如何通过 TensorFlow 加载 MNIST（包括下载）？

Question

MNIST 的 TensorFlow 文档推荐了多种不同的方式来加载 MNIST 数据集：

• https://www.tensorflow.org/tutorials/layers
• https://www.tensorflow.org/versions/r1.2/get_started/mnist/beginners
• https://www.tensorflow.org/versions/r1.2/get_started/mnist/pros

文档中描述的所有方式都会在 TensorFlow 1.8 中引发许多已弃用的警告。

我目前加载 MNIST 和创建训练批次的方式：

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})
        ...

我怎么能做完全一样的事情，只是用目前的方法？

我找不到这方面的任何文档。

在我看来，新方法是这样的：

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)

但是如何在我的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 数据集以加载训练、有效和测试图像：

您可以使用Dataset.from_tensor_slices 或Dataset.from_generator 为numpy 输入创建dataset。 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)

---

可在训练和验证之间切换的可馈送迭代器

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)