model_config {
  arch: "resnet"
  n_layers: 18
  use_bias: True
  use_batch_norm: True
  all_projections: True
  use_pooling: False
  freeze_bn: False
  freeze_blocks: 0
  freeze_blocks: 1
  input_image_size: "3,224,224"
}
train_config {
  train_dataset_path: "/data/car_make_dataset/training_set"
  val_dataset_path: "/data/car_make_dataset/val_set"
  pretrained_model_path: "/workspace/tao-experiments/pretrained_car_make_model/vehiclemakenet_vunpruned_v1.0/resnet18_vehiclemakenet.tlt"
  # Only ['sgd', 'adam'] are supported for optimizer
  optimizer {
      sgd {
      lr: 0.01
      decay: 0.0
      momentum: 0.9
      nesterov: False
      }
  }
  batch_size_per_gpu: 32
  n_epochs: 3
  # Number of CPU cores for loading data
  n_workers: 16
  # 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: 0.00005
  }

  # learning_rate
  lr_config {
      cosine {
      learning_rate: 0.04
      soft_start: 0.0
      }
  }

  preprocess_mode: "torch"

#  enable_random_crop: True
#  enable_center_crop: True
#  enable_color_augmentation: True
}
#eval_config {
#  eval_dataset_path: "/path/to/your/test/data"
#  model_path: "/workspace/tao-experiments/classification_make/weights/resnet_080.tlt"
#  top_k: 3
#  batch_size: 256
#  n_workers: 8
#  enable_center_crop: True
#}