TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

Load NumPy data

View on TensorFlow.org View source on GitHub Download notebook

This tutorial provides an example of loading data from NumPy arrays into a tf.data.Dataset.

This example loads the MNIST dataset from a .npz file. However, the source of the NumPy arrays is not important.

Setup

from __future__ import absolute_import, division, print_function, unicode_literals
 
import numpy as np
import tensorflow as tf

Load from .npz file

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']

Load NumPy arrays with tf.data.Dataset

Assuming you have an array of examples and a corresponding array of labels, pass the two arrays as a tuple into tf.data.Dataset.from_tensor_slices to create a 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))

Use the datasets

Shuffle and batch the datasets

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)

Build and train a model

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

model.compile(optimizer=tf.keras.optimizers.RMSprop(),
                loss=tf.keras.losses.SparseCategoricalCrossentropy(),
                metrics=[tf.keras.metrics.SparseCategoricalAccuracy()])
model.fit(train_dataset, epochs=10)
Epoch 1/10
938/938 [==============================] - 4s 4ms/step - loss: 3.5160 - sparse_categorical_accuracy: 0.8780
Epoch 2/10
938/938 [==============================] - 2s 2ms/step - loss: 0.5325 - sparse_categorical_accuracy: 0.9291
Epoch 3/10
938/938 [==============================] - 2s 2ms/step - loss: 0.3963 - sparse_categorical_accuracy: 0.9459
Epoch 4/10
938/938 [==============================] - 2s 2ms/step - loss: 0.3349 - sparse_categorical_accuracy: 0.9555
Epoch 5/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2991 - sparse_categorical_accuracy: 0.9609
Epoch 6/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2837 - sparse_categorical_accuracy: 0.9643
Epoch 7/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2512 - sparse_categorical_accuracy: 0.9675
Epoch 8/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2379 - sparse_categorical_accuracy: 0.9701
Epoch 9/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2259 - sparse_categorical_accuracy: 0.9726
Epoch 10/10
938/938 [==============================] - 2s 2ms/step - loss: 0.2051 - sparse_categorical_accuracy: 0.9743

<tensorflow.python.keras.callbacks.History at 0x7f96b4ae30b8>
model.evaluate(test_dataset)
157/157 [==============================] - 0s 2ms/step - loss: 0.4985 - sparse_categorical_accuracy: 0.9615

[0.4984860098452034, 0.9615]