ResNet50.yaml

# global configs
Global:
  checkpoints: null
  pretrained_model: null
  output_dir: "./output/"
  device: "gpu"
  class_num: 1000
  save_interval: 1
  eval_during_train: True
  eval_interval: 1
  epochs: 120
  print_batch_step: 10
  use_visualdl: False
  image_shape: [3, 224, 224]
  infer_imgs:

# model architecture
Arch:
  name: "ResNet50"

# loss function config for traing/eval process
Loss:
  Train:
    - CELoss:
        weight: 1.0
  Eval:
    - CELoss:
        weight: 1.0


Optimizer:
  name: Momentum
  momentum: 0.9
  lr:
    name: Piecewise
    learning_rate: 0.1
    decay_epochs: [30, 60, 90]
    values: [0.1, 0.01, 0.001, 0.0001]
  regularizer:
    name: 'L2'
    coeff: 0.0001


# data loader for train and eval
DataLoader:
  Train:
    # Dataset:
    # Sampler:
    # Loader:
    batch_size: 256
    num_workers: 4
    file_list: "./dataset/ILSVRC2012/train_list.txt"
    data_dir: "./dataset/ILSVRC2012/"
    shuffle_seed: 0
    transforms:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - RandCropImage:
            size: 224
        - RandFlipImage:
            flip_code: 1
        - NormalizeImage:
            scale: 1./255.
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - ToCHWImage:
  Eval:
    # TOTO: modify to the latest trainer
    # Dataset:
    # Sampler:
    # Loader:
    batch_size: 128
    num_workers: 4
    file_list: "./dataset/ILSVRC2012/val_list.txt"
    data_dir: "./dataset/ILSVRC2012/"
    shuffle_seed: 0
    transforms:
        - DecodeImage:
            to_rgb: True
            channel_first: False
        - ResizeImage:
            resize_short: 256
        - CropImage:
            size: 224
        - NormalizeImage:
            scale: 1.0/255.0
            mean: [0.485, 0.456, 0.406]
            std: [0.229, 0.224, 0.225]
            order: ''
        - ToCHWImage:

Metric:
    Train:
    - Topk:
        k: [1, 5]
    Eval:
    - Topk:
        k: [1, 5]