文章很棒，但是自己LSTM跑的结果好像不对哦

[soledada]

SVM is ok:

D:\program\Sentiment-Analysis-master>python predict.py svm 酒店的环境不错，空间挺大的 Using Theano backend. Building prefix dict from the default dictionary ... Loading model from cache c:\users\v-\appdata\local\temp\jieba.cache Loading model cost 0.314 seconds. Prefix dict has been built succesfully. 酒店的环境不错，空间挺大的 positive

D:\program\Sentiment-Analysis-master>python predict.py svm 电脑散热太差，偶尔还蓝屏，送货也太慢了吧 Using Theano backend. Building prefix dict from the default dictionary ... Loading model from cache c:\users\v-\appdata\local\temp\jieba.cache Loading model cost 0.317 seconds. Prefix dict has been built succesfully. 电脑散热太差，偶尔还蓝屏，送货也太慢了吧 negative

get the wrong result with LSTM:

D:\program\Sentiment-Analysis-master>python predict.py lstm 电脑散热太差，偶尔还蓝屏，送货也太慢了吧 Using Theano backend. loading model...... loading weights...... Building prefix dict from the default dictionary ... Loading model from cache c:\users\v-\appdata\local\temp\jieba.cache Loading model cost 0.319 seconds. Prefix dict has been built succesfully. 1/1 [==============================] - 0s 电脑散热太差，偶尔还蓝屏，送货也太慢了吧 positive

D:\program\Sentiment-Analysis-master>python predict.py lstm 酒店的环境不错，空间挺大的 Using Theano backend. loading model...... loading weights...... Building prefix dict from the default dictionary ... Loading model from cache c:\users\v-\appdata\local\temp\jieba.cache Loading model cost 0.324 seconds. Prefix dict has been built succesfully. 1/1 [==============================] - 0s 酒店的环境不错，空间挺大的 negative

[BUPTLdy]

@soledada ~/Sentiment Analysis$ python predict.py lstm 电脑散热太差，偶尔还蓝屏，送货也太慢了吧 Using Theano backend. loading model...... loading weights...... Building prefix dict from the default dictionary ... Loading model from cache /tmp/jieba.cache Loading model cost 0.299 seconds. Prefix dict has been built succesfully. 1/1 [==============================] - 0s 电脑散热太差，偶尔还蓝屏，送货也太慢了吧 negative ~/Sentiment Analysis$ python predict.py lstm 酒店的环境不错，空间挺大的 Using Theano backend. loading model...... loading weights...... Building prefix dict from the default dictionary ... Loading model from cache /tmp/jieba.cache Loading model cost 0.299 seconds. Prefix dict has been built succesfully. 1/1 [==============================] - 0s 酒店的环境不错，空间挺大的 positive

自己跑了下没错呀，注意到你是在windows下跑的，其中导入训练好的模型文件使用的是linux下的文件路径。

[soledada]

我修改了一下路径，还是有问题。但是训练了一下就好像都是对的了。 感谢作者