python - Use callbacks to pick best network

Question

I'm working on a classification task, trying to reconstruct a network from paper. In that paper, they are talking about doing a train test split 300 times and training the network each time after they are taking the mean of all predictions from each network for specific input data.

So here's the question: After the first evaluation it's skipping all the others because the evaluation of the last epoch of the first training is always better than the first epoch evaluation of the next network training, what can I do to compare the last epochs of networks? Here's the code:

checkpoint_filepath = './checkpoint'

model_checkpoint_callback = tf.keras.callbacks.ModelCheckpoint(
    filepath=checkpoint_filepath,
    save_weights_only=True,
    monitor='precision',
    mode='max',
    save_best_only=True)

lis = []

for i in range(300):

# Train test split

X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, stratify = Y)

# Create model

model_two_neuron = tf.keras.Sequential([
  tf.keras.layers.Dense(40, input_shape=(15,)),
  tf.keras.layers.Dense(2, activation=tf.nn.sigmoid)
])

model_two_neuron.compile(optimizer=tf.keras.optimizers.Adam(),
              loss=tf.keras.losses.MeanSquaredError(),
              metrics=[tf.keras.metrics.Precision()])

# Train

model_two_neuron.fit(X_train, y_train, epochs=20, callbacks=[model_checkpoint_callback])

# evaluate

value = model_two_neuron.evaluate(X_test, y_test)

Answer 1

等待大神答复