一、tf.losses.mean_squared_error函數函數
tf.losses.mean_squared_error( labels, predictions, weights=1.0, scope=None, loss_collection=tf.GraphKeys.LOSSES, reduction=Reduction.SUM_BY_NONZERO_WEIGHTS )
返回值:spa
加權損失浮動Tensor.若是reduction是NONE,則它的形狀與labels相同;不然,它是標量.code