256

"<torch.utils.data.dataloader.DataLoader object at 0x7fe0758590d0>"

"cuda"

64

196

0.3

100

0.1

0.1

0.0001

0.0001

512

12

2

10

3

5

4

10

"Discriminator( (first_conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(3, 12, 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(12, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(12, 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(12, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(12, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(12, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (4): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(12, 12, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(12, 24, 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(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(24, 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(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (4): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(24, 24, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(24, 48, 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(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(48, 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(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (4): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(48, 48, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(48, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(48, 96, 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(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(96, 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(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (4): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(96, 96, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(96, 192, 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(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(192, 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(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (4): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(192, 192, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(192, 384, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) (5): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(384, 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(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (4): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(384, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (2): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(384, 768, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) ) (classify): Sequential( (0): Conv2d(768, 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((196,), eps=1e-05, elementwise_affine=True) (layers): ModuleList( (0): Sequential( (0): Linear(in_features=196, out_features=196, bias=True) (1): LayerNorm((196,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Linear(in_features=196, out_features=196, bias=True) (1): LayerNorm((196,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Linear(in_features=196, out_features=196, bias=True) (1): LayerNorm((196,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Linear(in_features=196, out_features=196, bias=True) (1): LayerNorm((196,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) ) (out): Linear(in_features=196, out_features=196, bias=True) ) (synthesis): SynthesisNetwork( (blocks): ModuleList( (0): SynthesisBlock( (layers): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(512, 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(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (ada_in): AdaIN() (A1): Linear(in_features=196, out_features=1024, bias=True) (A2): Linear(in_features=196, out_features=1024, bias=True) (B1): Conv2d(10, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (B2): Conv2d(10, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): SynthesisBlock( (upsample): ConvTranspose2d(512, 256, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (layers): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(256, 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(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (ada_in): AdaIN() (A1): Linear(in_features=196, out_features=512, bias=True) (A2): Linear(in_features=196, out_features=512, bias=True) (B1): Conv2d(10, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (B2): Conv2d(10, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): SynthesisBlock( (upsample): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (layers): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(128, 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(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (ada_in): AdaIN() (A1): Linear(in_features=196, out_features=256, bias=True) (A2): Linear(in_features=196, out_features=256, bias=True) (B1): Conv2d(10, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (B2): Conv2d(10, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): SynthesisBlock( (upsample): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (layers): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (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)) (2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (ada_in): AdaIN() (A1): Linear(in_features=196, out_features=128, bias=True) (A2): Linear(in_features=196, out_features=128, bias=True) (B1): Conv2d(10, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (B2): Conv2d(10, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): SynthesisBlock( (upsample): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (layers): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (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)) (2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (ada_in): AdaIN() (A1): Linear(in_features=196, out_features=64, bias=True) (A2): Linear(in_features=196, out_features=64, bias=True) (B1): Conv2d(10, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (B2): Conv2d(10, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (5): SynthesisBlock( (upsample): ConvTranspose2d(32, 16, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (layers): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (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)) (2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(16, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): BatchNorm2d(16, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (ada_in): AdaIN() (A1): Linear(in_features=196, out_features=32, bias=True) (A2): Linear(in_features=196, out_features=32, bias=True) (B1): Conv2d(10, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (B2): Conv2d(10, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (to_rgb): Conv2d(16, 3, kernel_size=(1, 1), stride=(1, 1)) ) )"

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

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

0.9

0.9

0

"<torch.optim.lr_scheduler.MultiStepLR object at 0x7fe086c1e550>"

"<torch.optim.lr_scheduler.MultiStepLR object at 0x7fe07582fd90>"

0.5

0.5

0

0

1

0.7036973834037781

0.7045273959636689

0.705357426404953

0.4946015954017639

0.7300327003002167

0.7300327599048615

0.49479223489761354

0.00000000371281965172

0.0000000879530642095