增加交叉熵损失而不是减少
有没有办法翻转横向渗透损失的效果？
我有一个语言模型，我想以不会生成特定文本的方式训练模型。因此，我有两个损失，一个我想减少（loss1），另一个我想增加（loss2）：
loss1 = outputs['loss1']
loss2 = 1-outputs['loss2']
loss = loss1 + loss2
我的问题是，减去减去是正确的lose2从1？这样，它会增加而不是减少。
Is there a way to flip the effect of the cross-entropy loss?
I have a language model, and I want to train the model in a way that doesn't generate a specific text. Thus, I have two losses, one that I want to reduce (loss1) and another that I want to increase (loss2):
loss1 = outputs['loss1']
loss2 = 1-outputs['loss2']
loss = loss1 + loss2
My question is, is it correct to subtract loss2 from 1? in this way it increases instead of decreasing.
如果你对这篇内容有疑问，欢迎到本站社区发帖提问 参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。
绑定邮箱获取回复消息
由于您还没有绑定你的真实邮箱，如果其他用户或者作者回复了您的评论，将不能在第一时间通知您！
发布评论