mmaudio/ext/synchformer/divided_224_16x4.yaml

TRAIN:
  ENABLE: True
  DATASET: Ssv2
  BATCH_SIZE: 32
  EVAL_PERIOD: 5
  CHECKPOINT_PERIOD: 5
  AUTO_RESUME: True
  CHECKPOINT_EPOCH_RESET: True
  CHECKPOINT_FILE_PATH: /checkpoint/fmetze/neurips_sota/40944587/checkpoints/checkpoint_epoch_00035.pyth
DATA:
  NUM_FRAMES: 16
  SAMPLING_RATE: 4
  TRAIN_JITTER_SCALES: [256, 320]
  TRAIN_CROP_SIZE: 224
  TEST_CROP_SIZE: 224
  INPUT_CHANNEL_NUM: [3]
  MEAN: [0.5, 0.5, 0.5]
  STD: [0.5, 0.5, 0.5]
  PATH_TO_DATA_DIR: /private/home/mandelapatrick/slowfast/data/ssv2
  PATH_PREFIX: /datasets01/SomethingV2/092720/20bn-something-something-v2-frames
  INV_UNIFORM_SAMPLE: True
  RANDOM_FLIP: False
  REVERSE_INPUT_CHANNEL: True
  USE_RAND_AUGMENT: True
  RE_PROB: 0.0
  USE_REPEATED_AUG: False
  USE_RANDOM_RESIZE_CROPS: False
  COLORJITTER: False
  GRAYSCALE: False
  GAUSSIAN: False
SOLVER:
  BASE_LR: 1e-4
  LR_POLICY: steps_with_relative_lrs
  LRS: [1, 0.1, 0.01]
  STEPS: [0, 20, 30]
  MAX_EPOCH: 35
  MOMENTUM: 0.9
  WEIGHT_DECAY: 5e-2
  WARMUP_EPOCHS: 0.0
  OPTIMIZING_METHOD: adamw
  USE_MIXED_PRECISION: True
  SMOOTHING: 0.2
SLOWFAST:
  ALPHA: 8
VIT:
  PATCH_SIZE: 16
  PATCH_SIZE_TEMP: 2
  CHANNELS: 3
  EMBED_DIM: 768
  DEPTH: 12
  NUM_HEADS: 12
  MLP_RATIO: 4
  QKV_BIAS: True
  VIDEO_INPUT: True
  TEMPORAL_RESOLUTION: 8
  USE_MLP: True
  DROP: 0.0
  POS_DROPOUT: 0.0
  DROP_PATH: 0.2
  IM_PRETRAINED: True
  HEAD_DROPOUT: 0.0
  HEAD_ACT: tanh
  PRETRAINED_WEIGHTS: vit_1k
  ATTN_LAYER: divided
MODEL:
  NUM_CLASSES: 174
  ARCH: slow
  MODEL_NAME: VisionTransformer
  LOSS_FUNC: cross_entropy
TEST:
  ENABLE: True
  DATASET: Ssv2
  BATCH_SIZE: 64
  NUM_ENSEMBLE_VIEWS: 1
  NUM_SPATIAL_CROPS: 3
DATA_LOADER:
  NUM_WORKERS: 4
  PIN_MEMORY: True
NUM_GPUS: 8
NUM_SHARDS: 4
RNG_SEED: 0
OUTPUT_DIR: .
TENSORBOARD:
  ENABLE: True