common:
  dataset: NTU 
  batch_size: 6
  test_batch_size: 6
  num_workers: 6
  learning_rate: 0.01
  learning_rate_min: 0.00001
  momentum: 0.9
  weight_decay: 0.0003
  init_epochs: 0
  epochs: 100
  optim: SGD
  scheduler:
    name: cosin                     # Represent decayed learning rate with the cosine schedule
    warm_up_epochs: 3 
  loss:
    name: CE                        # cross entropy loss function
    labelsmooth: True
  MultiLoss: True                   # Enable multi-loss training strategy.
  loss_lamdb: [ 1, 0.5, 0.5, 0.5 ]  # The loss weight coefficient assigned for each sub-branch.
  distill: 1.                       # The loss weight coefficient assigned for distillation task.

model:
  Network: I3DWTrans                # I3DWTrans represent unimodal training, set FusionNet for multi-modal fusion training.
  sample_duration: 64               # Sampled frames in a video.
  sample_size: 224                  # The image is croped into 224x224.
  grad_clip: 5.
  SYNC_BN: 1                        # Utilize SyncBatchNorm.
  w: 10                             # Sliding window size.
  temper: 0.5                       # Distillation temperature setting.
  recoupling: True                  # Enable recoupling strategy during training.
  knn_attention: 0.7                # Hyperparameter used in k-NN attention: selecting Top-70% tokens.
  sharpness: True                   # Enable sharpness for each sub-branch's output.
  temp: [ 0.04, 0.07 ]              # Temperature parameter follows a cosine schedule from 0.04 to 0.07 during the training.
  frp: True                         # Enable FRP module.
  SEHeads: 1                        # Number of heads used in RCM module.
  N: 6                              # Number of Transformer blochs configured for each sub-branch.

dataset:
  type: M                           # M: RGB modality, K: Depth modality.
  flip: 0.5                         # Horizontal flip.
  rotated: 0.5                      # Horizontal rotation
  angle: (-10, 10)                  # Rotation angle
  Blur: False                       # Enable random blur operation for each video frame.
  resize: (320, 240)                # The input is spatially resized to 320x240 for NTU dataset.
  crop_size: 224                
  low_frames: 16                    # Number of frames sampled for small Transformer.       
  media_frames: 32                  # Number of frames sampled for medium Transformer.  
  high_frames: 48                   # Number of frames sampled for large Transformer.

bash run.sh tools/train.py config/NTU.yml 0,1,2,3,4,5,6,7 8

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --master_port=1234 train.py --config config/NTU.yml --nprocs 8  

bash run.sh tools/fusion.py config/NTU.yml 0,1,2,3,4,5,6,7 8

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --master_port=1234 fusion.py --config config/NTU.yml --nprocs 8  

CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 --master_port=1234 train.py --config config/NTU.yml --nprocs 1 --eval_only --resume /path/to/model_best.pth.tar