给我的batch_size值是多少？

Question

I want to predict the value of my x_test after compiling a CNN model:

y_test_predict= model.predict(x_test[3])

My x_test[3] has a shape about (8000, 1)

But this line of code gives me this erros that I don't understand really:

Traceback (most recent call last):
  File "CNN_Learning_Side_Channel_Attack.py", line 155, in <module>
    test_One_Trace= model.predict(x_test[3])
  File "/home/user/.local/lib/python3.4/site-packages/keras/models.py", line 899, in predict
    return self.model.predict(x, batch_size=batch_size, verbose=verbose)
  File "/home/user/.local/lib/python3.4/site-packages/keras/engine/training.py", line 1555, in predict
    check_batch_axis=False)
  File "/home/user/.local/lib/python3.4/site-packages/keras/engine/training.py", line 121, in _standardize_input_data
    str(array.shape))
ValueError: Error when checking : expected conv1d_1_input to have 3 dimensions, but got array with shape (8000, 1)

I would be very grateful if you could help me please.

Answer 1

For convolution operation to make sense you need to give 3 dimensions. In your case you are giving (8000, 1) which is clearly not having 3 dimensions( it has 2 ).

With information provided in question it is very difficult to exactly give you the dimensions, but your problem is mostly with dimensions. You should check your input dimensions while training.