model_config {
  # Model Architecture can be chosen from:
  # ['resnet', 'vgg', 'googlenet', 'alexnet']
  arch: "resnet"
  # for resnet --> n_layers can be [10, 18, 50]
  # for vgg --> n_layers can be [16, 19]
  n_layers: 18
  use_batch_norm: True
  use_bias: False
  all_projections: False
  use_pooling: True
  use_imagenet_head: True
  resize_interpolation_method: BICUBIC
  # if you want to use the pretrained model,
  # image size should be "3,224,224"
  # otherwise, it can be "3, X, Y", where X,Y >= 16
  input_image_size: "3,224,224"
}
train_config {
  train_dataset_path: "/workspace/tao-experiments/train"
  val_dataset_path: "/workspace/tao-experiments/val"
  pretrained_model_path: "/workspace/tao-experiments/pretrained/resnet_18.hdf5"
  # Only ['sgd', 'adam'] are supported for optimizer
  optimizer {
      sgd {
      lr: 0.01
      decay: 0.0
      momentum: 0.9
      nesterov: False
      }
  }
  batch_size_per_gpu: 8
  n_epochs: 100
  # Number of CPU cores for loading data
  n_workers: 4
  # regularizer
  reg_config {
      # regularizer type can be "L1", "L2" or "None".
      type: "L2"
      # if the type is not "None",
      # scope can be either "Conv2D" or "Dense" or both.
      scope: "Conv2D,Dense"
      # 0 < weight decay < 1
      weight_decay: 0.000015
  }
  # learning_rate
  lr_config {
      cosine {
      learning_rate: 0.04
      soft_start: 0.0
      }
  }
  enable_random_crop: True
  enable_center_crop: True
  enable_color_augmentation: True
  mixup_alpha: 0.2
  label_smoothing: 0.1
  preprocess_mode: "caffe"
  image_mean {
    key: 'b'
    value: 103.9
  }
  image_mean {
    key: 'g'
    value: 116.8
  }
  image_mean {
    key: 'r'
    value: 123.7
  }
}
eval_config {
  eval_dataset_path: "/workspace/tao-experiments/test"
  model_path: "/workspace/tao-experiments/results/weights/resnet_100.tlt"
  top_k: 3
  batch_size: 8
  n_workers: 4
  enable_center_crop: True
}