StepLR - 32x32

64

"<torch.utils.data.dataloader.DataLoader object at 0x7f6677a71b20>"

"cuda"

32

64

0.3

50

0.8

0.8

0.001

0.0001

64

4

2

2

"Discriminator( (first_conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(3, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (blocks): ModuleList( (0): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(4, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(4, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(4, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(4, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(4, 8, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) (1): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(8, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(8, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) (2): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(16, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) (3): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) (4): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) ) (classify): Sequential( (0): Conv2d(128, 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((64,), eps=1e-05, elementwise_affine=True) (layers): ModuleList( (0): Sequential( (0): Linear(in_features=64, out_features=64, bias=True) (1): LayerNorm((64,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Linear(in_features=64, out_features=64, bias=True) (1): LayerNorm((64,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) ) (out): Linear(in_features=64, out_features=64, bias=True) ) (synthesis): SynthesisNetwork( (blocks): ModuleList( (0): SynthesisBlock( (conv2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) (1): SynthesisBlock( (upsample): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (conv2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) (2): SynthesisBlock( (upsample): ConvTranspose2d(32, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (conv2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) (3): SynthesisBlock( (upsample): ConvTranspose2d(16, 8, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv1): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (conv2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(8, 8, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) ) (to_rgb): Conv2d(8, 3, kernel_size=(1, 1), stride=(1, 1)) ) )"

"Adam ( Parameter Group 0 amsgrad: False betas: (0.5, 0.99) eps: 1e-08 initial_lr: 0.001 lr: 0.001 weight_decay: 0 )"

"Adam ( Parameter Group 0 amsgrad: False betas: (0.5, 0.99) eps: 1e-08 initial_lr: 0.0001 lr: 0.0001 weight_decay: 0 )"

10

0

50

50

"<torch.optim.lr_scheduler.StepLR object at 0x7f66868a9f70>"

"<torch.optim.lr_scheduler.StepLR object at 0x7f6677a717f0>"

0

0

0.37869693350863887

5.192645639960674

1.4056763061335389

0.7766449201394855

1.5021786038544576

0.2189455065778803