“IF YOU CAN DO WHAT YOU DO BEST AND BE HAPPY, YOU’RE FURTHER ALONG IN LIFE THAN MOST PEOPLE.SO NEVER JUDGE YOUR CAPABILITIES AND NEVER COMPARE WITH OTHERS.”
- By Leonardo DiCaprio
Deep Learning uses various libraries to train the models. Some famous Deep Learning Libraries (in python ) are as follows:
From the above three, I like Tensorflow because of the below reasons.
a)Provides both C++ and Python API that makes it easier to work on.
b)Has a faster compilation time than other Deep Learning libraries like Torch and Keras.
c)Tensorflow supports both CPU’s( Central Processing Unit) and GPU’s( Graphical Processing Unit) computing devices.
What is Tensorflow?
Open Source library developed by GOOGLE.
Developed Originally to run large Numerical Computations.
Accepts data in the form of multidimensional arrays of higher dimensions called Tensors.
Works on the basis of Data Flow Graphs that have nodes and edges.
Tensors:- Tensors is a generalization of vectors and matrices of potentially higher dimensions. An array of data with different dimensions and ranks that are fed as input to the neural network are called Tensors.
Hence TPU’s ( Tensor Processing Unit ) Which is an AI accelerator Application-specific integrated circuit developed by Google Specifically for neural Network Machine also Supported by Tensorflow.
Some Application Of TensorFlow Which are as follows:
Looking the Above Broad Application we can Imagine that it’s Importance in Deep Learning. So All the Deep Learning Aspirants You can start now I’m Providing a short video on Object Detection which makes your interest in TensorFlow.
Happy Machine Learning(TensorFlow)
Author: Vikas Maurya
Originally published at https://knowledgeinai.blogspot.com on February 18, 2019.