Pierrotlc's group workspace
Group: BCELoss - 32x32
State
Notes
User
Tags
Created
Runtime
Sweep
batch_size
betas_d
betas_g
device
dim_image
dim_z
dropout
epochs
iter_D
lr_d
lr_g
n_channels
n_first_channels
n_layers_d_block
n_layers_z
netD
netG
optimD
optimG
seed
test_loader
train_loader
weight_GP
weight_err_d_real
data_cfg.dim_image
data_cfg.path
dataloader
discriminator_cfg.betas
discriminator_cfg.dropout
discriminator_cfg.gamma
discriminator_cfg.lr
discriminator_cfg.n_channels
discriminator_cfg.n_layers_d_block
discriminator_cfg.running_avg_factor
discriminator_cfg.weight_avg_factor
gamma_d
gamma_g
generator_cfg.betas
generator_cfg.dim_z
generator_cfg.dropout
generator_cfg.gamma
generator_cfg.lr
generator_cfg.n_channels
generator_cfg.n_layers_block
Failed
pierrotlc
1m 36s
-
64
-
-
cpu
32
32
-
15
-
0.0001
0.00001
128
8
4
3
Discriminator(
(first_conv): Conv2d(3, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(blocks): ModuleList(
(0): DiscriminatorBlock(
(convs): ModuleList(
(0): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(3): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(1): DiscriminatorBlock(
(convs): ModuleList(
(0): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(3): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(2): DiscriminatorBlock(
(convs): ModuleList(
(0): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(3): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(3): DiscriminatorBlock(
(convs): ModuleList(
(0): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(3): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(4): DiscriminatorBlock(
(convs): ModuleList(
(0): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
(3): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(downsample): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
)
(classify): Sequential(
(0): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Flatten(start_dim=1, end_dim=-1)
)
)
StyleGAN(
(mapping): MappingNetwork(
(norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(fully_connected): ModuleList(
(0): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(out_layer): Linear(in_features=32, out_features=32, bias=True)
)
(synthesis): SynthesisNetwork(
(blocks): ModuleList(
(0): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(1): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(2): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(3): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
)
(to_rgb): Conv2d(128, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 0.0001
weight_decay: 0
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 1e-05
weight_decay: 0
)
0
<torch.utils.data.dataloader.DataLoader object at 0x7fa71bd22100>
<torch.utils.data.dataloader.DataLoader object at 0x7fa71c215fd0>
-
0.03
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
pierrotlc
13h 38m 45s
-
64
-
-
cuda
32
32
-
15
-
0.00001
0.00001
128
8
-
3
Discriminator(
(first_conv): Conv2d(3, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(blocks): ModuleList(
(0): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(1): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(2): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(3): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(4): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
)
(classify): Sequential(
(0): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Flatten(start_dim=1, end_dim=-1)
)
)
StyleGAN(
(mapping): MappingNetwork(
(norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(fully_connected): ModuleList(
(0): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(out_layer): Linear(in_features=32, out_features=32, bias=True)
)
(synthesis): SynthesisNetwork(
(blocks): ModuleList(
(0): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(1): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(2): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(3): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
)
(to_rgb): Conv2d(128, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 1e-05
weight_decay: 0
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 1e-05
weight_decay: 0
)
0
<torch.utils.data.dataloader.DataLoader object at 0x7f493453a730>
<torch.utils.data.dataloader.DataLoader object at 0x7f493453a640>
-
0.03
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
pierrotlc
31m 49s
-
64
-
-
cuda
32
32
-
15
-
0.0001
0.00005
128
8
-
3
Discriminator(
(first_conv): Conv2d(3, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(blocks): ModuleList(
(0): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(1): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(2): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(3): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(4): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
)
(classify): Sequential(
(0): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Flatten(start_dim=1, end_dim=-1)
)
)
StyleGAN(
(mapping): MappingNetwork(
(norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(fully_connected): ModuleList(
(0): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(out_layer): Linear(in_features=32, out_features=32, bias=True)
)
(synthesis): SynthesisNetwork(
(blocks): ModuleList(
(0): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(1): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(2): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(3): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
)
(to_rgb): Conv2d(128, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 0.0001
weight_decay: 0
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 5e-05
weight_decay: 0
)
0
<torch.utils.data.dataloader.DataLoader object at 0x7faa85567700>
<torch.utils.data.dataloader.DataLoader object at 0x7faa85567610>
-
0.03
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
pierrotlc
48m 23s
-
64
-
-
cuda
32
32
-
35
-
0.0001
0.00005
128
8
-
3
Discriminator(
(first_conv): Conv2d(3, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(blocks): ModuleList(
(0): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(1): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(2): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(3): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(4): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
)
(classify): Sequential(
(0): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Flatten(start_dim=1, end_dim=-1)
)
)
StyleGAN(
(mapping): MappingNetwork(
(norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(fully_connected): ModuleList(
(0): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(out_layer): Linear(in_features=32, out_features=32, bias=True)
)
(synthesis): SynthesisNetwork(
(blocks): ModuleList(
(0): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(1): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(2): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(3): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
)
(to_rgb): Conv2d(128, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 0.0001
weight_decay: 0
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 5e-05
weight_decay: 0
)
0
<torch.utils.data.dataloader.DataLoader object at 0x7f551be82700>
<torch.utils.data.dataloader.DataLoader object at 0x7f551be82610>
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
pierrotlc
24m 46s
-
64
-
-
cuda
32
32
-
15
-
0.0001
0.00005
128
8
-
3
Discriminator(
(first_conv): Conv2d(3, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(blocks): ModuleList(
(0): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(1): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(2): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(3): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(4): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
)
(classify): Sequential(
(0): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Flatten(start_dim=1, end_dim=-1)
)
)
StyleGAN(
(mapping): MappingNetwork(
(norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(fully_connected): ModuleList(
(0): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(out_layer): Linear(in_features=32, out_features=32, bias=True)
)
(synthesis): SynthesisNetwork(
(blocks): ModuleList(
(0): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(1): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(2): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(3): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
)
(to_rgb): Conv2d(128, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 0.0001
weight_decay: 0
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 5e-05
weight_decay: 0
)
0
<torch.utils.data.dataloader.DataLoader object at 0x7f72ec0a3700>
<torch.utils.data.dataloader.DataLoader object at 0x7f72ec0a3610>
-
0.1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
pierrotlc
1h 22m 1s
-
128
-
-
cuda
32
32
-
35
-
0.0001
0.00005
128
8
-
3
Discriminator(
(first_conv): Conv2d(3, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(blocks): ModuleList(
(0): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(1): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(2): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(3): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
(4): DiscriminatorBlock(
(convs): Sequential(
(0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(2): LeakyReLU(negative_slope=0.01)
(3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(5): LeakyReLU(negative_slope=0.01)
)
(downsample): Conv2d(128, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1))
)
)
(classify): Sequential(
(0): Conv2d(256, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(1): Flatten(start_dim=1, end_dim=-1)
)
)
StyleGAN(
(mapping): MappingNetwork(
(norm): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(fully_connected): ModuleList(
(0): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(1): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
(2): Sequential(
(0): Linear(in_features=32, out_features=32, bias=True)
(1): LayerNorm((32,), eps=1e-05, elementwise_affine=True)
(2): LeakyReLU(negative_slope=0.01)
)
)
(out_layer): Linear(in_features=32, out_features=32, bias=True)
)
(synthesis): SynthesisNetwork(
(blocks): ModuleList(
(0): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(1): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(2): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
(3): SynthesisBlock(
(upsample): Upsample(scale_factor=2.0, mode=nearest)
(conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(ada_in): AdaIN()
)
)
(to_rgb): Conv2d(128, 3, kernel_size=(1, 1), stride=(1, 1))
)
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 0.0001
weight_decay: 0
)
Adam (
Parameter Group 0
amsgrad: False
betas: (0.9, 0.999)
eps: 1e-08
lr: 5e-05
weight_decay: 0
)
0
<torch.utils.data.dataloader.DataLoader object at 0x7f7be29c76d0>
<torch.utils.data.dataloader.DataLoader object at 0x7f7be29c75e0>
-
0.1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
1-6
of 6