shubham0204/spam_classification_tf

A TensorFlow Project which detects spam messages and uses this capability in Android apps.

Spam_Classification_TF

This project is quite old, and needs a refresh!

spam_classification_tf's Issues

ValueError: setting an array element with a sequence.

i am getting this following error when trying to run your code ..please provide me a solution to overcome it..

3343, 171)
(3343, 2)
(2229, 171)
(2229, 2)

TypeError                                 Traceback (most recent call last)
TypeError: float() argument must be a string or a number, not 'Tensor'

The above exception was the direct cause of the following exception:

ValueError                                Traceback (most recent call last)
<ipython-input-16-7996db5b94d7> in <module>()
     13 print( test_Y.shape )
     14 
---> 15 classifier = Classifier( number_of_classes=2 , maxlen=171 )
     16 #classifier.load_model( 'models/model.h5' )
     17 

10 frames
/usr/local/lib/python3.6/dist-packages/numpy/core/_asarray.py in asarray(a, dtype, order)
     83 
     84     """
---> 85     return array(a, dtype, copy=False, order=order)
     86 
     87 

ValueError: setting an array element with a sequence.

type object 'TFLiteConverterV2' has no attribute 'from_keras_model_file'

Thanks for your guidance, great article, but I get this error when running your project:
i clone your code and run TFliteBufferConverter.py :
type object 'TFLiteConverterV2' has no attribute 'from_keras_model_file'

if i convert by my code:

converter = tf.lite.TFLiteConverter.from_keras_model(model) converter.optimizations = [tf.lite.Optimize.DEFAULT] # sử dụng optimization nếu cần tối ưu thêm tflite_model = converter.convert() with open('model_optimizations.tflite', 'wb') as f: f.write(tflite_model)
i get model.tflite , but when i push it into androi project, i cannot open app, what diffrence?