Giter Club home page Giter Club logo

chinese_sentiment's People

Contributors

aespresso avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

chinese_sentiment's Issues

Unable to open file (Unable to open file: name = 'sentiment_checkpoint.keras',

您好,当我执行到
path_checkpoint='sentiment_checkpoint.keras'
checkpoint=ModelCheckpoint(filepath=path_checkpoint,monitor='val_loss',
verbose=1,save_weights_only=True,
save_best_only=True)
try:
model.load_weights(path_checkpoint)
except Exception as e:
print(e)

报错信息:

Unable to open file (Unable to open file: name = 'sentiment_checkpoint.keras', errno = 2, error message = 'no such file or directory', flags = 0, o_flags = 0)

你好,对于这个情感分析任务,我有几个疑问。

1.我们将一条短评,进行分词,然后将利用预训练的word2vec构建构建这个短评的embeddding,让这个embuding作为LSTM的输入项.而LSTM输入项应该是分词词语的向量才对吧,因为只有词语和词语之间才会有时间序列上的关联,而句子和句子间是没有的。
例如下图中的 x , x , x<t+1> ,应该是词语向量,而不是一个个embedding。
fb9ee87ffc5345babef134df0ab7259
2.如果LSTM输入的是词语向量,而LSTM中每个一LSTM单元的输出层都是二分类的话,是对一个一个词语去判断他的情感极性么?我觉得应该是整个LSTM循环之后再连接一个输出层二分类这样才是合理吧,然后如果是这样的话,我们对每一条短评都建立一个LSTM神经网络模型和二分类的输出层,最后一共m个短评构建出一个LSTM神经网络集群,从而去定义整个集群的损失函数sum(loss)/m么?
很抱歉,我是个初学者,在对LSTM和Word2vec上得理解得不够准确和透彻,希望得到您的解答,谢谢。

Originally posted by @Sujunheng in #2 (comment)

predict_sentiment(text)

您好,非常感谢您的分享,我在听完您的视频后,运行了程序,
test_list = [
'酒店设施不是新的,服务态度很不好',
'酒店卫生条件非常不好',
'床铺非常舒适',
'房间很凉,不给开暖气',
'房间很凉爽,空调冷气很足',
'酒店环境不好,住宿体验很不好',
'房间隔音不到位' ,
'晚上回来发现没有打扫卫生',
'因为过节所以要我临时加钱,比团购的价格贵'
]
for text in test_list:
predict_sentiment(text)
运行到上面的代码时报错了,
报错信息:InvalidArgumentError (see above for traceback): indices[0,231] = 83086 is not in [0, 50000)
[[Node: embedding/Gather = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](embedding/embeddings/read, embedding/Cast)]]
不知道是不是tensorflow版本的问题,请问你用的是哪个版本的tensorflow?

关于程序运行中的几个问题

首先非常感谢作者您的视频讲解和详细的代码,让小白能基本理解情感分析的过程。
但是在我运行程序过程中,有几个疑问得不到解答,希望能得到您的帮助~
1.pos文件夹中的文件并没有标记,positive_samples有,那么positive_samples是下载来的呢,还是自己标记的?
2.为什么要在BLSTM后还要加一层LSTM?一般有一层LSTM不就可以了吗?
3.在fit模型后,更改了回调函数的某个参数后再一次fit,为什么运行是基于上一次fit的结果来运行的?怕您不理解,我解释一下,就是上一次的结果为val_loss=0.31515,这次所有epoch的结果就全是0.31515。
4.为什么同一个epoch里,loss和accuracy不一样?
比如,epoch6/20,loss=0.3315,epoch00006,loss=0.3326,两个不一样
5.为什么运行结果显示的是把模型存入了sentiment_checkpoint.h5文件中,但我通过hdp查看却发现文件中一点数据也没有?
基础不是很好,如果问了些没水平的问题还请见谅~
期待您的解答!
再一次感谢您的付出~

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.