Convolutional Neural Networks (CNNs)
Introduction
In this tutorial we will implement a simple Convolutional Neural Network in TensorFlow with two convolutional layers, followed by two fully-connected layers at the end. The network structure is shown in the following figure and has classification accuracy of above 99% on MNIST data.
Fig1. CNN structure used for digit recognition
Note
-
For the step-by-step explanation of the code, checkout the CNN.
-
You may also clone the whole repo. and open the main.py file (which includes extensive inline comments) to run the network in you IDE of preference (e.g. PyCharm).
-
To learn more about CNNs, we suggest the Stanford's CS231n Convolutional Neural Networks for Visual Recognition Notes and video.