS | CIFAR10  |     w/o      |     5     |                64x1                 |    500000     | 400000 | 9.3217  | 10.5030 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_woReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_woReUinplace_is-iter400000_20210730_125743-4008a9ca.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_woReUinplace_20210730_125449_fid-d50568a4_is-04008a9ca.json) |
+| SAGAN-32x32-woInplaceReLU Best FID | CIFAR10  |     w/o      |     5     |                64x1                 |    500000     | 480000 | 9.3174  | 9.4252  | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_woReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_woReUinplace_fid-iter480000_20210730_125449-d50568a4.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_woReUinplace_20210730_125449_fid-d50568a4_is-04008a9ca.json) |
+| SAGAN-32x32-wInplaceReLU Best IS | CIFAR10  |      w       |     5     |                64x1                 |    500000     | 380000 | 9.2286  | 11.7760 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_wReLUinplace_is-iter380000_20210730_124937-c77b4d25.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_wReLUinplace_20210730_125155_fid-cbefb354_is-c77b4d25.json) |
+| SAGAN-32x32-wInplaceReLU Best FID | CIFAR10  |      w       |     5     |                64x1                 |    500000     | 460000 | 9.2061  | 10.7781 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_wReLUinplace_fid-iter460000_20210730_125155-cbefb354.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_wReLUinplace_20210730_125155_fid-cbefb354_is-c77b4d25.json) |
+| SAGAN-128x128-woInplaceReLU Best IS | ImageNet |     w/o      |     1     |                64x4                 |    1000000    | 980000 | 31.5938 | 36.7712 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b64x4.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_imagenet1k_128_Glr1e-4_Dlr4e-4_ndisc1_b32x4_woReLUinplace_is-iter980000_20210730_163140-cfbebfc6.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_imagenet1k_128_Glr1e-4_Dlr4e-4_ndisc1_b32x4_woReLUinplace_20210730_163431_fid-d7916963_is-cfbebfc6.json) |
+| SAGAN-128x128-woInplaceReLU Best FID | ImageNet |     w/o      |     1     |                64x4                 |    1000000    | 950000 | 28.4936 | 34.7838 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b64x4.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_imagenet1k_128_Glr1e-4_Dlr4e-4_ndisc1_b32x4_woReLUinplace_fid-iter950000_20210730_163431-d7916963.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_imagenet1k_128_Glr1e-4_Dlr4e-4_ndisc1_b32x4_woReLUinplace_20210730_163431_fid-d7916963_is-cfbebfc6.json) |
+| SAGAN-128x128-BigGAN Schedule Best IS | ImageNet |     w/o      |     1     |                32x8                 |    1000000    | 826000 | 69.5350 | 12.8295 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_noaug_bigGAN_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b32x8.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_128_woReLUinplace_noaug_bigGAN_imagenet1k_b32x8_Glr1e-4_Dlr-4e-4_ndisc1_20210818_210232-3f5686af.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_128_woReLUinplace_noaug_bigGAN_imagenet1k_b32x8_Glr1e-4_Dlr-4e-4_ndisc1_20210818_210232-3f5686af.json) |
+| SAGAN-128x128-BigGAN Schedule Best FID | ImageNet |     w/o      |     1     |                32x8                 |    1000000    | 826000 | 69.5350 | 12.8295 | [config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_noaug_bigGAN_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b32x8.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_128_woReLUinplace_noaug_bigGAN_imagenet1k_b32x8_Glr1e-4_Dlr-4e-4_ndisc1_20210818_210232-3f5686af.pth) | [Log](https://download.openmmlab.com/mmgen/sagan/sagan_128_woReLUinplace_noaug_bigGAN_imagenet1k_b32x8_Glr1e-4_Dlr-4e-4_ndisc1_20210818_210232-3f5686af.json) |
+
+'\*' Iteration counting rule in our implementation is different from others. If you want to align with other codebases, you can use the following conversion formula:
+
+```
+total_iters (biggan/pytorch studio gan) = our_total_iters / dist_step
+```
+
+We also provide converted pre-train models from [Pytorch-StudioGAN](https://github.com/POSTECH-CVLab/PyTorch-StudioGAN).
+To be noted that, in Pytorch Studio GAN, **inplace ReLU** is used in generator and discriminator.
