big-lama/config.yaml

run_title: b18_ffc075_batch8x15
training_model:
  kind: default
  visualize_each_iters: 1000
  concat_mask: true
  store_discr_outputs_for_vis: true
losses:
  l1:
    weight_missing: 0
    weight_known: 10
  perceptual:
    weight: 0
  adversarial:
    kind: r1
    weight: 10
    gp_coef: 0.001
    mask_as_fake_target: true
    allow_scale_mask: true
  feature_matching:
    weight: 100
  resnet_pl:
    weight: 30
    weights_path: ${env:TORCH_HOME}

optimizers:
  generator:
    kind: adam
    lr: 0.001
  discriminator:
    kind: adam
    lr: 0.0001
visualizer:
  key_order:
  - image
  - predicted_image
  - discr_output_fake
  - discr_output_real
  - inpainted
  rescale_keys:
  - discr_output_fake
  - discr_output_real
  kind: directory
  outdir: /group-volume/User-Driven-Content-Generation/r.suvorov/inpainting/experiments/r.suvorov_2021-04-30_14-41-12_train_simple_pix2pix2_gap_sdpl_novgg_large_b18_ffc075_batch8x15/samples
location:
  data_root_dir: /group-volume/User-Driven-Content-Generation/datasets/inpainting_data_root_large
  out_root_dir: /group-volume/User-Driven-Content-Generation/${env:USER}/inpainting/experiments
  tb_dir: /group-volume/User-Driven-Content-Generation/${env:USER}/inpainting/tb_logs
data:
  batch_size: 15
  val_batch_size: 2
  num_workers: 3
  train:
    indir: ${location.data_root_dir}/train
    out_size: 256
    mask_gen_kwargs:
      irregular_proba: 1
      irregular_kwargs:
        max_angle: 4
        max_len: 200
        max_width: 100
        max_times: 5
        min_times: 1
      box_proba: 1
      box_kwargs:
        margin: 10
        bbox_min_size: 30
        bbox_max_size: 150
        max_times: 3
        min_times: 1
      segm_proba: 0
      segm_kwargs:
        confidence_threshold: 0.5
        max_object_area: 0.5
        min_mask_area: 0.07
        downsample_levels: 6
        num_variants_per_mask: 1
        rigidness_mode: 1
        max_foreground_coverage: 0.3
        max_foreground_intersection: 0.7
        max_mask_intersection: 0.1
        max_hidden_area: 0.1
        max_scale_change: 0.25
        horizontal_flip: true
        max_vertical_shift: 0.2
        position_shuffle: true
    transform_variant: distortions
    dataloader_kwargs:
      batch_size: ${data.batch_size}
      shuffle: true
      num_workers: ${data.num_workers}
  val:
    indir: ${location.data_root_dir}/val
    img_suffix: .png
    dataloader_kwargs:
      batch_size: ${data.val_batch_size}
      shuffle: false
      num_workers: ${data.num_workers}
  visual_test:
    indir: ${location.data_root_dir}/korean_test
    img_suffix: _input.png
    pad_out_to_modulo: 32
    dataloader_kwargs:
      batch_size: 1
      shuffle: false
      num_workers: ${data.num_workers}
generator:
  kind: ffc_resnet
  input_nc: 4
  output_nc: 3
  ngf: 64
  n_downsampling: 3
  n_blocks: 18
  add_out_act: sigmoid
  init_conv_kwargs:
    ratio_gin: 0
    ratio_gout: 0
    enable_lfu: false
  downsample_conv_kwargs:
    ratio_gin: ${generator.init_conv_kwargs.ratio_gout}
    ratio_gout: ${generator.downsample_conv_kwargs.ratio_gin}
    enable_lfu: false
  resnet_conv_kwargs:
    ratio_gin: 0.75
    ratio_gout: ${generator.resnet_conv_kwargs.ratio_gin}
    enable_lfu: false
discriminator:
  kind: pix2pixhd_nlayer
  input_nc: 3
  ndf: 64
  n_layers: 4
evaluator:
  kind: default
  inpainted_key: inpainted
  integral_kind: ssim_fid100_f1
trainer:
  kwargs:
    gpus: -1
    accelerator: ddp
    max_epochs: 200
    gradient_clip_val: 1
    log_gpu_memory: None
    limit_train_batches: 25000
    val_check_interval: ${trainer.kwargs.limit_train_batches}
    log_every_n_steps: 1000
    precision: 32
    terminate_on_nan: false
    check_val_every_n_epoch: 1
    num_sanity_val_steps: 8
    limit_val_batches: 1000
    replace_sampler_ddp: false
  checkpoint_kwargs:
    verbose: true
    save_top_k: 5
    save_last: true
    period: 1
    monitor: val_ssim_fid100_f1_total_mean
    mode: max