我正在尝试训练一个机器学习模型来自动分割心脏。我使用的是TensorFlow 2.8.0。下面是我的一段代码：

for step in range(steps):
    print('\n****** Epoch {} Step {} ******'.format(epoch, step))
    batch_img0, batch_img1, batch_mask0, batch_mask1 = next(train_generator)
    print(model.train_on_batch([batch_img0, batch_img1, batch_mask0], batch_mask1, sample_weight=None, class_weight=None))

在这个for循环的层次上，我收到以下错误：

File "C:\Users\talba\Downloads\base de données\CardiacMotionFlow-master\segmentation\finetune_lvrv_net.py", line 323, in finetune_lvrv_net
    print(model.train_on_batch([batch_img0, batch_img1, batch_mask0], 
  File "C:\Users\talba\Downloads\jupiter\lib\site-packages\keras\engine\training.py", line 2093, in train_on_batch
    logs = self.train_function(iterator)
  File "C:\Users\talba\Downloads\jupiter\lib\site-packages\tensorflow\python\util\traceback_utils.py", line 153, in error_handler
    raise e.with_traceback(filtered_tb) from None
  File "C:\Users\talba\Downloads\jupiter\lib\site-packages\tensorflow\python\framework\func_graph.py", line 1147, in autograph_handler
    raise e.ag_error_metadata.to_exception(e)
AttributeError: in user code:

    File "C:\Users\talba\Downloads\jupiter\lib\site-packages\keras\engine\training.py", line 1021, in train_function  *
        return step_function(self, iterator)
    File "C:\Users\talba\Downloads\base de données\CardiacMotionFlow-master\segmentation\..\helpers.py", line 1356, in dice_coef5_0  *
        y_pred = tf.to_float(y_pred)

    AttributeError: module 'tensorflow' has no attribute 'to_float'

误差显然在这条线的水平上

print(model.train_on_batch([batch_img0, batch_img1, batch_mask0], batch_mask1, sample_weight=None, class_weight=None))

我收到属性错误AttributeError: module 'tensorflow' has no attribute 'to_float'，但我没有在代码中写一行float。我不明白。有人能帮我解决这个问题吗？