Tensorflow 2.0: Solving Classification and Regression Problems
After much hype, Google finally released TensorFlow 2.0 which is the latest version of Google’s flagship deep learning platform. A lot of long-awaited features have been introduced in TensorFlow 2.0. This article very briefly covers how you can develop simple classification and regression models using TensorFlow 2.0.
Classification with Tensorflow 2.0
If you have ever worked with Keras library, you are in for a treat. TensorFlow 2.0 now uses Keras API as its default library for training classification and regression models. Before TensorFlow 2.0, one of the major criticisms that the earlier versions of TensorFlow had to face stemmed from the complexity of model creation. Previously you need to stitch graphs, sessions and placeholders together in order to create even a simple logistic regression model. With TensorFlow 2.0, creating classification and regression models have become a piece of cake.
So without further ado, let’s develop a classification model with TensorFlow.
The Dataset
The dataset for the classification example can be downloaded freely from this link. Download the file in CSV format. If you open the downloaded CSV file, you will see that the file doesn’t contain any headers. The detail of