CSC (class-specific context) CoOp/CoCoOp in "base-new" and "cross-dataset".

[galaxyzen]

CSC (class-specific context) will generate context for every class:

  # CoOp.py
  # random initialization
  if cfg.TRAINER.COOP.CSC:
      print("Initializing class-specific contexts")
      ctx_vectors = torch.empty(n_cls, n_ctx, ctx_dim, dtype=dtype)

1. If I train the model with the setting cfg.TRAINER.COOP.CSC on a dataset which has 10 classes, can I eval this model on another dataset which may have 11 classes? I think the setting cfg.TRAINER.COOP.CSC causes the model is specific to n_cls .
2. If the cfg.TRAINER.COOP.CSC is turned on, I think the "base-new" experiment can't be conducted as well.