1. Constants and variables
Hi! My name is Isaiah Hull and this is a course on the fundamentals of the TensorFlow API in Python. In our first video, we will briefly introduce TensorFlow and then discuss its two basic objects of computation: constants and variables.
2. What is TensorFlow?
TensorFlow is an open-source library for graph-based numerical computation.
It was developed by the Google Brain Team.
It has both low and high level APIs.
You can use TensorFlow to perform addition, multiplication, and differentiation.
You can also use it to design and train machine learning models.
TensorFlow two point zero brought with it substantial changes.
Eager execution is now enabled by default, which allows users to write simpler and more intuitive code.
Additionally, model building is now centered around the Keras and Estimators high-level APIs.
3. What is a tensor?
The TensorFlow documentation describes a tensor as "a generalization of vectors and matrices to potentially higher dimensions." Now, if you are not familiar with linear algebra, you can simply think of a tensor as a collection of numbers, which is arranged into a particular shape.
4. What is a tensor?
As an example, let's say you have a slice of bread and you cut it into 9 pieces. One of those 9 pieces is a 0-dimensional tensor. This corresponds to a single number. A collection of 3 pieces that form a row or column is a 1-dimensional tensor. All 9 pieces together are a 2-dimensional tensor. And the whole loaf, which contains many slices, is a 3-dimensional tensor.
5. Defining tensors in TensorFlow
Now that you know what a tensor is, let's define a few. We will start by importing tensorflow as tf. We will then define 0-, 1-, 2-, and 3-dimensional tensors.
Note that each object will be a tf dot Tensor object.
6. Defining tensors in TensorFlow
If we want to print the array contained in that object, we can apply the dot numpy method and pass the resulting object to the print function.
7. Defining constants in TensorFlow
We next move on to constants, which are the simplest category of tensor in TensorFlow.
A constant does not change and cannot be trained.
It can, however, have any dimension.
In the code block, we've defined two constants. The constant a is a 2x3 tensor of 3s.
The constant b is a 2x2 tensor, which is constructed from the 1-dimensional tensor: 1, 2, 3, 4.
8. Using convenience functions to define constants
In the previous slide, we worked exclusively with the constant operation. However, in some cases, there are more convenient options for defining certain types of special tensors. You can use the zeros or ones operations to generate a tensor of arbitrary dimension that is populated entirely with zeros or ones. You can use the zeros_like or ones_like operations to populate tensors with zeros and ones, copying the dimension of some input tensor. Finally, you can use the fill operation to populate a tensor of arbitrary dimension with the same scalar value in each element.
9. Defining and initializing variables
Unlike a constant, a variable's value can change during computation. The value of a variable is shared, persistent, and modifiable. However, its data type and shape are fixed.
Let's take a look at how variables are constructed and used in TensorFlow. In the code, we first define a variable, a0, which is a 1-dimensional tensor with 6 elements. We can set its datatype to a 32-bit float or something else, such as a 16-bit int, as we have for a1.
We then define a constant, b.
And define c0 as the product of a0 and b. Note that certain TensorFlow operations, such as tf.multiply are overloaded, which allows us to use the simpler a0*b expression instead.
10. Let's practice!
It's now time to put what you've learned to use in some exercises.