-
您好,
感谢您提供这么好的学习资料!我用了ELMO+TextCNN的组合跑了IMDB数据集,得到了下面的结果,想问一下,最后的准确率的计算是应该只算最后一个epoch的accuracy还是把所有epoch的accuracy取平均?另外这个accuracy应该是测试集上的accuracy是吗?因为运行完模型以后没有保存训练的模型,如果能把训练的模型保存下来就更好了。
![微信截图_2020070…
-
Hi,
I have 2 questions :
1. The "One Drive" that you shared is, sadly, no longer available. Can you make it accessible again?
2. When I tried to run the `train_ABF.py` file I had the current…
-
# [Word2vec을 활용한 RNN 기반의 문서 분류에 관한 연구](http://www.dbpia.co.kr/Journal/IssueList/PLCT00001218)
- 한국지능시스템학회 논문지 2017.12
- 1st Author Name & Institute : Jung-Mi Kim(1), Ju-Hong Lee(2)
인하대학교 컴퓨터공학부 교수
…
-
为什么卷积核尺寸是(k, config.embed)
-
-
`自己写的预测类,输入文本即可得出结果,但是要用tensorflow才行,怎么把tensorflow pad那个删除?
下面写的预测类代码在TextCNN测试通过,但是在 kr.preprocessing.sequence.pad_sequences这个用到了kears代码,怎么把这个换成pyotorch的或者numpy的?请大神指教,大家一起交流下
from tensorflow…
-
Hi, thank you for sharing the rcv data source and I managed to request data and preprocessed it. I used my preprocessed rcv text and its id as X_train/X_test, train_id/text_id in readData_rcv1. I chos…
-
line 137: predict = []
line 145: predict += logits[0]
会报错:operands could not be broadcast together with shapes (0,) (n,)
(n是label个数)
原因应该是在循环中空数组和预测值logits的第0维相加出现了维度问题。
我改成了 line 137: predic…
-
-