关于您为什么会收到错误的原始问题:

To your original question as to why you're getting the error:

Error when checking input: expected input_1 to have 2 dimensions, but got array with shape (32,)

代码中断的原因是因为您没有将.batch()重新应用到dataset变量，就像这样:

The reason your code breaks is because you haven't applied the .batch() back to the dataset variable, like so:

dataset = dataset.batch(10)

您只是打了dataset.batch().

这会中断，因为没有batch()的输出张量不会被批处理，即您得到的形状是(32,)而不是(1,32).

This breaks because without the batch() the output tensors are not batched, i.e. you get shape (32,) instead of (1,32).