-
Notifications
You must be signed in to change notification settings - Fork 5.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
如何设置learning rate decay?Annealing the learning rate #1167
Comments
也对,这里应该加一下注释。。我下午加一下。。 |
多谢多谢 |
See #1170 不过里面加了一些强类型的Wrapper,如果手动的设置这几个参数,就参考下这里的XXXLRS怎么实现的吧。 |
简单的贴一下之前的文档,供参考:
|
@qingqing01 提醒说,代码里面目前的逻辑 learning_rate_schedule 也会修改 adagrad, adadelta, rmsprop 的全局学习率。修正上一条的说法。 |
您好,请问 然后第五个 "linear": lr = max(learning_rate - learning_rate_decay_a, learning_rate_decay_b) ,lr与num_samples_processed无关,不随着训练变化的嘛? 另外有没有能从optimizer得到当前的learing rate的方法呢?我看了一下code,并没有找到接口。使用optimizer.dict["opt_conf_proto"].learning_rate 也只能获得最开始初始的lr. |
|
好的~谢谢! |
* refine flags doc,test=develop * follow comments, test=develop
* fix_demo * fix_demo
在optimizers.py里面,我看到了设置learning rate decay的参数, 不过有两个,learning_rate_decay_a=0.,
learning_rate_decay_b=0.,
请问这两个参数有什么区别呢、分别代表什么含义呢?我应该用哪一个呢?
似乎并没有相关的wiki、文档记录呢。
The text was updated successfully, but these errors were encountered: