Search⌘ K
AI Features
Home
Courses
Applied Machine Learning: Deep Learning for Industry

Parsing

Understand the process of parsing serialized protocol buffers with TensorFlow's parsing functions. Learn to convert serialized data into feature dictionaries, handle fixed and variable-length features, and control output selection. This lesson helps you implement robust parsing functions as part of scalable data pipelines for machine learning models.

We'll cover the following...

Chapter Goals:

  • Learn how to parse a serialized protocol buffer
  • Understand how feature data is represented in TensorFlow
  • Implement a function that parses a serialized protocol buffer

A. Feature parsing

After creating an Example spec, it can be used to parse serialized protocol buffers that are read from a TFRecords file. Specifically, we use the Example spec as an argument to the tf.io.parse_single_example function, which converts a serialized protocol buffer into a usable feature dictionary.

Python 3.5
import tensorflow as tf
print(example_spec)
print(repr(ex))
parsed = tf.io.parse_single_example(
    ex.SerializeToString(), example_spec)
print(repr(parsed))

You’ll notice that the output of tf.io.parse_single_example ...