Probabilistic Deep Learning: With Python, Keras and TensorFlow Probability MEAP V06 by unknow

Author:unknow
Language: eng
Format: epub
Publisher: Manning Publications Co.
Published: 2020-05-11T22:00:00+00:00

Step through the notebook while reading.

https://github.com/tensorchiefs/dl_book/blob/master/chapter_05/nb_ch05_01.ipynb

Because probability distributions are the main tool for capturing uncertainties in probabilistic models, let’s check out how to work with a TFP distribution. TFP provides a quickly growing collection of distributions. The Normal distribution is the distribution family that you’re probably most familiar with, so let’s start with defining a Normal distribution from TFP. We’ll sample from it and determine the likelihood of the sampled values (see listing 5.1):

Listing 5.1: Working with a TFP Normal distribution

import tensorflow_probability as tfp

tfd = tfp.distributions

d = tfd.Normal(loc=[3], scale=1.5) #A

x = d.sample(2) # Draw two random points. #B

px = d.prob(x) # Compute density/mass. #C

print(x)

print(px)

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.