Skip to content

GitLab

Commit 1401de15 authored by dongchy920's avatar dongchy920
Browse files

stylegan2_mmcv

parents
Pipeline #1274 canceled with stages
Hide whitespace changes
Inline Side-by-side
Showing with 1646 additions and 0 deletions
build/lib/mmgen/.mim/configs/pix2pix/metafile.yml 0 → 100644
View file @ 1401de15
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
build/lib/mmgen/.mim/configs/pix2pix/pix2pix_vanilla_unet_bn_aerial2maps_b1x1_220k.py 0 → 100644
View file @ 1401de15
_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'])
build/lib/mmgen/.mim/configs/pix2pix/pix2pix_vanilla_unet_bn_facades_b1x1_80k.py 0 → 100644
View file @ 1401de15
_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'])
build/lib/mmgen/.mim/configs/pix2pix/pix2pix_vanilla_unet_bn_maps2aerial_b1x1_220k.py 0 → 100644
View file @ 1401de15
_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'])
build/lib/mmgen/.mim/configs/pix2pix/pix2pix_vanilla_unet_bn_wo_jitter_flip_edges2shoes_b1x4_190k.py 0 → 100644
View file @ 1401de15
_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'])
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/metafile.yml 0 → 100644
View file @ 1401de15
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
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-f_ffhq_256-1024_b2x8_1600k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c1_config-g_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-c_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-d_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-e_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-f_ffhq_256-896_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-h_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-i_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-j_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/mspie-stylegan2_c2_config-k_ffhq_256-512_b3x8_1100k.py 0 → 100644
View file @ 1401de15
_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))
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/singan_csg_bohemian.py 0 → 100644
View file @ 1401de15
_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
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/singan_csg_fish.py 0 → 100644
View file @ 1401de15
_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
build/lib/mmgen/.mim/configs/positional_encoding_in_gans/singan_interp-pad_balloons.py 0 → 100644
View file @ 1401de15
_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')
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment