| # Copyright (C) 2017 NVIDIA Corporation. All rights reserved. | |
| # Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). | |
| # logger options | |
| image_save_iter: 1000 # How often do you want to save output images during training | |
| image_display_iter: 10 # How often do you want to display output images during training | |
| display_size: 8 # How many images do you want to display each time | |
| snapshot_save_iter: 10000 # How often do you want to save trained models | |
| log_iter: 1 # How often do you want to log the training stats | |
| # optimization options | |
| max_iter: 1000000 # maximum number of training iterations | |
| batch_size: 1 # batch size | |
| weight_decay: 0.0001 # weight decay | |
| beta1: 0.5 # Adam parameter | |
| beta2: 0.999 # Adam parameter | |
| init: kaiming # initialization [gaussian/kaiming/xavier/orthogonal] | |
| lr: 0.0001 # initial learning rate | |
| lr_policy: step # learning rate scheduler | |
| step_size: 100000 # how often to decay learning rate | |
| gamma: 0.5 # how much to decay learning rate | |
| gan_w: 1 # weight of adversarial loss | |
| recon_x_w: 10 # weight of image reconstruction loss | |
| recon_h_w: 0 # weight of hidden reconstruction loss | |
| recon_kl_w: 0.01 # weight of KL loss for reconstruction | |
| recon_x_cyc_w: 10 # weight of cycle consistency loss | |
| recon_kl_cyc_w: 0.01 # weight of KL loss for cycle consistency | |
| vgg_w: 0 # weight of domain-invariant perceptual loss | |
| # model options | |
| gen: | |
| dim: 64 # number of filters in the bottommost layer | |
| activ: relu # activation function [relu/lrelu/prelu/selu/tanh] | |
| n_downsample: 2 # number of downsampling layers in content encoder | |
| n_res: 4 # number of residual blocks in content encoder/decoder | |
| pad_type: reflect # padding type [zero/reflect] | |
| dis: | |
| dim: 64 # number of filters in the bottommost layer | |
| norm: none # normalization layer [none/bn/in/ln] | |
| activ: lrelu # activation function [relu/lrelu/prelu/selu/tanh] | |
| n_layer: 4 # number of layers in D | |
| gan_type: lsgan # GAN loss [lsgan/nsgan] | |
| num_scales: 3 # number of scales | |
| pad_type: reflect # padding type [zero/reflect] | |
| # data options | |
| input_dim_a: 3 # number of image channels [1/3] | |
| input_dim_b: 3 # number of image channels [1/3] | |
| num_workers: 8 # number of data loading threads | |
| new_size: 256 # first resize the shortest image side to this size | |
| crop_image_height: 256 # random crop image of this height | |
| crop_image_width: 256 # random crop image of this width | |
| data_root: ./datasets/lol/ # dataset folder location |