-
Notifications
You must be signed in to change notification settings - Fork 128
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
Beam Search finalize() bug: not update parents in the "body" #2
Comments
@AaronYALai maybe you are right, i modified the beaming search decoding according to your comment, the performance has 5% improvement on my own dataset. |
@AaronYALai @interxuxing I think it should the next parents should be gather_helper(input_t.parents, parents) as the parent_idx is the traceback to the last timestep's parent at each timestep. |
你好,你最近也在也就公式图片到latex么,我跑了这个代码,发现EM指标只有51%,没有达到论文中的76%,这份代码是不是与论文的里提到的方法不一样。我没有看到本篇文章使用了Row encoder 的方法 |
你的EM51是跑了迭代次数多少 ,衰减多少,我按照默认配置跑6+13(decay),em只有36.57+% |
|
im2latex/model/components/beam_search_decoder_cell.py
Line 247 in 8e25d7e
The "body" function for the tf.while_loop extracts final decoding results time step by time step.
But the state "parents" has not been updated in the body function!
This should be as the following:
since parents for the next step are stored in "input_t" which is extracted for the current time step.
The text was updated successfully, but these errors were encountered: