我用python2.7 出现一下错误 其他环境依照要求配置，若该用python3.5 也是类似dtype的问题
File "predict.py", line 23, in
lstm_predict(sentence)
File "code/Sentiment_lstm.py", line 179, in lstm_predict
model = model_from_yaml(yaml_string)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/models.py", line 200, in model_from_yaml
return layer_from_config(config, custom_objects=custom_objects)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/utils/layer_utils.py", line 40, in layer_from_config
return layer_class.from_config(config['config'])
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/models.py", line 1080, in from_config
model.add(layer)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/models.py", line 327, in add
output_tensor = layer(self.outputs[0])
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/engine/topology.py", line 543, in call
self.build(input_shapes[0])
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/layers/recurrent.py", line 763, in build
self.W = K.concatenate([self.W_i, self.W_f, self.W_c, self.W_o])
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 1222, in concatenate
return tf.concat(axis, [to_dense(x) for x in tensors])
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1043, in concat
dtype=dtypes.int32).get_shape(
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 676, in convert_to_tensor
as_ref=False)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 741, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 113, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 102, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 374, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/Users/gt/Downloads/enter/envs/py27/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).name))
TypeError: Expected int32, got <tf.Variable 'lstm_1_W_i:0' shape=(100, 50) dtype=float32_ref> of type 'Variable' instead.

I want to pull your code for my graduation design, but it fails....

楼主考虑过多分类吗

Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("embedding_1/random_uniform:0", shape=(8310, 100), dtype=float32

Prefix dict has been built succesfully.
Traceback (most recent call last):
File "predict.py", line 23, in
lstm_predict(sentence)
File "code/Sentiment_lstm.py", line 187, in lstm_predict
data=input_transform(string)
File "code/Sentiment_lstm.py", line 173, in input_transform
model=gensim.models.Word2Vec.load_word2vec_format('lstm_data/Word2vec_model.pkl', binary = True, unicode_errors='ignore')
File "/anaconda3/lib/python3.6/site-packages/gensim/models/word2vec.py", line 1172, in load_word2vec_format
header = utils.to_unicode(fin.readline(), encoding=encoding)
File "/anaconda3/lib/python3.6/site-packages/gensim/utils.py", line 217, in any2unicode
return unicode(text, encoding, errors=errors)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte

Tried "model=gensim.models.Word2Vec.load_word2vec_format('lstm_data/Word2vec_model.pkl', unicode_errors='ignore')", still same error.

请问能解释下这两个参数是什么意思吗？？谢谢

我安装的是tensorflow (1.1.0)，在使用lstm_predict(string)函数时会报如下错误，大致判断是tensorflow 版本问题

运行时 用的是给出的例子 卡在line14 报错 ： ‘参数长度错误！’

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

Hi:
I installed TensorFlow 1.0 as Keras engine, but got error 'TypeError: Expected int32, got...' . Then I changed TensorFlow to 0.12, the program runs well. So, I suggest you could add TensorFlow version in README. Coz there is no TensorFlow version information in requirement.txt.

你好 麻烦博主了
训练阶段每个epoch只显示一步 运行了0秒 没有print test score
1/1 [==============================] - 0s
这个是怎么回事呢？貌似就没有训练这个阶段？

hi，你好
我跑你的demo时，报错了，不知道怎么弄。
报错信息如下：
AssertionError: Can't store in size_t for the bytes requested 50 * 4
Apply node that caused the error: GpuAllocEmpty(Elemwise{Composite{(Switch(LT(maximum(i0, i1), i2), (maximum(i0, i1) + i3), (maximum(i0, i1) - i3)) + i3)}}.0, Elemwise{Composite{((((i0 * Switch(EQ(i1, i2), i3, i1) * Switch(EQ(i4, i2), i3, i4)) // i5) * i6) // i7)}}[(0, 0)].0, TensorConstant{50})
Toposort index: 63
Inputs types: [TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int64, scalar)]
Inputs shapes: [(), (), ()]
Inputs strides: [(), (), ()]
Inputs values: [array(100), array(-42), array(50)]
Outputs clients: [[GpuIncSubtensor{InplaceSet;:int64:}(GpuAllocEmpty.0, GpuFromHost.0, Constant{1})]]

HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.

what is wrong with this ‘ValueError: You must specify either total_examples or total_words, for proper alpha and progress calculations. The usual value is total_examples=model.corpus_count‘ problem？thank you

