ValueError: Error when checking input: expected dense_36_input to have shape (None, 12) but got array with shape (140, 2)

Question

create model

model=Sequential()
model.add(Dense(input_dim = 12, units = 10, activation='relu', kernel_initializer='uniform'))
model.add(Dense(units = 8, activation='relu', kernel_initializer='uniform'))
model.add(Dense(units = 1, activation='sigmoid', kernel_initializer='uniform'))

print('Training the model...')

Compile model

model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

while running the model.fit()

Fit the model

model.fit(X_train,y_train,batch_size=32, epochs=10, verbose=1)

I am getting the Error

ValueError: Error when checking input: expected dense_36_input to have shape (None, 12) but got array with shape (140, 2)

shantanu pathak · Answer

@Angel
Input dimetion means how many no of feature or columns your input is supposed to have.
The neural network will try to adjust to this input shape.
In your case you have specified input_dim = 12 but in your data (140,2) there are only 2 features or columns.
So there are two options

Set input_dim =2

Reshape input array to in multiples of specified input dim i..e 12.

In your case ONLY option 1 works because (140,2) cannot be reshaped in multiples of 12.
Note:: other valid input_dim for you can be 14 (reshape input to (20,14)), 10 (reshape input to (28,10))

ValueError: Error when checking input: expected dense_36_input to have shape (None, 12) but got array with shape (140, 2)

create model

Compile model

Fit the model

One Answer

Input dimetion means how many no of feature or columns your input is supposed to have.

So there are two options

In your case ONLY option 1 works because (140,2) cannot be reshaped in multiples of 12.

Add your own answers!

Ask a Question