T-BRNN-pre model error during prediction

[bhavitvyamalik]

Hi @ottokart, I tried T-BRNN-pre model and it gave me this error (input text file was in all lower case):

Traceback (most recent call last):
  File "/home/lalitaggarwal/Downloads/punctuator2/env/lib/python3.6/site-packages/theano/compile/function_module.py", line 903, in __call__
    self.fn() if output_subset is None else\
ValueError: cannot reshape array of size 10000 into shape (200,256)

 

During handling of the above exception, another exception occurred:

 

Traceback (most recent call last):
  File "punctuator.py", line 172, in <module>
    restore(output_file, text, word_vocabulary, reverse_punctuation_vocabulary, predict)
  File "punctuator.py", line 84, in restore
    y = predict_function(to_array(converted_subsequence))
  File "/home/lalitaggarwal/Downloads/punctuator2/env/lib/python3.6/site-packages/theano/compile/function_module.py", line 917, in __call__
    storage_map=getattr(self.fn, 'storage_map', None))
  File "/home/lalitaggarwal/Downloads/punctuator2/env/lib/python3.6/site-packages/theano/gof/link.py", line 325, in raise_with_op
    reraise(exc_type, exc_value, exc_trace)
  File "/home/lalitaggarwal/Downloads/punctuator2/env/lib/python3.6/site-packages/six.py", line 702, in reraise
    raise value.with_traceback(tb)
  File "/home/lalitaggarwal/Downloads/punctuator2/env/lib/python3.6/site-packages/theano/compile/function_module.py", line 903, in __call__
    self.fn() if output_subset is None else\
ValueError: cannot reshape array of size 10000 into shape (200,256)
Apply node that caused the error: Reshape{2}(AdvancedSubtensor1.0, Join.0)
Toposort index: 33
Inputs types: [TensorType(float64, matrix), TensorType(int64, vector)]
Inputs shapes: [(200, 50), (2,)]
Inputs strides: [(400, 8), (8,)]
Inputs values: ['not shown', array([200, 256])]
Outputs clients: [[InplaceDimShuffle{0,x,1}(Reshape{2}.0)]]

T-BRNN-pre model is even better than Demo-Europarl-EN?