In this tutorial, we will:
Explore the MNIST and Fashion MNIST dataset like what it looks like, what are the features available and what we need to predict.
Implement a Simple Linear Classifier using Tensorflow and see how well the classifier performs on these datasets using the decrease in the Cost/Loss Function depicted using a plot w.r.t Epochs and other metrics.
Implement a DNNClassifier using Tensorflow Estimator API and see how easy it is to implement a classifier using Tensorflow Estimator API.
Requirements
- OS: Ubuntu/AWS Cloud/Google Cloud/Windows
- Python 3+
- Tensorflow
- Numpy [+ mkl for Windows]
Just show me the Code !!
The code for this tutorial is available as a iPython notebook here.
So, let's get started.
So, we see from this tutorial that a very simple DNN classifier with just two layers is able to reach an accuracy of 89%.
So, we have reached the end of this tutorial. I hope I was able to make you understand that how we can use Tensorflow and the Estimator API for a Classification task.
For more projects and code, follow me on Github
Please feel free to leave any comments, suggestions, corrections if any :)
comments powered by Disqus