swin-v2-msi/config.json

AMP_ENABLE: true
AMP_OPT_LEVEL: ''
AUG:
  AUTO_AUGMENT: rand-m9-mstd0.5-inc1
  COLOR_JITTER: 0.4
  CUTMIX: 1.0
  CUTMIX_MINMAX: null
  MIXUP: 0.8
  MIXUP_MODE: batch
  MIXUP_PROB: 1.0
  MIXUP_SWITCH_PROB: 0.5
  RECOUNT: 1
  REMODE: pixel
  REPROB: 0.25
BASE:
- ''
DATA:
  BANDS: all
  BATCH_SIZE: 64
  CACHE_MODE: part
  CHANNELS: 12
  DATASET: imagenet
  DATA_PATH: /workspace/storage/data/hydro/images/
  IMG_SIZE: 256
  INTERPOLATION: bicubic
  MASK_PATCH_SIZE: 32
  MASK_RATIO: 0.6
  MEAN:
  - 340.76769064
  - 429.9430203
  - 614.21682446
  - 590.23569706
  - 950.68368468
  - 1792.46290469
  - 2075.46795189
  - 2218.94553375
  - 2266.46036911
  - 2246.0605464
  - 1594.42694882
  - 1009.32729131
  NUM_WORKERS: 8
  PIN_MEMORY: true
  STD:
  - 554.81258967
  - 572.41639287
  - 582.87945694
  - 675.88746967
  - 729.89827633
  - 1096.01480586
  - 1273.45393088
  - 1365.45589904
  - 1356.13789355
  - 1302.3292881
  - 1079.19066363
  - 818.86747235
  ZIP_MODE: false
ENABLE_AMP: true
EVAL_MODE: false
FUSED_LAYERNORM: false
FUSED_WINDOW_PROCESS: false
LOCAL_RANK: 0
MODEL:
  DROP_PATH_RATE: 0.1
  DROP_RATE: 0.0
  IN_CHANS: 3
  LABEL_SMOOTHING: 0.1
  NAME: hydro_simmim_pretrain
  NUM_CLASSES: 1000
  PRETRAINED: Swin-Transformer/output/hydro_simmim_pretrain1/hydro_simmim_pretrain_swinv2_base_img256_window16_800ep/ckpt_epoch_670.pth
  RESUME: ''
  SIMMIM:
    NORM_TARGET:
      ENABLE: true
      PATCH_SIZE: 47
  SWIN:
    APE: false
    DEPTHS:
    - 2
    - 2
    - 6
    - 2
    EMBED_DIM: 96
    IN_CHANS: 3
    MLP_RATIO: 4.0
    NUM_HEADS:
    - 3
    - 6
    - 12
    - 24
    PATCH_NORM: true
    PATCH_SIZE: 4
    QKV_BIAS: true
    QK_SCALE: null
    WINDOW_SIZE: 7
  SWINV2:
    APE: false
    DEPTHS:
    - 2
    - 2
    - 18
    - 2
    EMBED_DIM: 128
    IN_CHANS: 12
    MLP_RATIO: 4.0
    NUM_HEADS:
    - 4
    - 8
    - 16
    - 32
    PATCH_NORM: true
    PATCH_SIZE: 4
    PRETRAINED_WINDOW_SIZES:
    - 0
    - 0
    - 0
    - 0
    QKV_BIAS: true
    WINDOW_SIZE: 16
  SWIN_MLP:
    APE: false
    DEPTHS:
    - 2
    - 2
    - 6
    - 2
    EMBED_DIM: 96
    IN_CHANS: 3
    MLP_RATIO: 4.0
    NUM_HEADS:
    - 3
    - 6
    - 12
    - 24
    PATCH_NORM: true
    PATCH_SIZE: 4
    WINDOW_SIZE: 7
  SWIN_MOE:
    APE: false
    AUX_LOSS_WEIGHT: 0.01
    CAPACITY_FACTOR: 1.25
    COSINE_ROUTER: false
    COSINE_ROUTER_DIM: 256
    COSINE_ROUTER_INIT_T: 0.5
    DEPTHS:
    - 2
    - 2
    - 6
    - 2
    EMBED_DIM: 96
    GATE_NOISE: 1.0
    INIT_STD: 0.02
    IN_CHANS: 3
    IS_GSHARD_LOSS: false
    MLP_FC2_BIAS: true
    MLP_RATIO: 4.0
    MOE_BLOCKS:
    - - -1
    - - -1
    - - -1
    - - -1
    MOE_DROP: 0.0
    NORMALIZE_GATE: false
    NUM_HEADS:
    - 3
    - 6
    - 12
    - 24
    NUM_LOCAL_EXPERTS: 1
    PATCH_NORM: true
    PATCH_SIZE: 4
    PRETRAINED_WINDOW_SIZES:
    - 0
    - 0
    - 0
    - 0
    QKV_BIAS: true
    QK_SCALE: null
    TOP_VALUE: 1
    USE_BPR: true
    WINDOW_SIZE: 7
  TYPE: swinv2
OUTPUT: output/hydro_simmim_pretrain/hydro_simmim_pretrain_swinv2_base_img256_window16_800ep
PRINT_FREQ: 100
SAVE_FREQ: 5
SEED: 0
TAG: hydro_simmim_pretrain_swinv2_base_img256_window16_800ep
TEST:
  CROP: true
  SEQUENTIAL: false
  SHUFFLE: false
THROUGHPUT_MODE: false
TRAIN:
  ACCUMULATION_STEPS: 1
  AUTO_RESUME: true
  BASE_LR: 2.5e-05
  CLIP_GRAD: 5.0
  EPOCHS: 800
  LAYER_DECAY: 1.0
  LR_SCHEDULER:
    DECAY_EPOCHS: 30
    DECAY_RATE: 0.1
    GAMMA: 0.1
    MULTISTEPS:
    - 700
    NAME: multistep
    WARMUP_PREFIX: true
  MIN_LR: 1.25e-06
  MOE:
    SAVE_MASTER: false
  OPTIMIZER:
    BETAS:
    - 0.9
    - 0.999
    EPS: 1.0e-08
    MOMENTUM: 0.9
    NAME: adamw
  START_EPOCH: 0
  USE_CHECKPOINT: false
  WARMUP_EPOCHS: 10
  WARMUP_LR: 1.25e-07
  WEIGHT_DECAY: 0.05