Beam Search finalize() bug: not update parents in the "body"

[AaronYALai]

https://github.com/guillaumegenthial/im2latex/blob/8e25d7ec2097e2c6515bbb5b41e8f16b79339967/model/components/beam_search_decoder_cell.py#L247

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!

def body(time, outputs_ta, parents): 
    ... (no update of parents) ...
    return (time + 1), outputs_ta, parents

This should be as the following:

return (time + 1), outputs_ta, input_t.parents

since parents for the next step are stored in "input_t" which is extracted for the current time step.

[interxuxing]

@AaronYALai maybe you are right, i modified the beaming search decoding according to your comment, the performance has 5% improvement on my own dataset.

[JunweiLiang]

@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.

[kim-yhow]

@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

[pageedward]

@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+%

[pageedward]

@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+%