jiangix

Continue training

2

I do know how to continue training when I stop the program. Only use python run_summarization.py? However, in train mode, I can not see code about load model which has...

Hi, very sorry for bothering you. I have a question. when the gpu memory is '24GB', batch_size = 1, how much is the 'max_enc_steps' and 'max_dec_steps'. I only have a...

wrong for increasing hidden_dim,emb_dim

1

Sorry for bothering you. In the early training, I set the 'hidden_dim' as 64, and set the 'emb_dim' as 32. Then ,when i increase them as '256' and '128'. it...

length of enc_batch and dec_batch for axis=1

2

Hi, Sorry for bothering you. In enc_batch[hps.batch_size, None], the length of axis=1 is the max number of article words of each example. In dec_batch[hps.batch_size, None], the length of axis=1 is...

Question about length of document and summary

2

Thanks sharing the awesome implementation. When I try to increase the length of document and summary from 400,100 to 800,200. It has an error 'Resource exhausted: OOM when allocating tensor'....

The low rouge scole

3

Hello, Thanks for your valuable code. I have a question. When I run the code for 500k iterations. I get the rouge result: ROUGE-1: rouge_1_f_score: 0.2648 with confidence interval (0.2574,...

Pytorch模型

4

您好，可以麻烦提供Pytorch版本吗？目前在使用pytorch transformer转化时出错了。后续可以跟您报告我们模型在使用xlnet模型做情感分类（CCF BDCI）的准确率，谢谢

Pytorch版本

3

您好，我在使用您提供的命令转化Pytorch版本时，会报错，请问是什么原因？ RuntimeError: Sizes mush be non-negative。应该是vocab_size=-1导致的？

Don't know how to create ISeq from: clojure.lang.Keyword

1

I hava an error when run the code. it is "Don't know how to create ISeq from: clojure.lang.Keyword".

when i run the java -jar xxx 50, I have an error "Don't know how to create ISeq from: clojure.lang.Keyword". How do I deal with it.