Created
March 27, 2019 09:49
-
-
Save IlievskiV/2d8cc7c9e8f87589f9aa2a98e5e22b35 to your computer and use it in GitHub Desktop.
Load data using the TensorFlow Dataset API
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tensorflow as tf | |
def make_dataset(): | |
sentences = ['The cat sat on the mat', 'The quick brown fox jumped over the lazy dog'] | |
dataset = tf.data.Dataset.from_tensor_slices(sentences) # | |
dataset = dataset.shuffle(buffer_size=1000) | |
dataset = dataset.map(lambda sentence: text_to_sequence(sentence), num_parallel_calls=4) | |
dataset = dataset.batch(batch_size=32) | |
dataset = dataset.prefetch(1) | |
return dataset | |
def make_iterator(): | |
train_dataset = make_dataset() | |
iterator = tf.data.Iterator.from_structure(output_types=train_dataset.output_types, | |
output_shapes=train_dataset.output_shapes) | |
training_init_op = iterator.make_initializer(train_dataset) | |
return iterator, training_init_op |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment