0

我需要将我的数据生成器转换Sequence为tf.data.Dataset格式。为此，我使用该from_generator函数为我的所有训练、验证和测试数据创建重复的 BatchedDataset。

  dataset = tf.data.Dataset.from_generator(gen_function,
                                           output_signature=output_signature)
  dataset = dataset.shuffle(shuffle_buffer,
                            reshuffle_each_iteration=True)
  dataset = dataset.repeat()
  dataset = dataset.batch(batch_size)

这些用于模型拟合：

OCR.model.fit(x=training_generator,
              validation_data=validation_generator,
              steps_per_epoch=steps_per_epoch, 
              epochs=epochs,
              use_multiprocessing=True,
              callbacks=callbacks,
              workers=workers,
              verbose=verbose)

这导致了以下错误：

    /user/.../python3.8/site-packages/tensorflow/python/keras/engine/data_adapter.py, 
    line 739, in _validate_args raise ValueError(
    ValueError: When providing an infinite dataset, you must specify the number of 
    steps to run (if you did not intend to create an infinite dataset, make sure to 
    not call `repeat()` on the dataset).
    [date time]: W tensorflow/core/kernels/data/generator_dataset_op.cc:107] Error 
    occurred when finalizing GeneratorDataset iterator: Failed precondition: Python 
    interpreter state is not initialized. The process may be terminated.
    >· [[{{node PyFunc}}]]

这很令人困惑，因为我按照建议指定了重复无限数据集的步数。steps_per_epoch此外，当我之前使用基于序列的数据生成器时，它以这种方式与指定的方式一起工作。

4

1 回答 1

0

解决方法很简单，只需要在函数中指定validation_steps参数即可。steps_per_epochfit

于 2021-04-26T11:20:09.593 回答