| model: | |
| checkpoint_path: ../../../checkpoints/kny_image_full_style/checkpoint | |
| vqvae_config: | |
| beta: 0.25 | |
| num_embeddings: 50257 | |
| embedding_dim: 128 | |
| autoencoder_config: | |
| z_channels: 512 | |
| channels: 32 | |
| channels_multiplier: | |
| - 2 | |
| - 4 | |
| - 8 | |
| - 8 | |
| num_res_blocks: 1 | |
| attention_resolution: | |
| - 16 | |
| resolution: 128 | |
| dropout: 0.0 | |
| discriminator_config: | |
| num_layers: 3 | |
| filters: 64 | |
| loss_config: | |
| discriminator: | |
| loss: "hinge" | |
| factor: 1.0 | |
| iter_start: 50000000 | |
| weight: 0.8 | |
| vqvae: | |
| codebook_weight: 1.0 | |
| perceptual_weight: 4.0 | |
| perceptual_loss: "style" # "vgg16", "vgg19", "style" | |
| trainer: | |
| batch_size: 32 | |
| n_epochs: 10000 | |
| gen_lr: 8e-5 | |
| disc_lr: 8e-5 | |
| gen_beta_1: 0.5 | |
| gen_beta_2: 0.9 | |
| disc_beta_1: 0.5 | |
| disc_beta_2: 0.9 | |
| gen_clip_norm: 1.0 | |
| disc_clip_norm: 1.0 | |