TimeSformer/configs/SSv2/SLOWFAST_16x8_R50.yaml

TRAIN:
  ENABLE: True
  DATASET: ssv2
  BATCH_SIZE: 16
  EVAL_PERIOD: 5
  CHECKPOINT_PERIOD: 5
  AUTO_RESUME: True
DATA:
  PATH_TO_DATA_DIR: " /path/to/ssv2/annotations/"
  PATH_PREFIX: "/path/to/ssv2/frames/"
  NUM_FRAMES: 64
  SAMPLING_RATE: 2
  TRAIN_JITTER_SCALES: [256, 320]
  TRAIN_CROP_SIZE: 224
  TEST_CROP_SIZE: 256
  INPUT_CHANNEL_NUM: [3, 3]
  INV_UNIFORM_SAMPLE: True
  RANDOM_FLIP: False
  REVERSE_INPUT_CHANNEL: True
SLOWFAST:
  ALPHA: 4
  BETA_INV: 8
  FUSION_CONV_CHANNEL_RATIO: 2
  FUSION_KERNEL_SZ: 7
RESNET:
  SPATIAL_STRIDES: [[1, 1], [2, 2], [2, 2], [2, 2]]
  SPATIAL_DILATIONS: [[1, 1], [1, 1], [1, 1], [1, 1]]
  ZERO_INIT_FINAL_BN: True
  WIDTH_PER_GROUP: 64
  NUM_GROUPS: 1
  DEPTH: 50
  TRANS_FUNC: bottleneck_transform
  STRIDE_1X1: False
  NUM_BLOCK_TEMP_KERNEL: [[3, 3], [4, 4], [6, 6], [3, 3]]
NONLOCAL:
  LOCATION: [[[], []], [[], []], [[], []], [[], []]]
  GROUP: [[1, 1], [1, 1], [1, 1], [1, 1]]
  INSTANTIATION: dot_product
BN:
  USE_PRECISE_STATS: True
  NUM_BATCHES_PRECISE: 200
  NORM_TYPE: sync_batchnorm
  NUM_SYNC_DEVICES: 4
SOLVER:
  BASE_LR: 0.2 #8 nodes
  LR_POLICY: cosine
  MAX_EPOCH: 200
  MOMENTUM: 0.9
  WEIGHT_DECAY: 1e-4
  WARMUP_EPOCHS: 34.0
  WARMUP_START_LR: 0.01
  OPTIMIZING_METHOD: sgd
  #SOLVER:
  #  BASE_LR: 0.03
  #  LR_POLICY: steps_with_relative_lrs
  #  LRS: [1, 0.1, 0.01, 0.001, 0.0001, 0.00001]
  #  STEPS: [0, 14, 18]
  #  MAX_EPOCH: 22
  #  MOMENTUM: 0.9
  #  WEIGHT_DECAY: 1e-6
  #  WARMUP_EPOCHS: 0.19
  #  WARMUP_START_LR: 0.0001
  #  OPTIMIZING_METHOD: sgd
MODEL:
  NUM_CLASSES: 174
  ARCH: slowfast
  LOSS_FUNC: cross_entropy
  DROPOUT_RATE: 0.5
TEST:
  ENABLE: True
  DATASET: ssv2
  BATCH_SIZE: 16
  NUM_ENSEMBLE_VIEWS: 1
  NUM_SPATIAL_CROPS: 1
DATA_LOADER:
  NUM_WORKERS: 4
  PIN_MEMORY: True
NUM_GPUS: 8
NUM_SHARDS: 1
RNG_SEED: 0
OUTPUT_DIR: .
#LOG_MODEL_INFO: False
LOG_MODEL_INFO: True