model: base_learning_rate: 4.5e-06 target: taming.models.local_sampler.LocalSamplerDualCodebookPE params: cond_stage_key: coord holistic_config: target: taming.models.vqgan.VQCirModel params: ckpt_path: embed_dim: 256 n_embed: 1024 ddconfig: double_z: false z_channels: 256 resolution: 256 in_channels: 3 out_ch: 3 ch: 128 ch_mult: - 1 - 1 - 2 - 2 - 4 num_res_blocks: 2 attn_resolutions: - 16 dropout: 0.0 lossconfig: target: taming.modules.losses.DummyLoss transformer_config: target: taming.modules.transformer.mingpt.GPT params: vocab_size: 1024 block_size: 402 n_layer: 24 n_head: 16 n_embd: 1024 first_stage_config: target: taming.models.vqgan.VQModel params: ckpt_path: embed_dim: 256 n_embed: 1024 ddconfig: double_z: false z_channels: 256 resolution: 256 in_channels: 3 out_ch: 3 ch: 128 ch_mult: - 1 - 1 - 2 - 2 - 4 num_res_blocks: 2 attn_resolutions: - 16 dropout: 0.0 lossconfig: target: taming.modules.losses.DummyLoss cond_stage_config: target: taming.modules.misc.coord.CoordStage params: n_embed: 1024 down_factor: 16 data: target: main.DataModuleFromConfig params: batch_size: 24 num_workers: 16 train: target: taming.data.custom.CustomTrain params: training_images_list_file: /home/chenzhaoxi/imgs/train_outdoor.txt size: 256 coord: true random_crop: true holistic: 128 validation: target: taming.data.custom.CustomTest params: test_images_list_file: /home/chenzhaoxi/imgs/test.txt size: 256 coord: true random_crop: true holistic: 128