pierrotlc

Pierrotlc's group workspace

Group: BCE - 32x32

1-4

of 4

Tags

Notes

Author

pierrotlc

State

Finished

Start time

January 26th, 2022 12:33:28 AM

Runtime

26m 21s

Tracked hours

25m 55s

Run path

pierrotlc/AnimeStyleGAN/16wezq2a

Linux-5.15.15-76051515-generic-x86_64-with-glibc2.10

Python version

3.8.5

Git repository

git clone git@github.com:Futurne/AnimeStyleGAN.git

Git state

git checkout -b "peachy-thunder-94" 5e69917e5456bb517e3836df16ec72aed04ecd9f

Command

launch_training.py

System Hardware

CPU count	16
GPU count	1
GPU type	NVIDIA GeForce RTX 3080 Laptop GPU

W&B CLI Version

0.12.9

Group

BCE - 32x32

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 21 keys
- batch_size:
  64
- ▶
  betas_d:[] 2 items
  - 0:
    0.5
  - 1:
    0.99
- ▶
  betas_g:[] 2 items
  - 0:
    0.5
  - 1:
    0.99
- device:
  "cuda"
- dim_image:
  32
- dim_z:
  100
- dropout:
  0.3
- epochs:
  30
- lr_d:
  0.0001
- lr_g:
  0.00001
- n_channels:
  256
- n_first_channels:
  16
- n_layers_d_block:
  2
- n_layers_z:
  4
- netD:
  "Discriminator( (first_conv): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(3, 16, 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(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)) ) (1): 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)) ) (2): 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)) ) (3): DiscriminatorBlock( (convs): ModuleList( (0): Sequential( (0): Dropout(p=0.3, inplace=False) (1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (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), bias=False) (2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(128, 256, 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(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (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), bias=False) (2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (3): LeakyReLU(negative_slope=0.01) ) ) (downsample): Conv2d(256, 512, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) ) ) (classify): Sequential( (0): Conv2d(512, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): Flatten(start_dim=1, end_dim=-1) ) )"
- netG:
  "StyleGAN( (mapping): MappingNetwork( (norm): LayerNorm((100,), eps=1e-05, elementwise_affine=True) (fully_connected): ModuleList( (0): Sequential( (0): Linear(in_features=100, out_features=100, bias=True) (1): LayerNorm((100,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (1): Sequential( (0): Linear(in_features=100, out_features=100, bias=True) (1): LayerNorm((100,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (2): Sequential( (0): Linear(in_features=100, out_features=100, bias=True) (1): LayerNorm((100,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) (3): Sequential( (0): Linear(in_features=100, out_features=100, bias=True) (1): LayerNorm((100,), eps=1e-05, elementwise_affine=True) (2): LeakyReLU(negative_slope=0.01) ) ) (out_layer): Linear(in_features=100, out_features=100, bias=True) ) (synthesis): SynthesisNetwork( (blocks): ModuleList( (0): SynthesisBlock( (conv2): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) (1): SynthesisBlock( (upsample): ConvTranspose2d(256, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv1): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (conv2): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) (2): SynthesisBlock( (upsample): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv1): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (conv2): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) (3): SynthesisBlock( (upsample): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1)) (conv1): Sequential( (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (conv2): Sequential( (0): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.01) ) (ada_in): AdaIN() ) ) (to_rgb): Conv2d(32, 3, kernel_size=(1, 1), stride=(1, 1)) ) )"
- optimD:
  "Adam ( Parameter Group 0 amsgrad: False betas: (0.5, 0.99) eps: 1e-08 lr: 0.0001 weight_decay: 0 )"
- optimG:
  "Adam ( Parameter Group 0 amsgrad: False betas: (0.5, 0.99) eps: 1e-08 lr: 1e-05 weight_decay: 0 )"
- seed:
  0
- test_loader:
  "<torch.utils.data.dataloader.DataLoader object at 0x7f0dea770c40>"
- train_loader:
  "<torch.utils.data.dataloader.DataLoader object at 0x7f0dea770b50>"

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 7 keys
- D_fake_loss:
  6.096827113314679
- D_loss:
  6.097842981940822
- D_real_loss:
  0.0010158680180259246
- fake_acc:
  0.0026546897072541086
- G_loss:
  0.002642223037822221
- ▶
  Generated images:{} 7 keys
- real_acc:
  0.9989866504543706

This run produced these artifacts as outputs. Total: 3. Learn more

run-16wezq2a-history:v0