Results 6 issues of Zhu Shuai

I met a problem yesterday when I want to get the `vocab_size` of the vocabulary namespace `transformer_tags` which I specify in `PretrainedTransformerIndexer`. I found this namespace doesn't defined when I...

Contributions welcome
question

I have no idea about the following error, looking forward to someone's help, thank you! ~~ ``` Traceback (most recent call last): File "disfluency_detection/pipelines/sentseg_train.py", line 427, in main() File "disfluency_detection/pipelines/sentseg_train.py",...

首先非常佩服大佬能写出这些代码,对我来说,光是理解就需要花费很长的时间,整个看下来也还是有很多不理解的地方,需要时间慢慢消化。不过,在读代码的过程中也有几点思考,想跟repo主交流一下。 1. 关于HMM和BiLSTM-CRF测试函数的问题,repo主写的接口函数test需要提供word2id和tag2id的参数;个人觉得如果是用训练好的模型对未标注序列进行测试的时候,也就是说迁移到一个新的环境的时候,这两个参数是很难提供的;个人想法是将word2id和tag2id这两个参数直接在__init__中提供,这样train和test函数就都不需要再提供这个参数了,便于迁移。 2. BiLSTM-Model中的test函数还需要提供tag_lists参数,这在作者的测试环境来说是可行的,因为测试集也是有标注的,只是为了检验得到的效果;但是在对真正无标注序列进行预测的时候是无法提供的,而该函数也没有考虑tag_lists无法提供的情况;相应的sort_by_lengths函数和preprocess_data_for_lstmcrf函数也要做一下简单的修改。 以上仅是个人的一些想法,希望能和作者交流一下,再次感谢你的代码!

I test the `text_motion` script according to the readme, but the body in the render result is opposite. I don't modify any config and have no idea whether it is...

- modify the cliff config and inference api to run cliff inference

Thanks for your work! I am also collecting a lot of papers related to human-motion-capture, some of them don't appear in your repo. I want to contribute to your repo,...