如何修改keras中的输出以进行反向传播

import keras
from keras.models import Model
from keras.layers import Dense

input_layer = keras.Input(shape=(input_dim,))
hidden_layer = Dense(hidden_dim, activation='relu')(input_layer)
output_layer = Dense(output_dim, activation='softmax')(hidden_layer)

model = Model(inputs=input_layer, outputs=output_layer)

model.compile(loss='categorical_crossentropy', optimizer='adam')

model.fit(x_train, y_train, epochs=num_epochs, batch_size=batch_size)