这个怎么回事？

你好
在运行代码的时候提示了DeprecationWarning，另外还有word2vec.py模块内部的Error

怀疑是不是安装的依赖包版本与代码的用法不匹配
能否写一下各个依赖包的版本？
谢谢！

Traceback (most recent call last):
File "Sentiment_lstm.py", line 204, in
lstm_predict(string)
File "Sentiment_lstm.py", line 178, in lstm_predict
model = model_from_yaml(yaml_string)
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/models.py", line 187, in model_from_yaml
return layer_from_config(config, custom_objects=custom_objects)
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/utils/layer_utils.py", line 36, in layer_from_config
return layer_class.from_config(config['config'])
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/models.py", line 1036, in from_config
model.add(layer)
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/models.py", line 312, in add
output_tensor = layer(self.outputs[0])
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/engine/topology.py", line 487, in call
self.build(input_shapes[0])
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/layers/recurrent.py", line 710, in build
self.W = K.concatenate([self.W_i, self.W_f, self.W_c, self.W_o])
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 718, in concatenate
return tf.concat(axis, [to_dense(x) for x in tensors])
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/tensorflow/python/util/dispatch.py", line 180, in wrapper
return target(*args, **kwargs)
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1254, in concat
tensor_shape.scalar())
File "/home/user/anaconda3/envs/gu_py27/lib/python2.7/site-packages/tensorflow/python/framework/tensor_shape.py", line 1023, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (4, 100, 50) and () are incompatible

如题

您好，我运行了主函数里面注释掉掉部分，在函数get_train_vecs 里面得到这个错误·～～。
get_train_vecs(x_train,x_test) #计算词向量并保存为train_vecs.npy,test_vecs.npy
File "code/Sentiment_svm.py", line 55, in get_train_vecs
imdb_w2v.train(x_train)
File "/data/home/guanggao/anaconda2/lib/python2.7/site-packages/gensim/models/word2vec.py", line 813, in train
raise ValueError("You must specify either total_examples or total_words, for proper alpha and progress calculations. The usual value is total_examples=model.corpus_count.")
ValueError: You must specify either total_examples or total_words, for proper alpha and progress calculations. The usual value is total_examples=model.corpus_count.

this need think

sentence length has imapct on classify of sentiment.

report

Using TensorFlow backend.
D:\Program Files (x86)\Python\lib\site-packages\gensim\utils.py:862: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
  warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")
load model from disk...
load weights from disk......
2017-10-19 16:02:40.450367: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.450667: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.450933: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.451196: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.451488: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.451763: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.452028: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:40.452314: W c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\platform\cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-10-19 16:02:41.074373: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:887] Found device 0 with properties: 
name: GeForce GTX 960M
major: 5 minor: 0 memoryClockRate (GHz) 1.176
pciBusID 0000:01:00.0
Total memory: 2.00GiB
Free memory: 1.65GiB
2017-10-19 16:02:41.074690: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:908] DMA: 0 
2017-10-19 16:02:41.074841: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:918] 0:   Y 
2017-10-19 16:02:41.075007: I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\gpu\gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 960M, pci bus id: 0000:01:00.0)
rebuild model from disk......
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\KIRIST~1\AppData\Local\Temp\jieba.cache
['你', '是', '傻', '逼', '。']
Loading model cost 1.078 seconds.
Prefix dict has been built succesfully.
1/1 [==============================] - 0s
[[1]]

svm

[0]

我在虚拟机中装的centos 7，在执行 sudo pip install -r requirements.txt 成功安装文件中的几个包后，执行python predict.py svm 这个手机质量很好，我很喜欢，不错不错 语句，结果显示没有 tensorflow。
安装tensorflow 1.0后问题解决，希望作者能更新下requirements。

Traceback (most recent call last):
File "/home/wj/malware/env/word2vec_test/Malware/code/malware_lstm.py", line 178, in
train()
File "/home/wj/malware/env/word2vec_test/Malware/code/malware_lstm.py", line 174, in train
train_lstm(n_symbols, embedding_weights, x_train, y_train, x_test, y_test)
File "/home/wj/malware/env/word2vec_test/Malware/code/malware_lstm.py", line 137, in train_lstm
model.add(LSTM(output_dim=50, activation='sigmoid', inner_activation='hard_sigmoid'))
File "/home/wj/malware/env/local/lib/python2.7/site-packages/keras/models.py", line 312, in add
output_tensor = layer(self.outputs[0])
File "/home/wj/malware/env/local/lib/python2.7/site-packages/keras/engine/topology.py", line 487, in call
self.build(input_shapes[0])
File "/home/wj/malware/env/local/lib/python2.7/site-packages/keras/layers/recurrent.py", line 710, in build
self.W = K.concatenate([self.W_i, self.W_f, self.W_c, self.W_o])
File "/home/wj/malware/env/local/lib/python2.7/site-packages/keras/backend/tensorflow_backend.py", line 718, in concatenate
return tf.concat(axis, [to_dense(x) for x in tensors])
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 1029, in concat
dtype=dtypes.int32).get_shape(
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 639, in convert_to_tensor
as_ref=False)
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 704, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 113, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/framework/constant_op.py", line 102, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 370, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/home/wj/malware/env/local/lib/python2.7/site-packages/tensorflow/python/framework/tensor_util.py", line 302, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).name))
TypeError: Expected int32, got <tf.Variable 'lstm_1_W_i:0' shape=(50, 50) dtype=float32_ref> of type 'Variable' instead.

这是哪里出错呢，找不到解决办法

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