cifar_optim.yaml

DESC:
  Example CIFAR sweep 1 of 3 (find lr and wd for cifar_regnet and cifar_best sweeps).
  Tunes the learning rate (lr) and weight decay (wd) for ResNet-56 at 50 epochs.
  The purpose of this sweep is to show how to optimize OPTIM parameters.
NAME: cifar/cifar_optim
SETUP:
  # Number of configs to sample
  NUM_CONFIGS: 64
  # SAMPLERS for optimization parameters
  SAMPLERS:
    OPTIM.BASE_LR:
      TYPE: float_sampler
      RAND_TYPE: log_uniform
      RANGE: [0.25, 5.0]
      QUANTIZE: 1.0e-10
    OPTIM.WEIGHT_DECAY:
      TYPE: float_sampler
      RAND_TYPE: log_uniform
      RANGE: [5.0e-5, 1.0e-3]
      QUANTIZE: 1.0e-10
  # BASE_CFG is R-56 with large batch size and stronger augmentation
  BASE_CFG:
    MODEL:
      TYPE: anynet
      NUM_CLASSES: 10
    ANYNET:
      STEM_TYPE: res_stem_cifar
      STEM_W: 16
      BLOCK_TYPE: res_basic_block
      DEPTHS: [9, 9, 9]
      WIDTHS: [16, 32, 64]
      STRIDES: [1, 2, 2]
    OPTIM:
      BASE_LR: 1.0
      LR_POLICY: cos
      MAX_EPOCH: 50
      MOMENTUM: 0.9
      NESTEROV: True
      WARMUP_EPOCHS: 5
      WEIGHT_DECAY: 0.0005
      EMA_ALPHA: 0.00025
      EMA_UPDATE_PERIOD: 32
    BN:
      USE_CUSTOM_WEIGHT_DECAY: True
    TRAIN:
      DATASET: cifar10
      SPLIT: train
      BATCH_SIZE: 1024
      IM_SIZE: 32
      MIXED_PRECISION: True
      LABEL_SMOOTHING: 0.1
      MIXUP_ALPHA: 0.5
    TEST:
      DATASET: cifar10
      SPLIT: test
      BATCH_SIZE: 1000
      IM_SIZE: 32
    NUM_GPUS: 1
    DATA_LOADER:
      NUM_WORKERS: 4
    LOG_PERIOD: 25
    VERBOSE: False
# Launch config options
LAUNCH:
  PARTITION: devlab
  NUM_GPUS: 1
  PARALLEL_JOBS: 32
  TIME_LIMIT: 60
# Analyze config options
ANALYZE:
  PLOT_CURVES_BEST: 3
  PLOT_METRIC_VALUES: True
  PLOT_COMPLEXITY_VALUES: True
  METRICS: [lr, wd, lr_wd]
  COMPLEXITY: [flops, params, acts, memory, epoch_fw_bw, epoch_time]
  PRE_FILTERS: {done: [1, 1, 1]}