cifar_regnet.yaml

DESC:
  Example CIFAR sweep 2 of 3 (uses lr and wd found by cifar_optim sweep).
  This sweep searches for a good RegNet-125MF model on cifar (same flops as R56).
  The purpose of this sweep is to show how to optimize REGNET parameters.
NAME: cifar/cifar_regnet
SETUP:
  # Number of configs to sample
  NUM_CONFIGS: 32
  # SAMPLER for RegNet
  SAMPLERS:
    REGNET:
      TYPE: regnet_sampler
      DEPTH: [6, 16]
      GROUP_W: [1, 32]
  # CONSTRAINTS for complexity (roughly based on R-56)
  CONSTRAINTS:
    CX:
      FLOPS: [0.12e+9, 0.13e+9]
      PARAMS: [0, 2.0e+6]
      ACTS: [0, 1.0e+6]
    REGNET:
      NUM_STAGES: [2, 2]
  # BASE_CFG is R-56 with large batch size and stronger augmentation
  BASE_CFG:
    MODEL:
      TYPE: regnet
      NUM_CLASSES: 10
    REGNET:
      STEM_TYPE: res_stem_cifar
      SE_ON: True
      STEM_W: 16
    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_METRIC_VALUES: True
  PLOT_COMPLEXITY_VALUES: True
  PLOT_CURVES_BEST: 3
  PLOT_CURVES_WORST: 0
  PLOT_MODELS_BEST: 8
  PLOT_MODELS_WORST: 0
  METRICS: [regnet_depth, regnet_w0, regnet_wa, regnet_wm, regnet_gw]
  COMPLEXITY: [flops, params, acts, memory, epoch_fw_bw, epoch_time]
  PRE_FILTERS: {done: [0, 1, 1]}