Classifying Dog and Cat using CNN on Tensorflow 2.x
Problem Statement
Dataset:
The Dogs vs. Cats dataset is a standard computer vision dataset that involves classifying photos as either containing a dog or cat It was only effectively addressed in the last few years using deep learning convolutional neural networks. While the dataset is effectively solved, it can be used as the basis for learning and practicing how to develop, evaluate, and use convolutional deep learning neural networks for image classification
Tasks to be Performed
We will be performing the following tasks:
Prepare the dataset for the model
Install Tensorflow 2.x
Develop convolutional neural network model for classifying the images or Dog Vs cat
Plot the change in accuracy per epochs
Evaluate the model on the testing data
Analyse the model summary
Add Dropout to prevent overfitting and check its effect on accuracy
Increasing the number of Hidden Layers check its effect on accuracy
Manipulate the batch_size and epochs and check its effect on accuracy
Dataset Description
The Dog Vs Cat image classification dataset consists of 8005 images belonging to 2 classes for training images and 2023 images belonging to 2 classes for testing images
Class I = Dog
Class II= Cat