pdfcoffee

TensorFlow 1.x and 2.x
In addition, we get the metainfo for MNIST:
tfds.core.DatasetInfo(
name='mnist',
version=1.0.0,
description='The MNIST database of handwritten digits.',
urls=['http://yann.lecun.com/exdb/mnist/'],
features=FeaturesDict({
'image': Image(shape=(28, 28, 1), dtype=tf.uint8),
'label': ClassLabel(shape=(), dtype=tf.int64, num_classes=10)
},
total_num_examples=70000,
splits={
'test': <tfds.core.SplitInfo num_examples=10000>,
'train': <tfds.core.SplitInfo num_examples=60000>
},
supervised_keys=('image', 'label'),
citation='"""
@article{lecun2010mnist,
title={MNIST handwritten digit database},
author={LeCun, Yann and Cortes, Corinna and Burges, CJ},
journal={ATT Labs [Online]. Available: http://yann. lecun.
com/exdb/mnist},
volume={2},
year={2010}
}
)
"""',
Sometimes it is useful to create a dataset from a NumPy array. Let's see how in this
code fragment, which uses tf.data.Dataset.from_tensor_slices():
import tensorflow as tf
import numpy as np
num_items = 100
num_list = np.arange(num_items)
# create the dataset from numpy array
num_list_dataset = tf.data.Dataset.from_tensor_slices(num_list)
We can also download a dataset, shuffle and batch the data, and take a slice from the
generator as shown in this example:
datasets, info = tfds.load('imdb_reviews', with_info=True, as_
[ 70 ]