alic-yuan / nlp-beginner-finish Goto Github PK
View Code? Open in Web Editor NEW此项目完成了关于 NLP-Beginner:自然语言处理入门练习 的所有任务,所有代码都经过测试,可以正常运行。
此项目完成了关于 NLP-Beginner:自然语言处理入门练习 的所有任务,所有代码都经过测试,可以正常运行。
Traceback (most recent call last):
File "main.py", line 127, in
cn.train()
File "main.py", line 71, in train
loss = model.log_likelihood(X,y)
File "/content/drive/My Drive/fudanlp/nlp-beginner-finish-master/task4/model/LSTM_CRF.py", line 40, in log_likelihood
x = x.transpose(0,1)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
873101411
感谢
在最新的 2020/04/29 版本中, 注意力对应邱老师的<<神经网络和深度学习>>第 8 章
你好,请问NER任务的模型保存没有按照指标保存最好的一轮吧?
大佬你好,我想问一下你使用过邱老师提供的那个数据集吗?我使用那个数据集后,随机生成句子的时候总是生成像这种字符,请问你能给我提供一点点建议吗,非常感谢。
想问一下task5中的perplexity困惑度该如何计算啊?好像没看到代码里有这方面的计算
Though it may be not worth mentioning... Just for reminder, if anyone wants to run task2, just modify the line 81 in torch_train.py and DELETE THE WORD "OPTIMIZER".
在task2中是不是对模型更新了,不应该将loss反向传播回去吧。如果传输回去,评估时得到的loss是已经使用了评估数据训练过的模型。
p_mask, h_mask = (p != 1).long(), (h != 1).long() # TODO: 这里是不是写错了 p != 0
m_p, m_h = self.inference(p_, h_, p_mask, h_mask) # m_p = m_h = [256,50,2400]
p_mask, h_mask = (p != 0).long(), (h != 0).long() 因为填充值默认是0
task1 predict.py是否有问题啊 谢谢
楼主,可否把你的运行环境展示出来,方便运行代码的时候配置相应的环境
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.