Do you train the whole network when you apply QAM in STCN?

[zhouweii234]

Do you train the whole network when you apply QAM in STCN? or you just load the weights of the initial model (trained without QAM) and load the parameters of QAM trained in QDMN, like what you do in Table 4.

[yongliu20]

We trained the whole network.