Question

MNIST的TensorFlow文档推荐了多种不同的加载MNIST数据集的方法：

文档中描述的所有方法都会使用TensorFlow 1.8抛出许多已弃用的警告。

我正在加载MNIST并创建培训批次的方式：

class MNIST:
    def __init__(self, optimizer):
        ...
        self.mnist_dataset = input_data.read_data_sets("/tmp/data/", one_hot=True)
        self.test_data = self.mnist_dataset.test.images.reshape((-1, self.timesteps, self.num_input))
        self.test_label = self.mnist_dataset.test.labels
        ...

    def train_run(self, sess):
        batch_input, batch_output = self.mnist_dataset.train.next_batch(self.batch_size, shuffle=True)
        batch_input = batch_input.reshape((self.batch_size, self.timesteps, self.num_input))
        _, loss = sess.run(fetches=[self.train_step, self.loss], feed_dict={self.input_placeholder: batch_input, self.output_placeholder: batch_output})
        ...

    def test_run(self, sess):
        loss = sess.run(fetches=[self.loss], feed_dict={self.input_placeholder: self.test_data, self.output_placeholder: self.test_label})
        ...

我怎么能用同样的方法做同样的事情呢？

我找不到任何关于此的文件。

在我看来，新方式符合以下方面：

train, test = tf.keras.datasets.mnist.load_data()
self.mnist_train_ds = tf.data.Dataset.from_tensor_slices(train)
self.mnist_test_ds = tf.data.Dataset.from_tensor_slices(test)

但我如何在train_run和test_run方法中使用这些数据集？

Answer 1

使用TF dataset API加载MNIST数据集的示例：

创建一个mnist数据集来加载训练，有效和测试图像：

您可以使用dataset或Dataset.from_tensor_slices为numpy输入创建Dataset.from_generator。 Dataset.from_tensor_slices将整个数据集添加到计算图中，因此我们将使用Dataset.from_generator代替。

#load mnist data
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

def create_mnist_dataset(data, labels, batch_size):
  def gen():
    for image, label in zip(data, labels):
        yield image, label
  ds = tf.data.Dataset.from_generator(gen, (tf.float32, tf.int32), ((28,28 ), ()))

  return ds.repeat().batch(batch_size)

#train and validation dataset with different batch size
train_dataset = create_mnist_dataset(x_train, y_train, 10)
valid_dataset = create_mnist_dataset(x_test, y_test, 20)

可以在培训和验证之间切换的可输入迭代器

handle = tf.placeholder(tf.string, shape=[])
iterator = tf.data.Iterator.from_string_handle(
handle, train_dataset.output_types, train_dataset.output_shapes)
image, label = iterator.get_next()

train_iterator = train_dataset.make_one_shot_iterator()
valid_iterator = valid_dataset.make_one_shot_iterator()

示例运行：

#A toy network
y = tf.layers.dense(tf.layers.flatten(image),1,activation=tf.nn.relu)
loss = tf.losses.mean_squared_error(tf.squeeze(y), label)

with tf.Session() as sess:
   sess.run(tf.global_variables_initializer())

   # The `Iterator.string_handle()` method returns a tensor that can be evaluated
   # and used to feed the `handle` placeholder.
   train_handle = sess.run(train_iterator.string_handle())
   valid_handle = sess.run(valid_iterator.string_handle())

   # Run training
   train_loss, train_img, train_label = sess.run([loss, image, label],
                                                 feed_dict={handle: train_handle})
   # train_image.shape = (10, 784) 

   # Run validation
   valid_pred, valid_img = sess.run([y, image], 
                                    feed_dict={handle: valid_handle})
   #test_image.shape = (20, 784)

如何通过TensorFlow加载MNIST（包括下载）？

1 个答案: