Attribute Error: 'List' object has no attribute 'shape' . Error while trying to train the model with multiple features( multiple arrays)

Question

I have two arrays "train_vol" and "train_time" with shape (164,6790) and one array "train_cap" with shape(164,1). I want to train the model like this... inputs--> train_vol and train_time output--> train_cap .....validation inputs --> val_vol,val_time and validation output --> val_cap....shape of val_vol,val_time is (42,6790) and val_cap is (42,1) 1]1

I am trying to use model.fit() to train the model.I tried giving 2 arrays as input to variable x** and 1 array to output variable y. But I am getting an error as shown.2]2

The document says I can give list of arrays as input. So i have tried but i am getting the following error as shown in the picture. Can Anyone let me know where I have done a mistake?3]3

Answer 1

You can create a model which takes multiple inputs as well as multiple output using functional API.

def create_model3():
    input1 = tf.keras.Input(shape=(13,), name = 'I1')
    input2 = tf.keras.Input(shape=(6,), name = 'I2')
    
    hidden1 = tf.keras.layers.Dense(units = 4, activation='relu')(input1)
    hidden2 = tf.keras.layers.Dense(units = 4, activation='relu')(input2)
    merge = tf.keras.layers.concatenate([hidden1, hidden2])
    hidden3 = tf.keras.layers.Dense(units = 3, activation='relu')(merge)
    output1 = tf.keras.layers.Dense(units = 2, activation='softmax', name ='O1')(hidden3)
    output2 = tf.keras.layers.Dense(units = 2, activation='softmax', name = 'O2')(hidden3)
    
    model = tf.keras.models.Model(inputs = [input1,input2], outputs = [output1,output2])
    
    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])
    return model

You can specify the connection between your layers using the syntax above. Your model can have more than 2 inputs. The model constructed using above code looks like this.

Note that 13 and 6 in the Input layers represent features in your respective data.

For training the model you can use the following syntax:

history = model.fit(
    x = {'I1':train_data, 'I2':new_train_data}, 
    y = {'O1':train_labels, 'O2': new_train_labels},
    batch_size = 32,
    epochs = 10,
    verbose = 1,
    callbacks = None,
    validation_data = [(val_data,new_val_data),(val_labels, new_val_labels)]
)

Here train_data and new_train_data are two separate data entities.
Note: You can also pass List instead of dictionary but the dictionary is more readable in terms of coding.

For more information on Functional API. You can check this link: Functional API