ValueError when compiling with Keras Sequential()

Question

I'm trying to compile a dataset with Sequential() with the Keras module, but I get back a value error:

ValueError: Error when checking model input: expected dense_input_1 to have shape (None, 33) but got array with shape (32, 36)

I went through my code many times, but couldn't find any possible error.

I have a dataset with 32 items, all which are converted into floats.

Here is the code for my neural network:

# Build neural network
# Sequential
model = Sequential()

# Neural network
model.add(Dense(36, input_dim=34, init='uniform', activation='sigmoid' ))
model.add(Dense(32, init='uniform', activation='sigmoid'))
model.add(Dense(32, init='uniform', activation='sigmoid'))
model.add(Dense(32, init='uniform', activation='sigmoid'))
model.add(Dense(33, init='uniform', activation='sigmoid'))

# Compile model
model.compile(loss='mean_squared_logarithmic_error', optimizer='SGD', metrics=['accuracy'])

# Fit model
history = model.fit(X, Y, nb_epoch=20, validation_split=0.2, batch_size=3)

Here is the complete error message I received:

Traceback (most recent call last):
  File "/Users/cliang/Desktop/Laurence/Python/Programs/Python/Collaborative_Projects/Cancer_screening/neural_network_alls_1.py", line 111, in <module>
    history = model.fit(X, Y, nb_epoch=20, validation_split=0.2, batch_size=3)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/models.py", line 672, in fit
    initial_epoch=initial_epoch)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 1116, in fit
    batch_size=batch_size)
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 1029, in _standardize_user_data
    exception_prefix='model input')
  File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 124, in standardize_input_data
    str(array.shape))
ValueError: Error when checking model input: expected dense_input_1 to have shape (None, 34) but got array with shape (32, 36)

ML_TN · Accepted Answer · 2017-05-07 09:16:53Z

1

As the error say, you have a miss match between your input data shape and the first layer. You clearly define that your input dimension is (number of features) is 34 input_dim=34, though you are passing data with 36 features.

I think you have confused between the number of neurons of the hidden layer 36 and your input data 34. Either you drop two column from your data or change input_dim=36.

edited May 7, 2017 at 9:16

answered May 6, 2017 at 20:40

ML_TN

7296 silver badges16 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Erik B. Over a year ago

34 is the length of the input vector, 36 is the number of neurons in the first dense layer (hence the length of the output of this layer), not the number of hidden layers.

Larry Over a year ago

@ML_TN thank you! I eventually found two things that went wrong. The error was there because there wasn't an output layer with just one neuron (which made the program run without error). Secondly, as you said, there was a mismatch between the input data and the first layer (I was using data from the wrong file). Thank you for your help @ML_TN!

Collectives™ on Stack Overflow

ValueError when compiling with Keras Sequential()

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related