1、tf.losses.mean_squared_error函数
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:
加权损失浮动Tensor.如果reduction是NONE,则它的形状与labels相同;否则,它是标量.
原文:https://www.cnblogs.com/xiaoniu-666/p/11102805.html