我正在使用 Keras 实现神经网络，但Sequential模型返回nan损失值。我在输出层有 sigmoid 激活函数，可以将输出压缩在 0 和 1 之间，但可能无法正常工作。

这是代码：

def data_generator(batch_count, training_dataset, training_dataset_labels):
  while True:
    start_range = 0
    for batch in batch_count:
      end_range = (start_range + batch[1])
      batch_dataset = training_dataset[start_range:end_range]
      batch_labels = training_dataset_labels[start_range:end_range]
      start_range = end_range
      yield batch_dataset, batch_dataset

mlp = keras.models.Sequential()

# add input layer
mlp.add(
    keras.layers.Input(
        shape = (training_dataset.shape[1], )
    )
)
# add hidden layer
mlp.add(
    keras.layers.Dense(
        units=training_dataset.shape[1] + 10,
        input_shape = (training_dataset.shape[1] + 10,),
        kernel_initializer='random_uniform',
        bias_initializer='zeros',
        activation='relu')
    )
# add output layer
mlp.add(
    keras.layers.Dense(
        units=1,
        input_shape = (1, ),
        kernel_initializer='glorot_uniform',
        bias_initializer='zeros',
        activation='sigmoid')
    )

print('Compiling model...\n')

mlp.compile(
    optimizer='adam',
    loss=listnet_loss
)

mlp.summary() # print model settings


# Training
with tf.device('/GPU:0'):
  print('Start training')
  #mlp.fit(training_dataset, training_dataset_labels, epochs=50, verbose=2, batch_size=3, workers=10)
  mlp.fit_generator(data_generator(groups_id_count, training_dataset, training_dataset_labels),
                    steps_per_epoch=len(training_dataset), epochs=50, verbose=2, workers=10, use_multiprocessing=True)

我能怎么做？