How to fix a value error in the model expected dense?

Question

I am trying deep learning (noob) with Keras. I was trying to creat the model after loading my dataset (training & testing). My code:

scaler = StandardScaler().fit(train)

train=scaler.transform(train)
test=scaler.transform(test)

# Creating Deep Model


model = Sequential()

# Add an input layer
model.add(Dense(12, activation='relu', input_shape=(11,)))

# Add one hidden layer
model.add(Dense(8, activation='relu'))

# Add an output layer
model.add(Dense(1, activation='sigmoid'))

#add improvements 
model.add(BatchNormalization())
model.add(Dropout(0.5))
#Train the model

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

model.fit(train,train_targets,epochs=20, batch_size=1, verbose=1)

However, I am recieving an erro at the last line:

ValueError: Error when checking input: expected dense_1_input to have shape (11,) but got array with shape (211,)

what does the error mean? and what could be causing it?

Answer 1

It means that you set your first layer to expect input shape (11,) by setting the hyperparameter to input_shape = (11,) and you later gave the model a shape equal to train. Try using: train.shape and check for the shape to make sure the model can work with it. You might want check this answer Keras input explanation: input_shape, units, batch_size, dim, etc to make sure you understand the core concepts of a neural network hyperparameters.