+
+|        Models        | Dataset  | Inplace ReLU | n_disc | Total Iters | IS (Our Pipeline) | FID (Our Pipeline) | IS (StudioGAN) | FID (StudioGAN) |        Config        |        Download        |        Original Download link         |
+| :------------------: | :------: | :----------: | :----: | :---------: | :---------------: | :----------------: | :------------: | :-------------: | :------------------: | :--------------------: | :-----------------------------------: |
+| SAGAN-32x32 StudioGAN | CIFAR10  |      w       |   5    |   100000    |       9.116       |      10.2011       |     8.680      |     14.009      | [Config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_cvt_studioGAN.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_32_cifar10_convert-studio-rgb_20210730_153321-080da7e2.pth) | [model](https://drive.google.com/drive/folders/1FA8hcz4MB8-hgTwLuDA0ZUfr8slud5P_) |
+| SAGAN0-128x128 StudioGAN | ImageNet |      w       |   1    |   1000000   |      27.367       |      40.1162       |     29.848     |     34.726      | [Config](https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_cvt_studioGAN.py) | [model](https://download.openmmlab.com/mmgen/sagan/sagan_128_imagenet1k_convert-studio-rgb_20210730_153357-eddb0d1d.pth) | [model](https://drive.google.com/drive/folders/1ZYaqeeumDgxOPDhRR5QLeLFIpgBJ9S6B) |
+
+- `Our Pipeline` denote results evaluated with our pipeline.
+- `StudioGAN` denote results released by Pytorch-StudioGAN.
+
+For IS metric, our implementation is different from PyTorch-Studio GAN in the following aspects:
+
+1. We use [Tero's Inception](https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/metrics/inception-2015-12-05.pt) for feature extraction.
+2. We use bicubic interpolation with PIL backend to resize image before feed them to Inception.
+
+For FID evaluation, we follow the pipeline of [BigGAN](https://github.com/ajbrock/BigGAN-PyTorch/blob/98459431a5d618d644d54cd1e9fceb1e5045648d/calculate_inception_moments.py#L52), where the whole training set is adopted to extract inception statistics, and Pytorch Studio GAN uses 50000 randomly selected samples. Besides, we also use [Tero's Inception](https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/metrics/inception-2015-12-05.pt) for feature extraction.
+
+You can download the preprocessed inception state by the following url: [CIFAR10](https://download.openmmlab.com/mmgen/evaluation/fid_inception_pkl/cifar10.pkl) and [ImageNet1k](https://download.openmmlab.com/mmgen/evaluation/fid_inception_pkl/imagenet.pkl).
+
+You can use following commands to extract those inception states by yourself.
+
+```
+# For CIFAR10
+python tools/utils/inception_stat.py --data-cfg configs/_base_/datasets/cifar10_inception_stat.py --pklname cifar10.pkl --no-shuffle --inception-style stylegan --num-samples -1 --subset train
+
+# For ImageNet1k
+python tools/utils/inception_stat.py --data-cfg configs/_base_/datasets/imagenet_128x128_inception_stat.py --pklname imagenet.pkl --no-shuffle --inception-style stylegan --num-samples -1 --subset train
+```
+
+## Citation
+
+```latex
+@inproceedings{zhang2019self,
+  title={Self-attention generative adversarial networks},
+  author={Zhang, Han and Goodfellow, Ian and Metaxas, Dimitris and Odena, Augustus},
+  booktitle={International conference on machine learning},
+  pages={7354--7363},
+  year={2019},
+  organization={PMLR},
+  url={https://proceedings.mlr.press/v97/zhang19d.html},
+}
+```
--- a/configs/sagan/metafile.yml
+++ b/configs/sagan/metafile.yml
+Collections:
+- Metadata:
+    Architecture:
+    - SAGAN
+  Name: SAGAN
+  Paper:
+  - https://proceedings.mlr.press/v97/zhang19d.html
+  README: configs/sagan/README.md
+Models:
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_woReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: CIFAR
+  Name: sagan_32_woReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1
+  Results:
+  - Dataset: CIFAR
+    Metrics:
+      FID: 10.503
+      IS: 9.3217
+      Inplace ReLU: w/o
+      Iter: 400000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 64x1
+      Total Iters\*: 500000.0
+      dist_step: 5.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_woReUinplace_is-iter400000_20210730_125743-4008a9ca.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_woReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: CIFAR
+  Name: sagan_32_woReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1
+  Results:
+  - Dataset: CIFAR
+    Metrics:
+      FID: 9.4252
+      IS: 9.3174
+      Inplace ReLU: w/o
+      Iter: 480000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 64x1
+      Total Iters\*: 500000.0
+      dist_step: 5.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_woReUinplace_fid-iter480000_20210730_125449-d50568a4.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: CIFAR
