TensorFlow 2.0
A tensor:
"A tensor is a generalization of vectors and matrices to potentially higher dimensions. Internally, TensorFlow represents tensors as n-dimensional arrays of base datatype." (https://www.tensorflow.org/guide/tensor)
It shouldn't surprise you that tensors are a fundamental aspect of TensorFlow. They are the main objects that are passed around and manipulated throughout the program. Each tensor represents a partial defined computation that will eventually produce a value. TensorFlow programs work by building a graph of Tensor objects that details how tensors are related. Running different parts of the graph allow results to be generated.
Each tensor has a data type and a shape.
Data Types Include: float32, int32, string and others.
Shape: Represents the dimension of data.
Just like vectors and matrices tensors can have operations applied to them like addition, subtraction, dot product, cross product etc.
In the next sections we will discuss some different properties of tensors. This is to make you more familiar with how tensorflow represents data and how you can manipulate this data.
It shouldn't surprise you that tensors are a fundamental aspect of TensorFlow. They are the main objects that are passed around and manipulated throughout the program. Each tensor represents a partial defined computation that will eventually produce a value. TensorFlow programs work by building a graph of Tensor objects that details how tensors are related. Running different parts of the graph allow results to be generated.
Each tensor has a data type and a shape.
Data Types Include: float32, int32, string and others.
Shape: Represents the dimension of data.
Just like vectors and matrices tensors can have operations applied to them like addition, subtraction, dot product, cross product etc.
In the next sections we will discuss some different properties of tensors. This is to make you more familiar with how tensorflow represents data and how you can manipulate this data.
TensorFlow
The core open source library to help you develop and train ML models.
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.
I have found one nice video on youtube that will help you people to learn TF.
Learn all about Tensorflow with this new 7-hour, information-packed and free course that not only shows how to apply Tensorflow 2.0 in your programs, also teaches the concepts of Machine Learning, AI and their core algorithms. All that in a simple and hands-on way.
While it makes the concepts of ML and AI approachable,this video-based course is not addressed to total beginners at coding as it presumes at least basic knowledge in Python.
Delivered on You Tube by Tim, well known for his Tech with Tim channel, Tensorflow 2.0 In 7 Hours was created in conjunction with FreeCodeCamp. It begins with the simple fundamentals but as it progresses it becomes increasingly involved with more advanced topics, the epitome being that of reinforcement learning. The concepts are demonstrated with practical cases such as applying the algorithms to computer vision and natural language processing code.
Comments
Post a Comment