AMT-G.yaml

exp_name: floloss1e-2_300epoch_bs24_lr1p5e-4
seed: 2023
epochs: 300
distributed: true
lr: 1.5e-4
lr_min: 2e-5
weight_decay: 0.0
resume_state: null
save_dir: work_dir
eval_interval: 1

network:
  name: networks.AMT-G.Model
  params:
    corr_radius: 3
    corr_lvls: 4
    num_flows: 5
data:
  train: 
    name: datasets.vimeo_datasets.Vimeo90K_Train_Dataset
    params: 
      dataset_dir: data/vimeo_triplet
  val:
    name: datasets.vimeo_datasets.Vimeo90K_Test_Dataset
    params: 
      dataset_dir: data/vimeo_triplet
  train_loader:
    batch_size: 24
    num_workers: 12
  val_loader:
    batch_size: 24
    num_workers: 3

logger:
  use_wandb: true  
  resume_id: null

losses:
  - {
    name: losses.loss.CharbonnierLoss,
    nickname: l_rec,
    params: {
      loss_weight: 1.0,
      keys: [imgt_pred, imgt]
    }
  }
  - {
    name: losses.loss.TernaryLoss,
    nickname: l_ter,
    params: {
      loss_weight: 1.0,
      keys: [imgt_pred, imgt]
    }
  }
  - {
    name: losses.loss.MultipleFlowLoss,
    nickname: l_flo,
    params: {
      loss_weight: 0.005,
      keys: [flow0_pred, flow1_pred, flow]
    }
  }