Gain insights into industry-level machine learning by applying advanced TensorFlow and Python techniques. Explore efficient methods for creating scalable models, from data pipelines to deployment and inference.

AML-DLI.tar.gz

case-study

In this course, you'll level up your skills learned in the Industry Case Study and Machine Learning for Software Engineers. You'll take the modeling and data pipeline concepts and apply them to production-level classification and regression models for industry deployment, while continuing to practice the most efficient techniques for building scalable machine learning models. After this course, you will be able to complete industry-level machine learning projects, from data pipeline creation to model deployment and inference.

The code for this course is built around the TensorFlow framework, one of the premier frameworks for industry machine learning, and the Python pandas library for data analysis. Knowledge of Python and TensorFlow are prerequisites. 

This course was created by AdaptiLab, a company specializing in evaluating, sourcing, and upskilling enterprise machine learning talent. It is built in collaboration with industry machine learning experts from Google, Microsoft, Amazon, and Apple.

Applied Machine Learning: Deep Learning for Industry

# 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.

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` is a dictionary mapping feature names to either a [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) or a [`tf.sparse.SparseTensor`](https://www.tensorflow.org/api_docs/python/tf/sparse/SparseTensor). Each `FixedLenFeature` is converted to a `tf.Tensor` and each `VarLenFeature` is converted to a `tf.SparseTensor`.

A `tf.Tensor` is basically TensorFlow's version of NumPy arrays, meaning it is a container for feature data with a fixed shape. `tf.sparse.SparseTensor` is used to represent data that may have many missing or empty values, making it useful for variable-length features.

In upcoming chapters, we'll discuss how we can combine the `tf.Tensor` and `tf.sparse.SparseTensor` values of the parsed dictionary to create an input layer for a TensorFlow model.

Parse data from serialized protocol buffers.

What you'll learn in this course

Data Pipeline

Model Execution

Parsing

Chapter Goals:

A. Feature parsing