In order to use the Tf.data.Dataset.from_tensor_slices method, do I need to have GPU on the PC?

Question

I’m doing my tensorflow training. So far so good:

data = numpy.random.random((1000, 32))
labels = numpy.random.random((1000, 10))
model.fit(data, labels, epochs=10, batch_size=32)

But when I do practice like this it makes a mistake:

data = numpy.random.random((1000, 32))
labels = numpy.random.random((1000, 10))
dataset = tf.data.Dataset.from_tensor_slices((data, labels))
dataset = dataset.batch(32)
model.fit(dataset, epochs=10)

Error appears StartAbort Out of range at each time:

Epoch 1/10
     32/Unknown - 1s 25ms/step - loss: 219.6890 - accuracy: 0.11002020-04-17 11:42:58.024503: W tensorflow/core/common_runtime/base_collective_executor.cc:216] BaseCollectiveExecutor::StartAbort Out of range: End of sequence
     [[{{node IteratorGetNext}}]]
32/32 [==============================] - 1s 25ms/step - loss: 219.6890 - accuracy: 0.1100

Help me, please! I’m new at tensorflow and also here, don’t be too hard on me.