python ValueError: Error when checking target: expected dense_2 to have shape (12,) but got array with shape (1,)

Question

writing a program, use keras to build BP neural networ to predict data(regression),the program is as follows:

bp_dataset = pd.read_csv('Dataset/allGlassStraightThroughTube.csv')
bp_tube_par = bp_dataset.iloc[:, 3:8]
bp_tube_eff = bp_dataset.iloc[:, -1:]


bp_tube_par_X_train,bp_tube_par_X_test,bp_tube_eff_Y_train,bp_tube_eff_Y_test = train_test_split(bp_tube_par,
                                                                                                 bp_tube_eff,
                                                                                                 random_state=33,
                                                                                                 test_size=0.3)

# normalize the train and test Dataset
sc_X = StandardScaler()
sc_Y = StandardScaler()
sc_bp_tube_par_X_train = sc_X.fit_transform(bp_tube_par_X_train)
sc_bp_tube_par_X_test = sc_X.transform(bp_tube_par_X_test)
sc_bp_tube_eff_Y_train = sc_Y.fit_transform(bp_tube_eff_Y_train)
sc_bp_tube_eff_Y_test = sc_Y.transform(bp_tube_eff_Y_test)

# build BP neural network
model = Sequential()
model.add(Dense(12, input_dim=5, activation='relu'))
model.add(Dense(12, activation='linear'))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy', 'mae'])
model.fit(sc_bp_tube_par_X_train, sc_bp_tube_eff_Y_train, epochs=100)
pre_sc_bp_tube_eff_Y_test = model.predict(sc_bp_tube_par_X_test)

but it errors:

Traceback (most recent call last):
  File "C:/Users/win/PycharmProjects/allGlassStraightThroughTube/bpTest.py", line 44, in <module>
model.fit(sc_bp_tube_par_X_train, sc_bp_tube_eff_Y_train, epochs=100)
  ...
  ValueError: Error when checking target: expected dense_2 to have shape (12,) but got array with shape (1,)

could you please tell me the reason and how to correct it

Suhas Shastry · Accepted Answer · 2020-03-03 08:14:47Z

1

model.add(Dense(12, activation='linear'))

12 here represents output dimension. In your case 12 is input dimension to second layer. Keras handle input dimensions for middle layers and you dont have to mention it explicitly.

Your code should be

model.add(Dense(1, activation='linear'))

answered Mar 3, 2020 at 8:14

Suhas Shastry

763 bronze badges

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

2 Comments

bin Over a year ago

thanks, but I modify it to (Dense(1,activation='linear')),the program can run, but when print the fit process, the "accuracy" always are zero, why

Suhas Shastry Over a year ago

Accuracy for regression does not make much sense. MSE or MAE is a better metric.

Collectives™ on Stack Overflow

python ValueError: Error when checking target: expected dense_2 to have shape (12,) but got array with shape (1,)

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