SpanPSP
SpanPSP copied to clipboard
thuhcsi
请教异常案例
你好。用人民日报模型，测试如下句子 中国首条仿生机器鱼则以中华鲤鱼为原型。 得到 中国#1首条#12仿生#1机器鱼2则以中华鲤鱼#2为#1原型 #12是偶发的异常吧
为什么这里这样写啊，理论上来说TP应该只有a11和a22的呢！ ``` precision1, recall1, fscore1 = score(a11 + a12 + a13 + a21 + a22 + a23 + a31 + a32 + a33, a01 + a02 + a03 , a10...
No module named 'tokenizations' hello, thanks for your nice work, when i try to inference, i meet this error, please tell me how to fix it ?
关于预训练模型
您好，非常感谢您的出色工作，请问您目前提供的预训练模型的训练数据是什么？是只有标贝的数据集还是您在论文里提到的(1) one large homegrown dataset from Peoples' Daily corpus;(2) the other is the small public TTS dataset from Databaker.两个数据集
i have the following warning when conducting inference, which does it matter? how should i fix it? thanks for your time. ``` Some weights of the model checkpoint at bert-base-chinese...
How many epochs do you use to train your released pretrained model "pretrained_SpanPSP_Databaker.pt"?
