X3D_M_256e.yaml

TRAIN:
  # ENABLE: False # default True
  DATASET: kinetics
  BATCH_SIZE: 128
  EVAL_PERIOD: 10
  CHECKPOINT_PERIOD: 10
  AUTO_RESUME: True
X3D:
  WIDTH_FACTOR: 2.0
  DEPTH_FACTOR: 2.2
  BOTTLENECK_FACTOR: 2.25
  DIM_C5: 2048
  DIM_C1: 12
TEST:
  ENABLE: True
  DATASET: kinetics
  BATCH_SIZE: 64
  # CHECKPOINT_FILE_PATH: 'x3d_m.pyth' # 76.21% top1 30-view accuracy to download from the model zoo (optional).
  # NUM_SPATIAL_CROPS: 1
  NUM_SPATIAL_CROPS: 3
DATA:
  NUM_FRAMES: 16
  SAMPLING_RATE: 5
  TRAIN_JITTER_SCALES: [256, 320]
  TRAIN_CROP_SIZE: 224
  # TEST_CROP_SIZE: 224 # use if TEST.NUM_SPATIAL_CROPS: 1
  TEST_CROP_SIZE: 256 # use if TEST.NUM_SPATIAL_CROPS: 3
  INPUT_CHANNEL_NUM: [3]
  DECODING_BACKEND: torchvision
RESNET:
  ZERO_INIT_FINAL_BN: True
  TRANS_FUNC: x3d_transform
  STRIDE_1X1: False
BN:
  USE_PRECISE_STATS: True
  NUM_BATCHES_PRECISE: 200
  WEIGHT_DECAY: 0.0
SOLVER:
  BASE_LR: 0.1 # 1 machine
  BASE_LR_SCALE_NUM_SHARDS: True
  LR_POLICY: cosine
  MAX_EPOCH: 256 #300
  WEIGHT_DECAY: 5e-5
  WARMUP_EPOCHS: 35.0
  WARMUP_START_LR: 0.01
  OPTIMIZING_METHOD: sgd
MODEL:
  NUM_CLASSES: 400
  ARCH: x3d
  MODEL_NAME: X3D
  LOSS_FUNC: cross_entropy
  DROPOUT_RATE: 0.5
DATA_LOADER:
  NUM_WORKERS: 8
  PIN_MEMORY: True
NUM_GPUS: 8
RNG_SEED: 0
OUTPUT_DIR: .