避免tf.data.Dataset数据集。从张量切片与估计器api

要使用可初始化或可重新初始化的迭代器,必须创建继承自的类tf.train.SessionRunHook会话,在培训和评估步骤中可以多次访问会话。

然后可以使用这个新类来初始化迭代器,这通常是在经典设置中执行的。您只需将这个新创建的钩子传递给training/evaluation函数或正确的train规范。

class IteratorInitializerHook(tf.train.SessionRunHook):
    def __init__(self):
        super(IteratorInitializerHook, self).__init__()
        self.iterator_initializer_func = None # Will be set in the input_fn

    def after_create_session(self, session, coord):
        # Initialize the iterator with the data feed_dict
        self.iterator_initializer_func(session) 


def get_inputs(X, y):
    iterator_initializer_hook = IteratorInitializerHook()

    def input_fn():
        X_pl = tf.placeholder(X.dtype, X.shape)
        y_pl = tf.placeholder(y.dtype, y.shape)

        dataset = tf.data.Dataset.from_tensor_slices((X_pl, y_pl))
        dataset = ...
        ...

        iterator = dataset.make_initializable_iterator()
        next_example, next_label = iterator.get_next()


        iterator_initializer_hook.iterator_initializer_func = lambda sess: sess.run(iterator.initializer,
                                                                                    feed_dict={X_pl: X, y_pl: y})

        return next_example, next_label

    return input_fn, iterator_initializer_hook

...

train_input_fn, train_iterator_initializer_hook = get_inputs(X_train, y_train)
test_input_fn, test_iterator_initializer_hook = get_inputs(X_test, y_test)

...

estimator.train(input_fn=train_input_fn,
                hooks=[train_iterator_initializer_hook]) # Don't forget to pass the hook !
estimator.evaluate(input_fn=test_input_fn,
                   hooks=[test_iterator_initializer_hook])