luopeixiang / im2latex

Pytorch implemention of Deep CNN Encoder + LSTM Decoder with Attention for Image to Latex

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

训练问题

OKCchampian opened this issue · comments

after i trained the model ,the loss is very low ,but when i evaluate on the train and test dataset all the scores are very very low and the predict is very bad ,why?I haven't change any code.

after i trained the model ,the loss is very low ,but when i evaluate on the train and test dataset all the scores are very very low and the predict is very bad ,why?I haven't change any code.

I have the same question, even worse... the loss stacks around 1.6.