yaoyao-liu / meta-transfer-learning

Whether the meta-validation data classes are consistent with the meta-train data classes in one task? For meta-validation during meta-train, the meta_lr is 0 which means ss_weights and fc_weights will not be updated. Whether the updates in fast_fc_weights will not influence fc_weights when the meta_lr is 0 ?
Looking forward to your reply,thanks!

Answer to Q1: Meta-train, meta-val, and meta-test set share no common class, i.e., the class occurs in meta-train won't occur in meta-val and meta-test.

Answer to Q2: During base-learning, the
temporary fc weights are detached from the parameter list so the updates won't be stored.

meta-transfer-learning/pytorch/models/mtl.py

Line 98 in 2fd01a2

    
           fast_weights = list(map(lambda p: p[1] - self.update_lr * p[0], zip(grad, self.base_learner.parameters())))

Thank you very much！

Question about meta-validation during meta-train