norybaby / sentiment_analysis_textcnn Goto Github PK

我训练好权重之后，执行python eval.py，发现并不能够成功预测。因为会显示如下错误：
ValueError: Cannot feed value of shape (64, 1290) for Tensor 'input_x:0', which has shape '(?, 82)'

具体如图所示：

您好，这段代码能进行多标签分类吗

运行后eval会报错，求问应该如何解决，感谢！

runfile('D:/sentiment_analysis_textcnn-master/textcnn/eval.py', wdir='D:/sentiment_analysis_textcnn-master/textcnn')
Reloaded modules: data_input_helper, text_cnn
Traceback (most recent call last):

File "D:\sentiment_analysis_textcnn-master\textcnn\eval.py", line 27, in
tf.flags.DEFINE_string("w2v_file", "../data/vectors.bin", "w2v_file path")

File "D:\caifeng\anaconda\envs\NewEnv\lib\site-packages\tensorflow\python\platform\flags.py", line 58, in wrapper
return original_function(*args, **kwargs)

File "D:\caifeng\anaconda\envs\NewEnv\lib\site-packages\absl\flags_defines.py", line 290, in DEFINE_string
**args)

File "D:\caifeng\anaconda\envs\NewEnv\lib\site-packages\absl\flags_defines.py", line 102, in DEFINE
module_name, required)

File "D:\caifeng\anaconda\envs\NewEnv\lib\site-packages\absl\flags_defines.py", line 136, in DEFINE_flag
fv[flag.name] = flag

File "D:\caifeng\anaconda\envs\NewEnv\lib\site-packages\absl\flags_flagvalues.py", line 429, in setitem
raise _exceptions.DuplicateFlagError.from_flag(name, self)

DuplicateFlagError: The flag 'w2v_file' is defined twice. First from D:\sentiment_analysis_textcnn-master\textcnn\train.py, Second from D:\sentiment_analysis_textcnn-master\textcnn\eval.py. Description from first occurrence: w2v_file path

多谢分享请问有没有可以使用自己词向量的加attention的bi-lstm的模型呀

`u@u-VirtualBox:~/sentiment_analysis_textcnn/textcnn$ python train.py

Parameters:
ALLOW_SOFT_PLACEMENT=True
BATCH_SIZE=64
CHECKPOINT_EVERY=100
DEV_SAMPLE_PERCENTAGE=0.1
DROPOUT_KEEP_PROB=0.5
EMBEDDING_DIM=128
EVALUATE_EVERY=50
FILTER_SIZES=2,3,4
L2_REG_LAMBDA=0.0
LOG_DEVICE_PLACEMENT=False
NUM_CHECKPOINTS=5
NUM_EPOCHS=10
NUM_FILTERS=128
TRAIN_DATA_FILE=../data/cutclean_label_corpus10000.txt
TRAIN_LABEL_DATA_FILE=
W2V_FILE=../data/vectors.bin

Loading data...
Traceback (most recent call last):
File "train.py", line 226, in
train(w2v_wr.model)
File "train.py", line 93, in train
x_train, x_dev, y_train, y_dev ,vocab_size= load_data(w2v_model)
File "train.py", line 54, in load_data
x_text, y = data_helpers.load_data_and_labels(FLAGS.train_data_file)
File "/home/u/sentiment_analysis_textcnn/textcnn/data_input_helper.py", line 76, in load_data_and_labels
with open(filepath, 'r', encoding='utf-8',errors='ignore') as f:
TypeError: file() takes at most 3 arguments (4 given)`` eval
u@u-VirtualBox:~/sentiment_analysis_textcnn/textcnn$ python eval.py

Parameters:
ALLOW_SOFT_PLACEMENT=True
BATCH_SIZE=64
CHECKPOINT_DIR=./runs/1501842714/checkpoints/
EVAL_TRAIN=True
LOG_DEVICE_PLACEMENT=False
VALID_DATA_FILE=../data/cutclean_label_corpus10000.txt
W2V_FILE=../data/vectors.bin

2018-01-11 10:02:53.954545: W 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.
2018-01-11 10:02:53.954615: W 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.
2018-01-11 10:02:53.954634: W 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.
Traceback (most recent call last):
File "eval.py", line 107, in
eval(w2v_wr.model)
File "eval.py", line 68, in eval
saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/saver.py", line 1679, in import_meta_graph
meta_graph_def = meta_graph.read_meta_graph_file(meta_graph_or_file)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/meta_graph.py", line 402, in read_meta_graph_file
raise IOError("File %s does not exist." % filename)
IOError: File None.meta does not exist.

`

想问下这个数据是从哪里来的哈

AttributeError: 'Word2VecKeyedVectors' object has no attribute 'vocab_hash'

这个代码的data文件夹中，这里的txt文件和bin文件似乎是一一对应的，那么我想用新数据写好txt文件，怎么得到这里匹配的bin文件？？？求救

请问这个是怎么生成的

l2_loss += tf.nn.l2_loss(b)
这里应该是
l2_loss += tf.nn.l2_loss(W)
l2损失正则应该是对W起作用，当然也可以同时加上loss(b)，像原始版本的代码一样。

请问您这里用到的数据是谭松波酒店数据集吗？