Book Image

Python: Advanced Guide to Artificial Intelligence

By : Giuseppe Bonaccorso, Rajalingappaa Shanmugamani
Book Image

Python: Advanced Guide to Artificial Intelligence

By: Giuseppe Bonaccorso, Rajalingappaa Shanmugamani

Overview of this book

This Learning Path is your complete guide to quickly getting to grips with popular machine learning algorithms. You'll be introduced to the most widely used algorithms in supervised, unsupervised, and semi-supervised machine learning, and learn how to use them in the best possible manner. Ranging from Bayesian models to the MCMC algorithm to Hidden Markov models, this Learning Path will teach you how to extract features from your dataset and perform dimensionality reduction by making use of Python-based libraries. You'll bring the use of TensorFlow and Keras to build deep learning models, using concepts such as transfer learning, generative adversarial networks, and deep reinforcement learning. Next, you'll learn the advanced features of TensorFlow1.x, such as distributed TensorFlow with TF clusters, deploy production models with TensorFlow Serving. You'll implement different techniques related to object classification, object detection, image segmentation, and more. By the end of this Learning Path, you'll have obtained in-depth knowledge of TensorFlow, making you the go-to person for solving artificial intelligence problems This Learning Path includes content from the following Packt products: • Mastering Machine Learning Algorithms by Giuseppe Bonaccorso • Mastering TensorFlow 1.x by Armando Fandango • Deep Learning for Computer Vision by Rajalingappaa Shanmugamani
Table of Contents (31 chapters)
Title Page
About Packt
Tensor Processing Units

Asserting on conditions with tf.Assert()

Yet another way to debug TensorFlow models is to insert conditional asserts. The tf.Assert() function takes a condition, and if the condition is false, it then prints the lists of given tensors and throws tf.errors.InvalidArgumentError.

  1. The tf.Assert() function has the following signature:
  1. An assert operation does not fall in the path of the graph like the tf.Print() function. To make sure that the tf.Assert() operation gets executed, we need to add it to the dependencies. For example, let us define an assertion to check that all the inputs are positive:
assert_op = tf.Assert(tf.reduce_all(tf.greater_equal(x,0)),[x])
  1. Addassert_op to the dependencies at the time of defining the model, as follows:
with tf.control_dependencies([assert_op]):
# x is input layer
layer = x
# add hidden layers
for i in range(num_layers):
        layer = tf.nn.relu(tf.matmul(layer, w[i]) + b[i])
# add output layer