ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

使用 tf.data 加载 NumPy 数据

在 Tensorflow.org 上查看 在 Google Colab 运行 在 Github 上查看源代码 下载此 notebook

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

.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 2ms/step - loss: 3.6542 - sparse_categorical_accuracy: 0.8796
Epoch 2/10
938/938 [==============================] - 2s 2ms/step - loss: 0.5308 - sparse_categorical_accuracy: 0.9272
Epoch 3/10
938/938 [==============================] - 2s 2ms/step - loss: 0.3838 - sparse_categorical_accuracy: 0.9475
Epoch 4/10
938/938 [==============================] - 2s 2ms/step - loss: 0.3091 - sparse_categorical_accuracy: 0.9566
Epoch 5/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2909 - sparse_categorical_accuracy: 0.9614
Epoch 6/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2562 - sparse_categorical_accuracy: 0.9652
Epoch 7/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2369 - sparse_categorical_accuracy: 0.9684
Epoch 8/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2382 - sparse_categorical_accuracy: 0.9717
Epoch 9/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2356 - sparse_categorical_accuracy: 0.9729
Epoch 10/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2117 - sparse_categorical_accuracy: 0.9760
<keras.callbacks.History at 0x7f6785371310>
model.evaluate(test_dataset)
157/157 [==============================] - 0s 2ms/step - loss: 0.6475 - sparse_categorical_accuracy: 0.9601
[0.6475387215614319, 0.960099995136261]