CODEWITHSUNDEEP
pythontensorflowkerasdeep-learning
yihao ren
yihao ren

Reputation: 379

Error when checking target: expected dense_192 to have 3 dimensions, but got array with shape (37118, 1)

Dear all: I'm very new to deep learning. I was trying to add a for loop to test all the possible combinations to get the best result. Currently what I have is the following.

def coeff_determination(y_true, y_pred):
    SS_res =  K.sum(K.square( y_true-y_pred )) 
    SS_tot = K.sum(K.square( y_true - K.mean(y_true) ) ) 
    return ( 1 - SS_res/(SS_tot + K.epsilon()) )

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3)
x_train = x_train.to_numpy()
x_test = x_test.to_numpy()
y_train = y_train.to_numpy()
y_test = y_test.to_numpy()
print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)

(37118, 105)
(37118,)
(15908, 105)
(15908,)

timesteps = 3
features = 35 #this is the number of features
x_train = x_train.reshape((x_train.shape[0], timesteps, features))
x_test = x_test.reshape((x_test.shape[0], timesteps, features))

dense_layers=[0, 1, 2]
layer_sizes=[32, 64, 128]
LSTM_layers=[1,2,3]
for dense_layer in dense_layers:
    for layer_size in layer_sizes:
        for LSTM_layer in LSTM_layers:
            NAME="{}-lstm-{}-nodes-{}-dense-{}".format(LSTM_layer, layer_size, dense_layer, int(time.time()))
            tensorboard = TensorBoard(log_dir=f"LSTM_logs\\{NAME}")
            print(NAME)
            model = Sequential()
            model.add(LSTM(layer_size, input_shape=(x_train.shape[1], x_train.shape[2]), return_sequences=True))
            for i in range(LSTM_layer-1):
                model.add(LSTM(layer_size, input_shape=(x_train.shape[1], x_train.shape[2]), return_sequences=True))
            for i in range(dense_layer):
                model.add(Dense(layer_size))
            model.add(Dense(1))
            model.compile(loss='mae', optimizer='adam',metrics=[coeff_determination])
            epochs = 10
            result = model.fit(x_train, y_train, epochs=epochs, batch_size=72, validation_data=(x_test, y_test), verbose=2, shuffle=False)

However, a got a traceback says the following

ValueError: Error when checking target: expected dense_192 to have 3 dimensions, but got array with shape (37118, 1)

and the error occurs in the following line.

---> 19             result = model.fit(x_train, y_train, epochs=epochs, batch_size=72, validation_data=(x_test, y_test), verbose=2, shuffle=False)

Could anyone please kindly give me some hint regarding how to solve the problem. Thanks a lot for your time and support.

Sincerely

Wilson

Upvotes: 0

Views: 48

Answers (1)

Gaussian Prior
Gaussian Prior

Reputation: 786

Use return_sequence = False for your last LSTM layer so it only returns a vector with the last hidden state.

Sincerely,

Alexander

more details: How to use return_sequences option and TimeDistributed layer in Keras?

Upvotes: 1

Related Questions