| model: | |
| base_learning_rate: 4.5e-05 | |
| target: taming.models.vqgan.VQModel | |
| params: | |
| image_key: threshold | |
| ckpt_path: | |
| embed_dim: 256 | |
| n_embed: 512 | |
| ddconfig: | |
| double_z: false | |
| z_channels: 256 | |
| resolution: 256 | |
| in_channels: 1 | |
| out_ch: 1 | |
| ch: 128 | |
| ch_mult: | |
| - 1 | |
| - 1 | |
| - 2 | |
| - 2 | |
| - 4 | |
| num_res_blocks: 2 | |
| attn_resolutions: | |
| - 16 | |
| dropout: 0.0 | |
| lossconfig: | |
| target: taming.modules.losses.vqperceptual.VQLPIPSWithDiscriminator | |
| params: | |
| disc_conditional: false | |
| disc_in_channels: 1 | |
| disc_start: 100000 | |
| disc_weight: 0.2 | |
| codebook_weight: 1.0 |