In this tutorial, we will use a neural network model for image recognition. We get our data from Kaggle's dogs-vs-cats competition and use Keras, an easy to use python library for deep learning, to train our model to classify images.
We will go over the following topics:
- How to use a convolutional neural network model already trained on different set of images and change it to make it suitable for our own use.
- How to work with Keras, create batches of images, train and evaluate the accuracy of the image recognition model.
- Building blocks of the image classification model including convolutional and fully connected layers.