Convolution Neural Network for Dog and Cats Recognition

Model contains a basic recognizer using Keras Library with Tensorflow in backend.

Introduction

Here is a Simple CNN that achieves over 84% Accuracy of Training set and 75% Accuracy of Test set. By adding 2nd Convolution layer we increase the Accuracy of Training set over 85% and Test set 82%.

Steps

• Convolution2D Layer
• MaxPool2D Layer
• Flatten Layer
• Dense Layer
• Compiling the CNN
• Fitting the CNN to the images

---

Setups

Step 1 — Create New Conda Environment
•conda create -n py35 python=3.5 anaconda
Step 2 — Install Spyder in the New Environment
Step 3 — Install the Packages
•conda install theano
•conda install tensorflow
•conda install keras
Step 4 — Run Spyder from the Environment
Step 5 — Test the Packages