+  Name: sagan_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1
+  Results:
+  - Dataset: CIFAR
+    Metrics:
+      FID: 11.776
+      IS: 9.2286
+      Inplace ReLU: w
+      Iter: 380000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 64x1
+      Total Iters\*: 500000.0
+      dist_step: 5.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_wReLUinplace_is-iter380000_20210730_124937-c77b4d25.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: CIFAR
+  Name: sagan_32_wReLUinplace_lr-2e-4_ndisc5_cifar10_b64x1
+  Results:
+  - Dataset: CIFAR
+    Metrics:
+      FID: 10.7781
+      IS: 9.2061
+      Inplace ReLU: w
+      Iter: 460000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 64x1
+      Total Iters\*: 500000.0
+      dist_step: 5.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_cifar10_32_lr2e-4_ndisc5_b64x1_wReLUinplace_fid-iter460000_20210730_125155-cbefb354.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b64x4.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: IMAGENET
+  Name: sagan_128_woReLUinplace_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b64x4
+  Results:
+  - Dataset: IMAGENET
+    Metrics:
+      FID: 36.7712
+      IS: 31.5938
+      Inplace ReLU: w/o
+      Iter: 980000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 64x4
+      Total Iters\*: 1000000.0
+      dist_step: 1.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_imagenet1k_128_Glr1e-4_Dlr4e-4_ndisc1_b32x4_woReLUinplace_is-iter980000_20210730_163140-cfbebfc6.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b64x4.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: IMAGENET
+  Name: sagan_128_woReLUinplace_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b64x4
+  Results:
+  - Dataset: IMAGENET
+    Metrics:
+      FID: 34.7838
+      IS: 28.4936
+      Inplace ReLU: w/o
+      Iter: 950000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 64x4
+      Total Iters\*: 1000000.0
+      dist_step: 1.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_imagenet1k_128_Glr1e-4_Dlr4e-4_ndisc1_b32x4_woReLUinplace_fid-iter950000_20210730_163431-d7916963.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_noaug_bigGAN_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b32x8.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: IMAGENET
+  Name: sagan_128_woReLUinplace_noaug_bigGAN_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b32x8
+  Results:
+  - Dataset: IMAGENET
+    Metrics:
+      FID: 12.8295
+      IS: 69.535
+      Inplace ReLU: w/o
+      Iter: 826000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 32x8
+      Total Iters\*: 1000000.0
+      dist_step: 1.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_128_woReLUinplace_noaug_bigGAN_imagenet1k_b32x8_Glr1e-4_Dlr-4e-4_ndisc1_20210818_210232-3f5686af.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_128_woReLUinplace_noaug_bigGAN_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b32x8.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: IMAGENET
+  Name: sagan_128_woReLUinplace_noaug_bigGAN_Glr-1e-4_Dlr-4e-4_ndisc1_imagenet1k_b32x8
+  Results:
+  - Dataset: IMAGENET
+    Metrics:
+      FID: 12.8295
+      IS: 69.535
+      Inplace ReLU: w/o
+      Iter: 826000.0
+      Log: '[Log]'
+      Total Batchsize (BZ_PER_GPU * NGPU): 32x8
+      Total Iters\*: 1000000.0
+      dist_step: 1.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_128_woReLUinplace_noaug_bigGAN_imagenet1k_b32x8_Glr1e-4_Dlr-4e-4_ndisc1_20210818_210232-3f5686af.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_cvt_studioGAN.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: Others
+  Name: sagan_32_cvt_studioGAN
+  Results:
+  - Dataset: Others
+    Metrics:
+      FID (Our Pipeline): 10.2011
+      FID (StudioGAN): 14.009
+      IS (Our Pipeline): 9.116
+      IS (StudioGAN): 8.68
+      Inplace ReLU: w
+      Total Iters: 100000.0
+      n_disc: 5.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_32_cifar10_convert-studio-rgb_20210730_153321-080da7e2.pth
+- Config: https://github.com/open-mmlab/mmgeneration/tree/master/configs/sagan/sagan_32_cvt_studioGAN.py
+  In Collection: SAGAN
+  Metadata:
+    Training Data: Others
+  Name: sagan_32_cvt_studioGAN
+  Results:
+  - Dataset: Others
+    Metrics:
+      FID (Our Pipeline): 40.1162
+      FID (StudioGAN): 34.726
+      IS (Our Pipeline): 27.367
+      IS (StudioGAN): 29.848
+      Inplace ReLU: w
+      Total Iters: 1000000.0
+      n_disc: 1.0
+    Task: Conditional GANs
+  Weights: https://download.openmmlab.com/mmgen/sagan/sagan_128_imagenet1k_convert-studio-rgb_20210730_153357-eddb0d1d.pth
--- a/configs/sagan/sagan_128_cvt_studioGAN.py
+++ b/configs/sagan/sagan_128_cvt_studioGAN.py
+_base_ = ['../_base_/models/sagan/sagan_128x128.py']