yunitata / coling2018 Goto Github PK

Hi Yunita,
Thank you for sharing the codes. It is a very beautiful work and the paper is also very helpful for new people like me. I wanted to run the complete model, but getting some error on running feature_analysis.py
It would be very kind of yours for helping me.

Traceback (most recent call last):
File "feature_analysis.py", line 110, in
main()
File "feature_analysis.py", line 83, in main
args.batch_size, args.nb_class, args.nb_epoch, args.lr, args.model_path, args.weight_path, args.hidden_size, args.feature_dim, args.dropout)
File "feature_analysis.py", line 40, in FNN
nb_class, nb_epoch, batch_size, lr, md_path, w_path, hidden_size, input_dim, dropout)
File "/home/iit/Desktop/coling2018-master/model.py", line 213, in model_dense
callbacks=[earlystop_cb, checkPoint], verbose=2)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/models.py", line 652, in fit
sample_weight=sample_weight)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/engine/training.py", line 1038, in fit
batch_size=batch_size)
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/engine/training.py", line 963, in _standardize_user_data
exception_prefix='model input')
File "/usr/local/lib/python2.7/dist-packages/Keras-1.1.2-py2.7.egg/keras/engine/training.py", line 111, in standardize_input_data
str(array.shape))
Exception: Error when checking model input: expected dense_input_1 to have shape (None, 728) but got array with shape (450, 1098)

Hi, yunitata,
You are so nice to share you source code. And could you please share the datasets please?
Or could you send me the datasets to the email [email protected]
Thanks very much!

Hi Yunita,
I meet an error when I run feature_analysis.py as below:

(nlp_py35) xiaojinhui@X10DBi:~/hzq/C_or_T$ python feature_analysis.py --data ccat50 --train_path ../twitter_data/varying_training_set_size_50_sample/train.csv --test_path ../twitter_data/varying_training_set_size_50_sample/test.csv --nb_class 50
/home/xiaojinhui/hzq/nlp_py35/lib/python3.5/site-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.
Traceback (most recent call last):
File "feature_analysis.py", line 13, in
import model
ImportError: No module named 'model'

So, should there have been a python file named model.py which is missed?