lstm结果是错误的是为什么呢？

[812093147]

python predict.py lstm 这书的印刷质量的太差了吧，还有缺页，以后再也不买了
/usr/local/lib/python2.7/dist-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
"This module will be removed in 0.20.", DeprecationWarning)
Using TensorFlow backend.
loading model......
loading weights......
Building prefix dict from the default dictionary ...
Loading model from cache /tmp/jieba.cache
Loading model cost 0.271 seconds.
Prefix dict has been built succesfully.
1/1 [==============================] - 0s
这书的印刷质量的太差了吧，还有缺页，以后再也不买了 positive

[sichun]

我也出现这个问题 似乎svm的结果更好

[flame110]

lstm 模型训练模型load的时候报错：
......
File "D:/Python/51job/textclassify/Sentiment-Analysis-master/code/Sentiment_lstm.py", line 178, in lstm_predict
model = model_from_yaml(yaml_string)
......
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("embedding_1/random_uniform:0", shape=(8310, 100), dtype=float32)'
是keras版本的问题吗，博主用的哪个版本？我用的keras2.03
还是在生产train模型save成yaml文件前需要cast一下？请问博主知道怎么弄吗？

[sichun]

之前closed issue里有人已经解答了， 我上网找到的解决方案是环境设为：
tensorflow 1.1.0
keras 1.2.2