| trainer: | |
| target: trainer.TrainerDifIRLPIPS | |
| model: | |
| target: models.unet.UNetModelSwin | |
| ckpt_path: ~ | |
| params: | |
| image_size: 64 | |
| in_channels: 8 | |
| model_channels: 160 | |
| out_channels: 8 | |
| attention_resolutions: [64,32,16,8] | |
| dropout: 0 | |
| channel_mult: [1, 2, 2, 4] | |
| num_res_blocks: [2, 2, 2, 2] | |
| conv_resample: True | |
| dims: 2 | |
| use_fp16: False | |
| num_head_channels: 32 | |
| use_scale_shift_norm: True | |
| resblock_updown: False | |
| swin_depth: 2 | |
| swin_embed_dim: 192 | |
| window_size: 8 | |
| mlp_ratio: 4 | |
| cond_lq: True | |
| lq_size: 512 | |
| diffusion: | |
| target: models.script_util.create_gaussian_diffusion | |
| params: | |
| sf: 1 | |
| schedule_name: exponential | |
| schedule_kwargs: | |
| power: 0.3 | |
| etas_end: 0.99 | |
| steps: 4 | |
| min_noise_level: 0.2 | |
| kappa: 2.0 | |
| weighted_mse: False | |
| predict_type: xstart | |
| timestep_respacing: ~ | |
| scale_factor: 1.0 | |
| normalize_input: True | |
| latent_flag: True | |
| autoencoder: | |
| target: ldm.models.autoencoder.VQModelTorch | |
| ckpt_path: weights/ffhq512_vq_f8_dim8_face.pth | |
| use_fp16: True | |
| params: | |
| embed_dim: 8 | |
| n_embed: 4096 | |
| ddconfig: | |
| double_z: False | |
| z_channels: 8 | |
| resolution: 512 | |
| in_channels: 3 | |
| out_ch: 3 | |
| ch: 64 | |
| ch_mult: | |
| - 1 | |
| - 2 | |
| - 4 | |
| - 8 | |
| num_res_blocks: | |
| - 1 | |
| - 2 | |
| - 3 | |
| - 4 | |
| attn_resolutions: [] | |
| dropout: 0.0 | |
| padding_mode: zeros | |
| data: | |
| train: | |
| type: gfpgan | |
| params: | |
| dir_path: /mnt/sfs-common/zsyue/database/FFHQ/images512x512 | |
| im_exts: png | |
| io_backend: | |
| type: disk | |
| use_hflip: true | |
| mean: [0.5, 0.5, 0.5] | |
| std: [0.5, 0.5, 0.5] | |
| out_size: 512 | |
| blur_kernel_size: 41 | |
| kernel_list: ['iso', 'aniso'] | |
| kernel_prob: [0.5, 0.5] | |
| blur_sigma: [0.1, 15] | |
| downsample_range: [0.8, 32] | |
| noise_range: [0, 20] | |
| jpeg_range: [30, 100] | |
| color_jitter_prob: ~ | |
| color_jitter_pt_prob: ~ | |
| gray_prob: 0.01 | |
| gt_gray: True | |
| need_gt_path: False | |
| val: | |
| type: base | |
| params: | |
| dir_path: testdata/faceir/cropped_faces/lq | |
| transform_type: default | |
| transform_kwargs: | |
| mean: 0.5 | |
| std: 0.5 | |
| im_exts: png | |
| need_path: False | |
| recursive: False | |
| train: | |
| # learning rate | |
| lr: 5e-5 # learning rate | |
| lr_min: 2e-5 | |
| lr_schedule: cosin | |
| warmup_iterations: 5000 | |
| # dataloader | |
| batch: [56, 8] | |
| microbatch: 7 | |
| num_workers: 6 | |
| prefetch_factor: 2 | |
| # optimization settings | |
| weight_decay: 0 | |
| ema_rate: 0.999 | |
| iterations: 400000 # total iterations | |
| # save logging | |
| save_freq: 10000 | |
| log_freq: [200, 2000, 1] # [training loss, training images, val images] | |
| loss_coef: [1.0, 10.0] # [mse, lpips] | |
| local_logging: True # manually save images | |
| tf_logging: False # tensorboard logging | |
| # validation settings | |
| use_ema_val: True | |
| val_freq: ${train.save_freq} | |
| val_y_channel: True | |
| val_resolution: ${model.params.lq_size} | |
| val_padding_mode: reflect | |
| # training setting | |
| use_amp: True # amp training | |
| seed: 123456 # random seed | |
| global_seeding: False | |
| # model compile | |
| compile: | |
| flag: False | |
| mode: reduce-overhead # default, reduce-overhead | |