Hello. Apologies for the confusion caused by the keyboard issue earlier.
Thank you for your excellent work. In the implementation of the TwoStreamBatchSampler(Sampler) class, you mentioned, "An 'epoch' is one iteration through the primary indices. During the epoch, the secondary indices are iterated through as many times as needed."
However, the original paper's implementation involves a complete traversal of the unlabeled data once. Does this mean that the code implementation deviates from the original paper?
Hello. Apologies for the confusion caused by the keyboard issue earlier.
Thank you for your excellent work. In the implementation of the TwoStreamBatchSampler(Sampler) class, you mentioned, "An 'epoch' is one iteration through the primary indices. During the epoch, the secondary indices are iterated through as many times as needed."
However, the original paper's implementation involves a complete traversal of the unlabeled data once. Does this mean that the code implementation deviates from the original paper?