search

zackhy / TextClassification

Text classification using different neural networks (CNN, LSTM, Bi-LSTM, C-LSTM).
MIT License
194 stars 60 forks source link

ACCURACY #4

Closed zxs1995 closed 6 years ago

zxs1995 commented 6 years ago

may I ask you what is the accuracy of your implementation ,please

zxs1995 commented 6 years ago

may I ask you what the accuracy of your implementation is ,please.

zackhy commented 6 years ago

@zxs1995 accuracy = number of correct predictions / number of all predictions

FajarSukma commented 6 years ago

i have try to run test.py but i got this error

(tf15) E:\Fajar\Programming\Python\Deep Learning\TextClassification\TextClassification-master>python test.py --test_data_file=./data/data.csv --run_dir=./runs/1530085310/ --checkpoi
nt=clf-10000

C:\Users\FajarSukma\Anaconda3\envs\tf15\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprec
ated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
Building dataset ...
Traceback (most recent call last):
  File "test.py", line 38, in <module>
    shuffle=False)
  File "E:\Fajar\Programming\Python\Deep Learning\TextClassification\TextClassification-master\data_helper.py", line 38, in load_data
    sw = _stop_words(sw_path)
  File "E:\Fajar\Programming\Python\Deep Learning\TextClassification\TextClassification-master\data_helper.py", line 149, in _stop_words
    with open(path, 'r', encoding='utf-8') as f:
TypeError: expected str, bytes or os.PathLike object, not Flag

Could you help me,please?

zackhy commented 6 years ago

@FajarSukma If you don't have a stop word file, try assigning the sw_path at line 33 to None and see if this works.