Keras LSTM - 'Error when checking model target: expected no data, but got:' data

Question

I am doing simple sequence prediction. My model and data look like this:

def generate_rnn(input_shape):
    In = Input(shape=(input_shape[1], 1))
    x = LSTM(4)(In)
    x = Flatten()(x) # I tried both with and without flatten, same results
    Out = Dense(1)(x)
    
    model = Model([In, Out])
    model.compile(optimizer=Adam(), loss='MSE', metrics=['mse'])
    
    return model

X = np.random.rand(100, 5)
y = np.random.rand(100, 1)
X = X.reshape(X.shape[0], X.shape[1], 1)

rnn = generate_rnn(X.shape)
rnn.fit(X, y, epochs=10)

Firtst time when I run the program, at function call rnn.fit() I get following error message:

File "C:\Users\achib\Anaconda3\envs\deep\lib\site-packages\tensorflow_core\python\keras\backend.py", line 1237, in dtype return x.dtype.base_dtype.name

AttributeError: 'NoneType' object has no attribute 'dtype'

If I run rnn.fit() again in console, I get following error message:

ValueError: ('Error when checking model target: expected no data, but got:',

And then my y variable gets printed. I have worked with LSTM networks in Keras before, but its my first time encountering such an issue? Any help?

Answer 1

The documentation for the Model class ->https://keras.io/api/models/model/#model-class

According to this, Model class must receive input and output as different parameters and not as a part of the same list. That's what the-

ValueError: ('Error when checking model target: expected no data, but got:',

means. The model's target variable(y) is empty. So removing the square bracket should help.

Hope this helped.

May the force be with you.