Binary image classification using convolutional neural network (cat-dog example)

Project description:

Input: 4000 labeled images as cat and dog. The set is divided into training, validation and test sets of 1000, 500 and 500 examples of each class, respectively.

Goal: Classifying a new image as cat or dog.

Network model: It is shown in the following figure:

Resulting loss and accuracy are shown in the following figures:

Modification:

To increase the accuracy, data augmentation is used to obtain more training data. Resulting loss and accuracy are shown in the following figures:

The source code of this project is available in my Github page.