使用 tf.data 加载 NumPy 数据

本教程提供了一个将数据从 NumPy 数组加载到 tf.data.Dataset 中的示例。

此示例从 .npz 文件加载 MNIST 数据集。但是，NumPy 数组的来源并不重要。

安装

import numpy as np
import tensorflow as tf

从 .npz 文件中加载

DATA_URL = 'https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz'

path = tf.keras.utils.get_file('mnist.npz', DATA_URL)
with np.load(path) as data:
  train_examples = data['x_train']
  train_labels = data['y_train']
  test_examples = data['x_test']
  test_labels = data['y_test']

使用 tf.data.Dataset 加载 NumPy 数组

假设您有一个示例数组和相应的标签数组，请将两个数组作为元组传递给 tf.data.Dataset.from_tensor_slices 以创建 tf.data.Dataset 。

train_dataset = tf.data.Dataset.from_tensor_slices((train_examples, train_labels))
test_dataset = tf.data.Dataset.from_tensor_slices((test_examples, test_labels))

使用该数据集

打乱和批次化数据集

BATCH_SIZE = 64
SHUFFLE_BUFFER_SIZE = 100

train_dataset = train_dataset.shuffle(SHUFFLE_BUFFER_SIZE).batch(BATCH_SIZE)
test_dataset = test_dataset.batch(BATCH_SIZE)

建立和训练模型

model = tf.keras.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),
    tf.keras.layers.Dense(128, activation='relu'),
    tf.keras.layers.Dense(10)
])

model.compile(optimizer=tf.keras.optimizers.RMSprop(),
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['sparse_categorical_accuracy'])

model.fit(train_dataset, epochs=10)

Epoch 1/10
938/938 [==============================] - 3s 3ms/step - loss: 3.1038 - sparse_categorical_accuracy: 0.8682
Epoch 2/10
938/938 [==============================] - 2s 3ms/step - loss: 0.4801 - sparse_categorical_accuracy: 0.9248
Epoch 3/10
938/938 [==============================] - 2s 3ms/step - loss: 0.3644 - sparse_categorical_accuracy: 0.9421
Epoch 4/10
938/938 [==============================] - 2s 3ms/step - loss: 0.3237 - sparse_categorical_accuracy: 0.9518
Epoch 5/10
938/938 [==============================] - 2s 3ms/step - loss: 0.2789 - sparse_categorical_accuracy: 0.9572
Epoch 6/10
938/938 [==============================] - 2s 3ms/step - loss: 0.2522 - sparse_categorical_accuracy: 0.9621
Epoch 7/10
938/938 [==============================] - 2s 3ms/step - loss: 0.2474 - sparse_categorical_accuracy: 0.9652
Epoch 8/10
938/938 [==============================] - 2s 3ms/step - loss: 0.2237 - sparse_categorical_accuracy: 0.9686
Epoch 9/10
938/938 [==============================] - 2s 3ms/step - loss: 0.2138 - sparse_categorical_accuracy: 0.9717
Epoch 10/10
938/938 [==============================] - 2s 3ms/step - loss: 0.1984 - sparse_categorical_accuracy: 0.9720
<keras.callbacks.History at 0x7feb8cfeeee0>

model.evaluate(test_dataset)

157/157 [==============================] - 0s 2ms/step - loss: 0.6538 - sparse_categorical_accuracy: 0.9504
[0.6537826657295227, 0.9503999948501587]