zhangxixi0904

I got the same problem: Input to reshape is a tensor with 9489 values, but the requested shape has 12356

Thank you so much for your advice!! I am wondering if the version incompatible too @balzac001

@Qiuchenggit Hi, can you train this network? I try on my own dataset, but the dimension seems not fit.Something wrong in the RPN.py. If there were any change you have...

数据集是不是不公开啊？这个领域还是很缺数据啊

分词模型遇到了一样的问题 Taskflow("word_segmentation",mode='accurate')

Did somebody know the reason for multiplying embedding weights by sqrt(d_model)？

I met the same problem, have you solved it?