SAN
SAN copied to clipboard
tal-tech
Syntax-Aware Network for Handwritten Mathematical Expression Recognition
https://github.com/tal-tech/SAN/blob/abd2b5b40340ecc4c88dcc104d0bc23085147d34/models/Hierarchical_attention/decoder.py#L122 It seems should be: `c2p_hidden = self.c2p_out_gru(c2p_context_vec, c2p_hidden_first)` Is it right?
Excuse me, could you tell me how to generate pkls from https://github.com/JianshuZhang/WAP/tree/master/data ? I use your gen_pkl.py script, but it does not work. Thanks! 
The provided link to the dataset HME100K is inaccessible. Is there any other way I can download the dataset?
After downloading the dataset, I tried run gen_hybrid_data.py to generate the tree txt according to the train_labels.txt. It shows the error below: unknown word before { train_476 1 unknown word...
I convert latex to label but get error because some keyword not handle in code. Such as: \mbox,... In case double { get same error: ``` \sqrt { { o...
 Table 2 mentioned data augmentation, but it seems that there is no further explanation in the paper. Would you kindly explain in here? I plan to follow your work...
Is the format of the SAN model output a LATEX sequence? Or is it a mathematical expression in print format?
Can you provide more details about the config of optimizer used for HME100K dataset? Thanks!
In the pip install -r requirement.txt，errors are often reported. You can tell the Python version and export requirements without using @local files. Thank you for your arrange and open source
