The application of self-attention layer raised index error

So I am doing a classification machine learning with the input of (batch, step, features).

In order to improve the accuracy of this model, I intended to apply a self-attention layer to it.

I am unfamiliar with how to use it for my case since most examples online are concerned with embedding NLP models.

def opt_select(optimizer):
    
    if optimizer == 'Adam':
        adamopt = tf.keras.optimizers.Adam(lr=learning_rate, beta_1=0.9, beta_2=0.999, epsilon=1e-8)
        return adamopt
    
    elif optimizer == 'RMS':
        
        RMSopt = tf.keras.optimizers.RMSprop(lr=learning_rate, rho=0.9, epsilon=1e-6)
        return RMSopt
    
    else:
        print('undefined optimizer')

def LSTM_attention_model(X_train, y_train, X_test, y_test, num_classes, loss,batch_size=68, units=128, learning_rate=0.005,epochs=20, dropout=0.2, recurrent_dropout=0.2,optimizer='Adam'):
   
            
    class myCallback(tf.keras.callbacks.Callback):
        def on_epoch_end(self, epoch, logs={}):
            if (logs.get('acc') > 0.90):
                print("\nReached 90% accuracy so cancelling training!")
                self.model.stop_training = True

    callbacks = myCallback()

    model = tf.keras.models.Sequential()
    model.add(Masking(mask_value=0.0, input_shape=(X_train.shape[1], X_train.shape[2])))
    model.add(Bidirectional(LSTM(units, dropout=dropout, recurrent_dropout=recurrent_dropout)))
    model.add(SeqSelfAttention(attention_activation='sigmoid'))
    model.add(Dense(num_classes, activation='softmax'))
    
    opt = opt_select(optimizer)
    
    model.compile(loss=loss,
                  optimizer=opt,
                  metrics=['accuracy'])

    history = model.fit(X_train, y_train,
                        batch_size=batch_size,
                        epochs=epochs,
                        validation_data=(X_test, y_test),
                        verbose=1,
                        callbacks=[callbacks])

    score, acc = model.evaluate(X_test, y_test,
                                batch_size=batch_size)

    yhat = model.predict(X_test)

    return history, that

This led to IndexError: list index out of range

What is the correct way to apply this layer to my model?

---

As requested, one may use the following codes to simulate a set of the dataset.

import tensorflow as tf
from tensorflow.keras.layers import Dense, Dropout,Bidirectional,Masking,LSTM
from keras_self_attention import SeqSelfAttention


X_train = np.random.rand(700, 50,34)
y_train = np.random.choice([0, 1], 700)
X_test = np.random.rand(100, 50, 34)
y_test = np.random.choice([0, 1], 100)

batch_size= 217
epochs = 600
dropout = 0.6
Rdropout = 0.7
learning_rate = 0.00001
optimizer = 'RMS'
loss = 'categorical_crossentropy'
num_classes = y_train.shape[1]

LSTM_attention_his,yhat = LSTM_attention_model(X_train,y_train,X_test,y_test,loss =loss,num_classes=num_classes,batch_size=batch_size,units=32,learning_rate=learning_rate,epochs=epochs,dropout = 0.5,recurrent_dropout=Rdropout,optimizer=optimizer)

from The application of self-attention layer raised index error